{"catalog":{"changes":[],"entries":{"[\"kilo\",\"aion-labs/aion-2.0\"]":{"classification":"paid","cost":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000002","prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-2.0","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","expiration_date":null,"id":"aion-labs/aion-2.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-2.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000002","prompt":"0.0000008"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion-2.0","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","expiration_date":null,"id":"aion-labs/aion-2.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-2.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000002","prompt":"0.0000008"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"aion-labs/aion-3.0\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-3.0","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","expiration_date":null,"id":"aion-labs/aion-3.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion-3.0","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","expiration_date":null,"id":"aion-labs/aion-3.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"aion-labs/aion-3.0-mini\"]":{"classification":"paid","cost":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-3.0-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.0-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0-Mini","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion-3.0-Mini","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.0-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0-Mini","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"aion-labs/aion-3.5\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-3.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.5","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion 3.5","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.5","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"aion-labs/aion-3.5-mini\"]":{"classification":"paid","cost":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-3.5-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","expiration_date":null,"id":"aion-labs/aion-3.5-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5 Mini","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion 3.5 Mini","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","expiration_date":null,"id":"aion-labs/aion-3.5-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5 Mini","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"aion-labs/aion-rp-llama-3.1-8b\"]":{"classification":"paid","cost":{"completion":"0.0000016","discount":0,"prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"aion-labs/aion-rp-llama-3.1-8b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","expiration_date":null,"id":"aion-labs/aion-rp-llama-3.1-8b","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-RP 1.0 (8B)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"AionLabs: Aion-RP 1.0 (8B)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","expiration_date":null,"id":"aion-labs/aion-rp-llama-3.1-8b","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-RP 1.0 (8B)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"amazon/nova-2-lite-v1\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"amazon/nova-2-lite-v1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","expiration_date":null,"id":"amazon/nova-2-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova 2 Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":65535}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Amazon: Nova 2 Lite","raw":{"architecture":{"input_modalities":["text","image","video","file"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","expiration_date":null,"id":"amazon/nova-2-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova 2 Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":65535}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"amazon/nova-lite-v1\"]":{"classification":"paid","cost":{"completion":"0.00000024","discount":0,"prompt":"0.00000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"amazon/nova-lite-v1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","expiration_date":null,"id":"amazon/nova-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Lite 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000006"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Amazon: Nova Lite 1.0","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","expiration_date":null,"id":"amazon/nova-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Lite 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000006"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"amazon/nova-micro-v1\"]":{"classification":"paid","cost":{"completion":"0.00000014","discount":0,"prompt":"0.000000035"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"amazon/nova-micro-v1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":128000,"created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","expiration_date":null,"id":"amazon/nova-micro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Micro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000014","discount":0,"prompt":"0.000000035"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":5120}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Amazon: Nova Micro 1.0","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":128000,"created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","expiration_date":null,"id":"amazon/nova-micro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Micro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000014","discount":0,"prompt":"0.000000035"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":5120}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"amazon/nova-premier-v1\"]":{"classification":"paid","cost":{"completion":"0.0000125","discount":0,"input_cache_read":"0.000000625","prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"amazon/nova-premier-v1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","expiration_date":null,"id":"amazon/nova-premier-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Premier 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000125","discount":0,"input_cache_read":"0.000000625","prompt":"0.0000025"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":32000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Amazon: Nova Premier 1.0","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","expiration_date":null,"id":"amazon/nova-premier-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Premier 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000125","discount":0,"input_cache_read":"0.000000625","prompt":"0.0000025"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":32000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"amazon/nova-pro-v1\"]":{"classification":"paid","cost":{"completion":"0.0000032","discount":0,"prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"amazon/nova-pro-v1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","expiration_date":null,"id":"amazon/nova-pro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Pro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Amazon: Nova Pro 1.0","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","expiration_date":null,"id":"amazon/nova-pro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Pro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthracite-org/magnum-v4-72b\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthracite-org/magnum-v4-72b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","expiration_date":null,"id":"anthracite-org/magnum-v4-72b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Magnum v4 72B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Magnum v4 72B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","expiration_date":null,"id":"anthracite-org/magnum-v4-72b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Magnum v4 72B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-fable-5\"]":{"classification":"paid","cost":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-fable-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","enkrypt":{"bias_score":0,"cbrn_score":0,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":0,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-fable-5","nist_score":0,"owasp_score":0,"provider":"anthropic","risk_score":0,"robustness_score":null,"safety_score":0,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"anthropic/claude-fable-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.5169082,"overallScore":0.71011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Fable 5 ($$$$)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","enkrypt":{"bias_score":0,"cbrn_score":0,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":0,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-fable-5","nist_score":0,"owasp_score":0,"provider":"anthropic","risk_score":0,"robustness_score":null,"safety_score":0,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"anthropic/claude-fable-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.5169082,"overallScore":0.71011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-fable-5.1\"]":{"classification":"paid","cost":{"completion":"0.00005","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-fable-5.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","expiration_date":null,"id":"anthropic/claude-fable-5.1","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":91.4074256,"overallScore":0.76179775},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Fable 5.1 ($$$$)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","expiration_date":null,"id":"anthropic/claude-fable-5.1","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":91.4074256,"overallScore":0.76179775},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-haiku-4.5\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-haiku-4.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","expiration_date":null,"id":"anthropic/claude-haiku-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Haiku 4.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","expiration_date":null,"id":"anthropic/claude-haiku-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-haiku-5.5\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-haiku-5.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","expiration_date":null,"id":"anthropic/claude-haiku-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Haiku 5.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","expiration_date":null,"id":"anthropic/claude-haiku-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-4.1\"]":{"classification":"paid","cost":{"completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","prompt":"0.000015","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-4.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","expiration_date":null,"id":"anthropic/claude-opus-4.1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":32000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 4.1 ($$$$)","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","expiration_date":null,"id":"anthropic/claude-opus-4.1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":32000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-4.5\"]":{"classification":"paid","cost":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-4.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","expiration_date":null,"id":"anthropic/claude-opus-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 4.5","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","expiration_date":null,"id":"anthropic/claude-opus-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-4.6\"]":{"classification":"paid","cost":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-4.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","expiration_date":null,"id":"anthropic/claude-opus-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 4.6","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","expiration_date":null,"id":"anthropic/claude-opus-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-4.7\"]":{"classification":"paid","cost":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-4.7","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","enkrypt":{"bias_score":76.49,"cbrn_score":3.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.78,"jailbreak_score":1.72662,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-7","nist_score":20,"owasp_score":26,"provider":"anthropic","risk_score":19.9881,"robustness_score":null,"safety_score":28.4683,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"anthropic/claude-opus-4.7","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.7","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":100.5076156,"overallScore":0.7011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 4.7","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","enkrypt":{"bias_score":76.49,"cbrn_score":3.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.78,"jailbreak_score":1.72662,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-7","nist_score":20,"owasp_score":26,"provider":"anthropic","risk_score":19.9881,"robustness_score":null,"safety_score":28.4683,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"anthropic/claude-opus-4.7","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.7","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":100.5076156,"overallScore":0.7011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-4.8\"]":{"classification":"paid","cost":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-4.8","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","enkrypt":{"bias_score":48.06,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":24.89,"jailbreak_score":3.02158,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-8","nist_score":16,"owasp_score":21,"provider":"anthropic","risk_score":16.4467,"robustness_score":null,"safety_score":21.9727,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.73},"expiration_date":null,"id":"anthropic/claude-opus-4.8","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.8","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":85.194714,"overallScore":0.67640449},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 4.8","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","enkrypt":{"bias_score":48.06,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":24.89,"jailbreak_score":3.02158,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-8","nist_score":16,"owasp_score":21,"provider":"anthropic","risk_score":16.4467,"robustness_score":null,"safety_score":21.9727,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.73},"expiration_date":null,"id":"anthropic/claude-opus-4.8","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.8","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":85.194714,"overallScore":0.67640449},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-5\"]":{"classification":"paid","cost":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","enkrypt":{"bias_score":40.83,"cbrn_score":25.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-5","nist_score":14,"owasp_score":15,"provider":"openai_compatible","risk_score":13.8351,"robustness_score":null,"safety_score":19.4868,"source":"Anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.18},"expiration_date":null,"id":"anthropic/claude-opus-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":113.5366288,"overallScore":0.71460674},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","enkrypt":{"bias_score":40.83,"cbrn_score":25.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-5","nist_score":14,"owasp_score":15,"provider":"openai_compatible","risk_score":13.8351,"robustness_score":null,"safety_score":19.4868,"source":"Anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.18},"expiration_date":null,"id":"anthropic/claude-opus-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":113.5366288,"overallScore":0.71460674},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-opus-5.5\"]":{"classification":"paid","cost":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-opus-5.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","expiration_date":null,"id":"anthropic/claude-opus-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"preferredIndex":5,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus 5.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","expiration_date":null,"id":"anthropic/claude-opus-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"preferredIndex":5,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-sonnet-4.5\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-sonnet-4.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","expiration_date":null,"id":"anthropic/claude-sonnet-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Sonnet 4.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","expiration_date":null,"id":"anthropic/claude-sonnet-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-sonnet-4.6\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-sonnet-4.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","enkrypt":{"bias_score":81.14,"cbrn_score":15.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":32.89,"jailbreak_score":null,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-4-6","nist_score":32,"owasp_score":39,"provider":"anthropic","risk_score":32.4787,"robustness_score":null,"safety_score":null,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":null},"expiration_date":null,"id":"anthropic/claude-sonnet-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"terminalBench":{"avgAttemptCostUsd":53.374126600000004,"overallScore":0.5505618},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Sonnet 4.6","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","enkrypt":{"bias_score":81.14,"cbrn_score":15.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":32.89,"jailbreak_score":null,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-4-6","nist_score":32,"owasp_score":39,"provider":"anthropic","risk_score":32.4787,"robustness_score":null,"safety_score":null,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":null},"expiration_date":null,"id":"anthropic/claude-sonnet-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"terminalBench":{"avgAttemptCostUsd":53.374126600000004,"overallScore":0.5505618},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-sonnet-5\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-sonnet-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","enkrypt":{"bias_score":29.46,"cbrn_score":7.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":2.01439,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-5","nist_score":9,"owasp_score":11,"provider":"anthropic","risk_score":9.20561,"robustness_score":null,"safety_score":13.3119,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.18},"expiration_date":null,"id":"anthropic/claude-sonnet-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":36.186279799999994,"overallScore":0.59550562},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Sonnet 5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","enkrypt":{"bias_score":29.46,"cbrn_score":7.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":2.01439,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-5","nist_score":9,"owasp_score":11,"provider":"anthropic","risk_score":9.20561,"robustness_score":null,"safety_score":13.3119,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.18},"expiration_date":null,"id":"anthropic/claude-sonnet-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":36.186279799999994,"overallScore":0.59550562},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"anthropic/claude-sonnet-5.5\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"anthropic/claude-sonnet-5.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","expiration_date":null,"id":"anthropic/claude-sonnet-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Sonnet 5.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","expiration_date":null,"id":"anthropic/claude-sonnet-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"arcee-ai/trinity-large-thinking\"]":{"classification":"paid","cost":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"arcee-ai/trinity-large-thinking","lastListed":"2026-10-26T12:50:18.846Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1775058318,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","expiration_date":"2026-10-26","id":"arcee-ai/trinity-large-thinking","inference_provider_ids":["arcee-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Arcee AI: Trinity Large Thinking (retires Oct 26)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":80000}},"metadataProvenance":{"fetchedAt":"2026-10-26T12:50:18.846Z","source":"kilo"},"metadataRetained":true,"name":"Arcee AI: Trinity Large Thinking (retires Oct 26)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1775058318,"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","expiration_date":"2026-10-26","id":"arcee-ai/trinity-large-thinking","inference_provider_ids":["arcee-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Arcee AI: Trinity Large Thinking (retires Oct 26)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":80000}},"retirementDates":["2026-10-26"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-1.6\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-1.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":["2026-11-11"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-1.6-flash\"]":{"classification":"paid","cost":{"completion":"0.0000003","discount":0,"prompt":"0.000000075"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-1.6-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6-flash","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6-flash","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":["2026-11-11"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-2-1-turbo\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-2-1-turbo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","expiration_date":null,"id":"bytedance-seed/seed-2-1-turbo","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 2.1 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed 2.1 Turbo","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","expiration_date":null,"id":"bytedance-seed/seed-2-1-turbo","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 2.1 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-2.0-code\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-2.0-code","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-2.0-code","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Code (retires Nov 11)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed-2.0-Code (retires Nov 11)","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-2.0-code","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Code (retires Nov 11)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-11-11"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-2.0-lite\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-2.0-lite","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","expiration_date":null,"id":"bytedance-seed/seed-2.0-lite","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed-2.0-Lite","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","expiration_date":null,"id":"bytedance-seed/seed-2.0-lite","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance-seed/seed-2.0-mini\"]":{"classification":"paid","cost":{"completion":"0.0000004","discount":0,"prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance-seed/seed-2.0-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","expiration_date":null,"id":"bytedance-seed/seed-2.0-mini","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance Seed: Seed-2.0-Mini","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","expiration_date":null,"id":"bytedance-seed/seed-2.0-mini","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"bytedance/ui-tars-1.5-7b\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bytedance/ui-tars-1.5-7b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","expiration_date":null,"id":"bytedance/ui-tars-1.5-7b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance: UI-TARS 7B ","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":2048}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ByteDance: UI-TARS 7B ","raw":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","expiration_date":null,"id":"bytedance/ui-tars-1.5-7b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance: UI-TARS 7B ","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":2048}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cognitivecomputations/dolphin-mistral-24b-venice-edition\"]":{"classification":"paid","cost":{"completion":"0.0000009","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","expiration_date":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Venice: Uncensored","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Venice: Uncensored","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","expiration_date":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Venice: Uncensored","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/command-a\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/command-a","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","expiration_date":null,"id":"cohere/command-a","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: Command A","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","expiration_date":null,"id":"cohere/command-a","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/command-a-plus\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/command-a-plus","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":192000,"created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","expiration_date":null,"id":"cohere/command-a-plus","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A+","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tools","top_k","top_p"],"top_provider":{"context_length":192000,"is_moderated":true,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: Command A+","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":192000,"created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","expiration_date":null,"id":"cohere/command-a-plus","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A+","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tools","top_k","top_p"],"top_provider":{"context_length":192000,"is_moderated":true,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/command-r-08-2024\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/command-r-08-2024","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","expiration_date":null,"id":"cohere/command-r-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: Command R (08-2024)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","expiration_date":null,"id":"cohere/command-r-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/command-r-plus-08-2024\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/command-r-plus-08-2024","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","enkrypt":{"bias_score":98.71,"cbrn_score":9.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":60,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":86.67,"jailbreak_score":6.71053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r-plus-08-2024","nist_score":53,"owasp_score":62,"provider":"cohere","risk_score":52.9355,"robustness_score":null,"safety_score":41.5541,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.14},"expiration_date":null,"id":"cohere/command-r-plus-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R+ (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: Command R+ (08-2024)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","enkrypt":{"bias_score":98.71,"cbrn_score":9.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":60,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":86.67,"jailbreak_score":6.71053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r-plus-08-2024","nist_score":53,"owasp_score":62,"provider":"cohere","risk_score":52.9355,"robustness_score":null,"safety_score":41.5541,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.14},"expiration_date":null,"id":"cohere/command-r-plus-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R+ (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/command-r7b-12-2024\"]":{"classification":"paid","cost":{"completion":"0.00000015","discount":0,"prompt":"0.0000000375"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/command-r7b-12-2024","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","enkrypt":{"bias_score":99.48,"cbrn_score":28.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":55,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.56,"jailbreak_score":12.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r7b-12-2024","nist_score":41,"owasp_score":44,"provider":"cohere","risk_score":40.632,"robustness_score":null,"safety_score":29.1988,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.45},"expiration_date":null,"id":"cohere/command-r7b-12-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R7B (12-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"prompt":"0.0000000375"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: Command R7B (12-2024)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","enkrypt":{"bias_score":99.48,"cbrn_score":28.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":55,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.56,"jailbreak_score":12.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r7b-12-2024","nist_score":41,"owasp_score":44,"provider":"cohere","risk_score":40.632,"robustness_score":null,"safety_score":29.1988,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.45},"expiration_date":null,"id":"cohere/command-r7b-12-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R7B (12-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"prompt":"0.0000000375"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"cohere/north-mini-code:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"cohere/north-mini-code:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":256000,"created":1781723748,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","expiration_date":null,"id":"cohere/north-mini-code:free","inference_provider_ids":["cohere"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Cohere: North Mini Code (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Cohere: North Mini Code (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":256000,"created":1781723748,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","expiration_date":null,"id":"cohere/north-mini-code:free","inference_provider_ids":["cohere"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Cohere: North Mini Code (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"deepseek/deepseek-chat\"]":{"classification":"paid","cost":{"completion":"0.0000010287","prompt":"0.0000002574"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-chat","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","enkrypt":{"bias_score":85.27,"cbrn_score":8.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":26.67,"jailbreak_score":9.07895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-chat","nist_score":34,"owasp_score":38,"provider":"deepseek","risk_score":33.7785,"robustness_score":null,"safety_score":25.1931,"source":"deepseek-chat","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.45},"expiration_date":null,"id":"deepseek/deepseek-chat","inference_provider_ids":["deepinfra","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000010287","prompt":"0.0000002574"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","enkrypt":{"bias_score":85.27,"cbrn_score":8.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":26.67,"jailbreak_score":9.07895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-chat","nist_score":34,"owasp_score":38,"provider":"deepseek","risk_score":33.7785,"robustness_score":null,"safety_score":25.1931,"source":"deepseek-chat","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.45},"expiration_date":null,"id":"deepseek/deepseek-chat","inference_provider_ids":["deepinfra","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000010287","prompt":"0.0000002574"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-chat-v3-0324\"]":{"classification":"paid","cost":{"completion":"0.00000114","input_cache_read":"0.00000011","prompt":"0.00000029"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-chat-v3-0324","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","expiration_date":null,"id":"deepseek/deepseek-chat-v3-0324","inference_provider_ids":["gmicloud","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3 0324","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000114","input_cache_read":"0.00000011","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3 0324","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","expiration_date":null,"id":"deepseek/deepseek-chat-v3-0324","inference_provider_ids":["gmicloud","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3 0324","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000114","input_cache_read":"0.00000011","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-chat-v3.1\"]":{"classification":"paid","cost":{"completion":"0.00000095","input_cache_read":"0.00000013","prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-chat-v3.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","expiration_date":null,"id":"deepseek/deepseek-chat-v3.1","inference_provider_ids":["coreweave","deepinfra","sambanova","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000095","input_cache_read":"0.00000013","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3.1","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","expiration_date":null,"id":"deepseek/deepseek-chat-v3.1","inference_provider_ids":["coreweave","deepinfra","sambanova","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000095","input_cache_read":"0.00000013","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-r1-0528\"]":{"classification":"paid","cost":{"completion":"0.00000215","input_cache_read":"0.00000035","prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-r1-0528","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","enkrypt":{"bias_score":74.94,"cbrn_score":53.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":57.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":73.78,"jailbreak_score":27.1711,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-r1-0528","nist_score":52,"owasp_score":57,"provider":"fireworks","risk_score":52.4164,"robustness_score":null,"safety_score":24.8069,"source":"accounts","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"deepseek/deepseek-r1-0528","inference_provider_ids":["deepinfra","siliconflow","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: R1 0528","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000215","input_cache_read":"0.00000035","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: R1 0528","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","enkrypt":{"bias_score":74.94,"cbrn_score":53.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":57.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":73.78,"jailbreak_score":27.1711,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-r1-0528","nist_score":52,"owasp_score":57,"provider":"fireworks","risk_score":52.4164,"robustness_score":null,"safety_score":24.8069,"source":"accounts","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"deepseek/deepseek-r1-0528","inference_provider_ids":["deepinfra","siliconflow","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: R1 0528","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000215","input_cache_read":"0.00000035","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v3.1-terminus\"]":{"classification":"paid","cost":{"completion":"0.000001","prompt":"0.00000027"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v3.1-terminus","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","expiration_date":null,"id":"deepseek/deepseek-v3.1-terminus","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1 Terminus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3.1 Terminus","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","expiration_date":null,"id":"deepseek/deepseek-v3.1-terminus","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1 Terminus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v3.2\"]":{"classification":"paid","cost":{"completion":"0.00000038","input_cache_read":"0.00000013","prompt":"0.00000026"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v3.2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","expiration_date":null,"id":"deepseek/deepseek-v3.2","inference_provider_ids":["amazon-bedrock","atlas-cloud","baidu","deepinfra","digitalocean","gmicloud","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000038","input_cache_read":"0.00000013","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3.2","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","expiration_date":null,"id":"deepseek/deepseek-v3.2","inference_provider_ids":["amazon-bedrock","atlas-cloud","baidu","deepinfra","digitalocean","gmicloud","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000038","input_cache_read":"0.00000013","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v3.2-exp\"]":{"classification":"paid","cost":{"completion":"0.00000041","prompt":"0.00000027"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v3.2-exp","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","enkrypt":{"bias_score":77,"cbrn_score":18.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":53.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.22,"jailbreak_score":23.8849,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v3.2-exp","nist_score":34,"owasp_score":37,"provider":"novita","risk_score":34.5025,"robustness_score":null,"safety_score":32.8789,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"deepseek/deepseek-v3.2-exp","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2 Exp","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000041","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V3.2 Exp","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","enkrypt":{"bias_score":77,"cbrn_score":18.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":53.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.22,"jailbreak_score":23.8849,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v3.2-exp","nist_score":34,"owasp_score":37,"provider":"novita","risk_score":34.5025,"robustness_score":null,"safety_score":32.8789,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"deepseek/deepseek-v3.2-exp","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2 Exp","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000041","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4-flash\"]":{"classification":"paid","cost":{"completion":"0.000000182","input_cache_read":"0.0000000182","prompt":"0.000000091"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","enkrypt":{"bias_score":85.27,"cbrn_score":29.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":23.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":21.0072,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-flash","nist_score":36,"owasp_score":41,"provider":"novita","risk_score":36.2603,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.36},"expiration_date":null,"id":"deepseek/deepseek-v4-flash","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","digitalocean","fireworks","gmicloud","mancer","novita","parasail","relace","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000182","input_cache_read":"0.0000000182","prompt":"0.000000091"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Flash 0423","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","enkrypt":{"bias_score":85.27,"cbrn_score":29.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":23.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":21.0072,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-flash","nist_score":36,"owasp_score":41,"provider":"novita","risk_score":36.2603,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.36},"expiration_date":null,"id":"deepseek/deepseek-v4-flash","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","digitalocean","fireworks","gmicloud","mancer","novita","parasail","relace","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000182","input_cache_read":"0.0000000182","prompt":"0.000000091"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4-flash-0731\"]":{"classification":"paid","cost":{"completion":"0.000001320000","input_cache_read":"0.000000028000","prompt":"0.000000440000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4-flash-0731","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","expiration_date":null,"id":"deepseek/deepseek-v4-flash-0731","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0731","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001320000","input_cache_read":"0.000000028000","prompt":"0.000000440000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Flash 0731","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","expiration_date":null,"id":"deepseek/deepseek-v4-flash-0731","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0731","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001320000","input_cache_read":"0.000000028000","prompt":"0.000000440000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4-flash-vision-exp\"]":{"classification":"paid","cost":{"completion":"0.0000006468","input_cache_read":"0.00000000686","prompt":"0.0000002156"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4-flash-vision-exp","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","expiration_date":null,"id":"deepseek/deepseek-v4-flash-vision-exp","inference_provider_ids":["deepinfra","gmicloud","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006468","input_cache_read":"0.00000000686","prompt":"0.0000002156"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","expiration_date":null,"id":"deepseek/deepseek-v4-flash-vision-exp","inference_provider_ids":["deepinfra","gmicloud","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006468","input_cache_read":"0.00000000686","prompt":"0.0000002156"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4-pro\"]":{"classification":"paid","cost":{"completion":"0.0000032","discount":0,"input_cache_read":"0.000000135","prompt":"0.0000016"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","enkrypt":{"bias_score":85.27,"cbrn_score":17.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":22.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":33.78,"jailbreak_score":9.06475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-pro","nist_score":33,"owasp_score":39,"provider":"novita","risk_score":33.2118,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.45},"expiration_date":null,"id":"deepseek/deepseek-v4-pro","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","deepseek","digitalocean","gmicloud","nebius","novita","relace","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.000000135","prompt":"0.0000016"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":15.908566,"overallScore":0.44044944},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Pro 0423","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","enkrypt":{"bias_score":85.27,"cbrn_score":17.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":22.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":33.78,"jailbreak_score":9.06475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-pro","nist_score":33,"owasp_score":39,"provider":"novita","risk_score":33.2118,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.45},"expiration_date":null,"id":"deepseek/deepseek-v4-pro","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","deepseek","digitalocean","gmicloud","nebius","novita","relace","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.000000135","prompt":"0.0000016"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":15.908566,"overallScore":0.44044944},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4-pro-0813\"]":{"classification":"paid","cost":{"completion":"0.000003960000","input_cache_read":"0.000000044000","prompt":"0.000001320000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4-pro-0813","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","expiration_date":null,"id":"deepseek/deepseek-v4-pro-0813","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0813","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003960000","input_cache_read":"0.000000044000","prompt":"0.000001320000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Pro 0813","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","expiration_date":null,"id":"deepseek/deepseek-v4-pro-0813","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0813","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003960000","input_cache_read":"0.000000044000","prompt":"0.000001320000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4.1-flash\"]":{"classification":"paid","cost":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4.1-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cohere","coreweave","crusoe","deepinfra","deepseek","digitalocean","fireworks","gmicloud","google-vertex","inference-net","makora","mancer","modal","morph","nebius","novita","open-inference","parasail","pareto","particle","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":2.5831196000000003,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4.1 Flash","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cohere","coreweave","crusoe","deepinfra","deepseek","digitalocean","fireworks","gmicloud","google-vertex","inference-net","makora","mancer","modal","morph","nebius","novita","open-inference","parasail","pareto","particle","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":2.5831196000000003,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"deepseek/deepseek-v4.1-flash-1017\"]":{"classification":"paid","cost":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"deepseek/deepseek-v4.1-flash-1017","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash-1017","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash 1017","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"preferredIndex":7,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4.1 Flash 1017","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash-1017","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash 1017","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"preferredIndex":7,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"dots-studio/dots-3-note-preview:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"dots-studio/dots-3-note-preview:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":512000,"created":1786680361,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","expiration_date":"2026-12-31","id":"dots-studio/dots-3-note-preview:free","inference_provider_ids":["atlas-cloud"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Dots Studio: Dots3-Note Preview (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":512000,"is_moderated":false,"max_completion_tokens":460800}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Dots Studio: Dots3-Note Preview (free)","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":512000,"created":1786680361,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","expiration_date":"2026-12-31","id":"dots-studio/dots-3-note-preview:free","inference_provider_ids":["atlas-cloud"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Dots Studio: Dots3-Note Preview (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":512000,"is_moderated":false,"max_completion_tokens":460800}},"retirementDates":["2026-12-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"elorian/glimpse\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"elorian/glimpse","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","expiration_date":null,"id":"elorian/glimpse","inference_provider_ids":["elorian","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Elorian: Glimpse","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":256000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Elorian: Glimpse","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","expiration_date":null,"id":"elorian/glimpse","inference_provider_ids":["elorian","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Elorian: Glimpse","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":256000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"fireworks/ember-1\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","prompt":"0.000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"fireworks/ember-1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","expiration_date":null,"id":"fireworks/ember-1","inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Fireworks: Ember-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Fireworks: Ember-1","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","expiration_date":null,"id":"fireworks/ember-1","inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Fireworks: Ember-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-2.5-flash\"]":{"classification":"paid","cost":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-2.5-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","enkrypt":{"bias_score":75.16,"cbrn_score":15.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45.37,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.38,"jailbreak_score":27.1429,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-flash","nist_score":32,"owasp_score":35,"provider":"gemini","risk_score":32.0541,"robustness_score":null,"safety_score":32.1138,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.52},"expiration_date":null,"id":"google/gemini-2.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 2.5 Flash","raw":{"architecture":{"input_modalities":["file","image","text","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","enkrypt":{"bias_score":75.16,"cbrn_score":15.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45.37,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.38,"jailbreak_score":27.1429,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-flash","nist_score":32,"owasp_score":35,"provider":"gemini","risk_score":32.0541,"robustness_score":null,"safety_score":32.1138,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.52},"expiration_date":null,"id":"google/gemini-2.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-2.5-flash-image\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","internal_reasoning":"0.0000025","prompt":"0.0000003","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-2.5-flash-image","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":32768,"created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","expiration_date":null,"id":"google/gemini-2.5-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","internal_reasoning":"0.0000025","prompt":"0.0000003","web_search":"0.014"},"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":32768,"created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","expiration_date":null,"id":"google/gemini-2.5-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","internal_reasoning":"0.0000025","prompt":"0.0000003","web_search":"0.014"},"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-2.5-flash-lite\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"image":"0.00000005","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000002","prompt":"0.00000005","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-2.5-flash-lite","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","expiration_date":null,"id":"google/gemini-2.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"image":"0.00000005","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000002","prompt":"0.00000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 2.5 Flash Lite","raw":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","expiration_date":null,"id":"google/gemini-2.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"image":"0.00000005","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000002","prompt":"0.00000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-2.5-pro\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-2.5-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","enkrypt":{"bias_score":61.15,"cbrn_score":20.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.63,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":38.46,"jailbreak_score":31.0714,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-pro","nist_score":36,"owasp_score":39,"provider":"gemini","risk_score":35.8097,"robustness_score":null,"safety_score":32.5203,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.98},"expiration_date":null,"id":"google/gemini-2.5-pro","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 2.5 Pro","raw":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","enkrypt":{"bias_score":61.15,"cbrn_score":20.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.63,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":38.46,"jailbreak_score":31.0714,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-pro","nist_score":36,"owasp_score":39,"provider":"gemini","risk_score":35.8097,"robustness_score":null,"safety_score":32.5203,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.98},"expiration_date":null,"id":"google/gemini-2.5-pro","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-2.5-pro-preview\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-2.5-pro-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","audio","pdf"],"modality":"text+image+file+audio->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","expiration_date":null,"id":"google/gemini-2.5-pro-preview","inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro Preview 06-05","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 2.5 Pro Preview 06-05","raw":{"architecture":{"input_modalities":["file","image","text","audio","pdf"],"modality":"text+image+file+audio->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","expiration_date":null,"id":"google/gemini-2.5-pro-preview","inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro Preview 06-05","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3-flash-preview\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000015","prompt":"0.00000025","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3-flash-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","expiration_date":null,"id":"google/gemini-3-flash-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3 Flash Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000015","prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3 Flash Preview","raw":{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","expiration_date":null,"id":"google/gemini-3-flash-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3 Flash Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000015","prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3-pro-image\"]":{"classification":"paid","cost":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3-pro-image","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3-pro-image-preview\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3-pro-image-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-flash-image\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-flash-image","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","expiration_date":null,"id":"google/gemini-3.1-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","expiration_date":null,"id":"google/gemini-3.1-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-flash-image-preview\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-flash-image-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","expiration_date":null,"id":"google/gemini-3.1-flash-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","expiration_date":null,"id":"google/gemini-3.1-flash-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-flash-lite\"]":{"classification":"paid","cost":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-flash-lite","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","expiration_date":null,"id":"google/gemini-3.1-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.1 Flash Lite","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","expiration_date":null,"id":"google/gemini-3.1-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-flash-lite-image\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"prompt":"0.00000025","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-flash-lite-image","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-flash-lite-preview\"]":{"classification":"paid","cost":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-flash-lite-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.1 Flash Lite Preview","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-pro-preview\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-pro-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","expiration_date":null,"id":"google/gemini-3.1-pro-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.1 Pro Preview","raw":{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","expiration_date":null,"id":"google/gemini-3.1-pro-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.1-pro-preview-customtools\"]":{"classification":"paid","cost":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.1-pro-preview-customtools","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","image","video","file","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","expiration_date":null,"id":"google/gemini-3.1-pro-preview-customtools","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","raw":{"architecture":{"input_modalities":["text","audio","image","video","file","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","expiration_date":null,"id":"google/gemini-3.1-pro-preview-customtools","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.5-flash\"]":{"classification":"paid","cost":{"completion":"0.0000045","discount":0,"image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000045","prompt":"0.00000075","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.5-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","enkrypt":{"bias_score":80.36,"cbrn_score":52,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":11.56,"jailbreak_score":30.6475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.5-flash","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.3289,"robustness_score":null,"safety_score":38.332,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"google/gemini-3.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000045","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":104.4912192,"overallScore":0.64719101},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.5 Flash","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","enkrypt":{"bias_score":80.36,"cbrn_score":52,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":11.56,"jailbreak_score":30.6475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.5-flash","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.3289,"robustness_score":null,"safety_score":38.332,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"google/gemini-3.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000045","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":104.4912192,"overallScore":0.64719101},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.5-flash-lite\"]":{"classification":"paid","cost":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.5-flash-lite","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","expiration_date":null,"id":"google/gemini-3.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.5 Flash Lite","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","expiration_date":null,"id":"google/gemini-3.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.6-flash\"]":{"classification":"paid","cost":{"completion":"0.000001875","discount":0,"image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","internal_reasoning":"0.000001875","prompt":"0.000000375","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.6-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","enkrypt":{"bias_score":83.72,"cbrn_score":52.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":27.56,"jailbreak_score":28.4892,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.6-flash","nist_score":36,"owasp_score":40,"provider":"openai_compatible","risk_score":35.5088,"robustness_score":null,"safety_score":43.7851,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"google/gemini-3.6-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.6 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001875","discount":0,"image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","internal_reasoning":"0.000001875","prompt":"0.000000375","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":80.3143008,"overallScore":0.47865169},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.6 Flash","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","enkrypt":{"bias_score":83.72,"cbrn_score":52.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":27.56,"jailbreak_score":28.4892,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.6-flash","nist_score":36,"owasp_score":40,"provider":"openai_compatible","risk_score":35.5088,"robustness_score":null,"safety_score":43.7851,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"google/gemini-3.6-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.6 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001875","discount":0,"image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","internal_reasoning":"0.000001875","prompt":"0.000000375","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":80.3143008,"overallScore":0.47865169},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.7-flash\"]":{"classification":"paid","cost":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.7-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","expiration_date":null,"id":"google/gemini-3.7-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.7 Flash","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","expiration_date":null,"id":"google/gemini-3.7-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-3.8-flash\"]":{"classification":"paid","cost":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-3.8-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","expiration_date":null,"id":"google/gemini-3.8-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.8 Flash (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":112.2663174,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 3.8 Flash (50% off)","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","expiration_date":null,"id":"google/gemini-3.8-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.8 Flash (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":112.2663174,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-4-argon\"]":{"classification":"paid","cost":{"completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","internal_reasoning":"0.000010000000","prompt":"0.000002000000","web_search":"0.028000000000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-4-argon","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","expiration_date":null,"id":"google/gemini-4-argon","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 4 Argon (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","internal_reasoning":"0.000010000000","prompt":"0.000002000000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini 4 Argon (50% off)","raw":{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","expiration_date":null,"id":"google/gemini-4-argon","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 4 Argon (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","internal_reasoning":"0.000010000000","prompt":"0.000002000000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemini-nano-banana-2.1\"]":{"classification":"paid","cost":{"completion":"0.0000075","discount":0,"prompt":"0.0000015","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemini-nano-banana-2.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","expiration_date":null,"id":"google/gemini-nano-banana-2.1","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2.1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Nano Banana 2.1","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","expiration_date":null,"id":"google/gemini-nano-banana-2.1","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2.1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-2-27b-it\"]":{"classification":"paid","cost":{"completion":"0.00000065","discount":0,"prompt":"0.00000065"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-2-27b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":8192,"created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","enkrypt":{"bias_score":68.22,"cbrn_score":10.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.56,"jailbreak_score":6.11842,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-2-27b-it","nist_score":22,"owasp_score":24,"provider":"together","risk_score":21.6434,"robustness_score":null,"safety_score":24.1611,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"google/gemma-2-27b-it","inference_provider_ids":["nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 2 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000065"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":2048}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 2 27B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":8192,"created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","enkrypt":{"bias_score":68.22,"cbrn_score":10.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.56,"jailbreak_score":6.11842,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-2-27b-it","nist_score":22,"owasp_score":24,"provider":"together","risk_score":21.6434,"robustness_score":null,"safety_score":24.1611,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"google/gemma-2-27b-it","inference_provider_ids":["nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 2 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000065"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":2048}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-3-12b-it\"]":{"classification":"paid","cost":{"completion":"0.00000012","discount":0,"prompt":"0.00000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-3-12b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":86.82,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":31.56,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-12b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.3775,"robustness_score":null,"safety_score":22.6834,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.95},"expiration_date":null,"id":"google/gemma-3-12b-it","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 3 12B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":86.82,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":31.56,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-12b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.3775,"robustness_score":null,"safety_score":22.6834,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.95},"expiration_date":null,"id":"google/gemma-3-12b-it","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-3-27b-it\"]":{"classification":"paid","cost":{"completion":"0.00000016","discount":0,"prompt":"0.00000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-3-27b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":82.95,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":43.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36,"jailbreak_score":7.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-27b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.0275,"robustness_score":null,"safety_score":23.6486,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.64},"expiration_date":null,"id":"google/gemma-3-27b-it","inference_provider_ids":["deepinfra","nebius","nextbit","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000016","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 3 27B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":82.95,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":43.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36,"jailbreak_score":7.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-27b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.0275,"robustness_score":null,"safety_score":23.6486,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.64},"expiration_date":null,"id":"google/gemma-3-27b-it","inference_provider_ids":["deepinfra","nebius","nextbit","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000016","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-3-4b-it\"]":{"classification":"paid","cost":{"completion":"0.00000005","discount":0,"input_cache_read":"0.00000002","prompt":"0.00000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-3-4b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":83.98,"cbrn_score":11.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":51.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":44,"jailbreak_score":10.8553,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-4b-it","nist_score":39,"owasp_score":45,"provider":"openai_compatible","risk_score":39.109,"robustness_score":null,"safety_score":25.5309,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"google/gemma-3-4b-it","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 4B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"input_cache_read":"0.00000002","prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 3 4B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":83.98,"cbrn_score":11.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":51.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":44,"jailbreak_score":10.8553,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-4b-it","nist_score":39,"owasp_score":45,"provider":"openai_compatible","risk_score":39.109,"robustness_score":null,"safety_score":25.5309,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"google/gemma-3-4b-it","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 4B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"input_cache_read":"0.00000002","prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-4-26b-a4b-it\"]":{"classification":"paid","cost":{"completion":"0.000000108","discount":0,"input_cache_read":"0.000000018","prompt":"0.000000036"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-4-26b-a4b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","enkrypt":{"bias_score":87.08,"cbrn_score":37,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":21.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-26B-A4B-it","nist_score":29,"owasp_score":33,"provider":"openai_compatible","risk_score":28.5312,"robustness_score":null,"safety_score":36.5678,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"google/gemma-4-26b-a4b-it","inference_provider_ids":["akashml","cloudflare","coreweave","darkbloom","deepinfra","dekallm","gmicloud","google-vertex","io-net","makora","nextbit","novita","parasail","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 26B A4B ","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000108","discount":0,"input_cache_read":"0.000000018","prompt":"0.000000036"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 4 26B A4B ","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","enkrypt":{"bias_score":87.08,"cbrn_score":37,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":21.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-26B-A4B-it","nist_score":29,"owasp_score":33,"provider":"openai_compatible","risk_score":28.5312,"robustness_score":null,"safety_score":36.5678,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"google/gemma-4-26b-a4b-it","inference_provider_ids":["akashml","cloudflare","coreweave","darkbloom","deepinfra","dekallm","gmicloud","google-vertex","io-net","makora","nextbit","novita","parasail","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 26B A4B ","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000108","discount":0,"input_cache_read":"0.000000018","prompt":"0.000000036"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-4-31b-it\"]":{"classification":"paid","cost":{"completion":"0.000000166","discount":0,"input_cache_read":"0.00000005","prompt":"0.000000099"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/gemma-4-31b-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","enkrypt":{"bias_score":91.47,"cbrn_score":33.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12,"jailbreak_score":19.4245,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-31B-it","nist_score":29,"owasp_score":34,"provider":"openai_compatible","risk_score":29.4562,"robustness_score":null,"safety_score":38.5726,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"google/gemma-4-31b-it","inference_provider_ids":["chutes","coreweave","crusoe","deepinfra","friendli","gmicloud","io-net","modal","modelrun","nextbit","novita","parasail","primeintellect","sambanova","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 31B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000166","discount":0,"input_cache_read":"0.00000005","prompt":"0.000000099"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemma 4 31B","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","enkrypt":{"bias_score":91.47,"cbrn_score":33.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12,"jailbreak_score":19.4245,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-31B-it","nist_score":29,"owasp_score":34,"provider":"openai_compatible","risk_score":29.4562,"robustness_score":null,"safety_score":38.5726,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"google/gemma-4-31b-it","inference_provider_ids":["chutes","coreweave","crusoe","deepinfra","friendli","gmicloud","io-net","modal","modelrun","nextbit","novita","parasail","primeintellect","sambanova","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 31B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000166","discount":0,"input_cache_read":"0.00000005","prompt":"0.000000099"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/gemma-4-31b-it:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-02T23:03:49.693Z","fresh":false,"id":"google/gemma-4-31b-it:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","expiration_date":null,"id":"google/gemma-4-31b-it:free","inference_provider_ids":["google-ai-studio"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Google: Gemma 4 31B (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"Google: Gemma 4 31B (free)","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","expiration_date":null,"id":"google/gemma-4-31b-it:free","inference_provider_ids":["google-ai-studio"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Google: Gemma 4 31B (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"google/lyria-3-clip-preview\"]":{"classification":"conflict","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/lyria-3-clip-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907255,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","expiration_date":null,"id":"google/lyria-3-clip-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Clip Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Lyria 3 Clip Preview","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907255,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","expiration_date":null,"id":"google/lyria-3-clip-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Clip Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"google/lyria-3-pro-preview\"]":{"classification":"conflict","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"google/lyria-3-pro-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907286,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","expiration_date":null,"id":"google/lyria-3-pro-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Pro Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Lyria 3 Pro Preview","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907286,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","expiration_date":null,"id":"google/lyria-3-pro-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Pro Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"gryphe/mythomax-l2-13b\"]":{"classification":"paid","cost":{"completion":"0.00000011","discount":0,"prompt":"0.00000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"gryphe/mythomax-l2-13b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8192,"created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","expiration_date":null,"id":"gryphe/mythomax-l2-13b","inference_provider_ids":["mancer","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MythoMax 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000011","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":4096,"is_moderated":false,"max_completion_tokens":3686}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MythoMax 13B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8192,"created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","expiration_date":null,"id":"gryphe/mythomax-l2-13b","inference_provider_ids":["mancer","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MythoMax 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000011","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":4096,"is_moderated":false,"max_completion_tokens":3686}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"ibm-granite/granite-4.0-h-micro\"]":{"classification":"paid","cost":{"completion":"0.000000112","discount":0,"prompt":"0.000000017"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"ibm-granite/granite-4.0-h-micro","lastListed":"2026-10-26T22:38:18.540Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131000,"created":1760927695,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...","enkrypt":{"bias_score":86.05,"cbrn_score":12.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":21.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":22.67,"jailbreak_score":11.0791,"lastCheckedAt":"2026-10-26T04:00:23.855Z","model_name":"granite-4.0-h-micro","nist_score":29,"owasp_score":34,"provider":"openai_compatible","risk_score":28.6467,"robustness_score":null,"safety_score":34.0818,"source":"IBM","staleAfter":"2026-10-27T06:00:23.855Z","toxicity_score":0.91},"expiration_date":null,"id":"ibm-granite/granite-4.0-h-micro","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"IBM: Granite 4.0 Micro","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000112","discount":0,"prompt":"0.000000017"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131000,"is_moderated":false,"max_completion_tokens":117900}},"metadataProvenance":{"fetchedAt":"2026-10-26T22:38:18.540Z","source":"kilo"},"metadataRetained":true,"name":"IBM: Granite 4.0 Micro","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131000,"created":1760927695,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...","enkrypt":{"bias_score":86.05,"cbrn_score":12.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":21.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":22.67,"jailbreak_score":11.0791,"lastCheckedAt":"2026-10-26T04:00:23.855Z","model_name":"granite-4.0-h-micro","nist_score":29,"owasp_score":34,"provider":"openai_compatible","risk_score":28.6467,"robustness_score":null,"safety_score":34.0818,"source":"IBM","staleAfter":"2026-10-27T06:00:23.855Z","toxicity_score":0.91},"expiration_date":null,"id":"ibm-granite/granite-4.0-h-micro","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"IBM: Granite 4.0 Micro","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000112","discount":0,"prompt":"0.000000017"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131000,"is_moderated":false,"max_completion_tokens":117900}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"ibm-granite/granite-4.2-8b\"]":{"classification":"paid","cost":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"ibm-granite/granite-4.2-8b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","expiration_date":null,"id":"ibm-granite/granite-4.2-8b","inference_provider_ids":["coreweave","deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"IBM: Granite 4.2 8B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"IBM: Granite 4.2 8B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","expiration_date":null,"id":"ibm-granite/granite-4.2-8b","inference_provider_ids":["coreweave","deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"IBM: Granite 4.2 8B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inception/mercury-2\"]":{"classification":"paid","cost":{"completion":"0.00000075","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inception/mercury-2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":50000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Inception: Mercury 2 (retires Nov 8)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":50000}},"retirementDates":["2026-11-08"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inception/mercury-2.5\"]":{"classification":"paid","cost":{"completion":"0.000000750000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inception/mercury-2.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":260000,"created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2.5","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2.5 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000750000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":260000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Inception: Mercury 2.5 (retires Nov 8)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":260000,"created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2.5","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2.5 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000750000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":260000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":["2026-11-08"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inception/mercury-3\"]":{"classification":"paid","cost":{"completion":"0.000000700000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inception/mercury-3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792158337,"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","expiration_date":"2026-11-08","id":"inception/mercury-3","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 3 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000700000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Inception: Mercury 3 (retires Nov 8)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792158337,"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","expiration_date":"2026-11-08","id":"inception/mercury-3","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 3 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000700000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-11-08"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inclusionai/ling-3.0-flash\"]":{"classification":"paid","cost":{"completion":"0.000000180000","input_cache_read":"0.000000012000","prompt":"0.000000060000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inclusionai/ling-3.0-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","expiration_date":null,"id":"inclusionai/ling-3.0-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000180000","input_cache_read":"0.000000012000","prompt":"0.000000060000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"inclusionAI: Ling 3.0 Flash","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","expiration_date":null,"id":"inclusionai/ling-3.0-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000180000","input_cache_read":"0.000000012000","prompt":"0.000000060000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inclusionai/ling-3.0-flash-vl\"]":{"classification":"paid","cost":{"completion":"0.00000018","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inclusionai/ling-3.0-flash-vl","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","expiration_date":null,"id":"inclusionai/ling-3.0-flash-vl","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000018","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"inclusionAI: Ling 3.0 Flash VL","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","expiration_date":null,"id":"inclusionai/ling-3.0-flash-vl","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000018","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inclusionai/ling-3.1-flash\"]":{"classification":"paid","cost":{"completion":"0.000000900000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inclusionai/ling-3.1-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","expiration_date":null,"id":"inclusionai/ling-3.1-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.1 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000900000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"inclusionAI: Ling 3.1 Flash","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","expiration_date":null,"id":"inclusionai/ling-3.1-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.1 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000900000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inclusionai/ling-3.1-flash-1019-free\"]":{"classification":"free","cost":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-30T14:22:44.671Z","fresh":false,"id":"inclusionai/ling-3.1-flash-1019-free","lastListed":"2026-11-03T09:40:53.490Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"inclusionai/ling-3.1-flash-1019-free","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"An updated checkpoint of inclusionAI's Ling 3.1 Flash, provided free of charge by Novita AI until November 3, 2026. Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model with 25B active parameters out of 560B total and a 1M-token context window.","hugging_face_id":"","id":"inclusionai/ling-3.1-flash-1019-free","inference_provider_ids":["novita"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"inclusionAI: Ling 3.1 Flash 1019 (free)","opencode":{"ai_sdk_provider":"openrouter","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-03T09:40:53.490Z","source":"kilo"},"metadataRetained":true,"name":"inclusionAI: Ling 3.1 Flash 1019 (free)","raw":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"inclusionai/ling-3.1-flash-1019-free","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"An updated checkpoint of inclusionAI's Ling 3.1 Flash, provided free of charge by Novita AI until November 3, 2026. Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model with 25B active parameters out of 560B total and a 1M-token context window.","hugging_face_id":"","id":"inclusionai/ling-3.1-flash-1019-free","inference_provider_ids":["novita"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"inclusionAI: Ling 3.1 Flash 1019 (free)","opencode":{"ai_sdk_provider":"openrouter","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"inference-net/schematron-v2-small\"]":{"classification":"paid","cost":{"completion":"0.00000023","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inference-net/schematron-v2-small","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","expiration_date":null,"id":"inference-net/schematron-v2-small","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Small","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000023","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Inference.net: Schematron V2 Small","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","expiration_date":null,"id":"inference-net/schematron-v2-small","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Small","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000023","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"inference-net/schematron-v2-turbo\"]":{"classification":"paid","cost":{"completion":"0.00000015","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"inference-net/schematron-v2-turbo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","expiration_date":null,"id":"inference-net/schematron-v2-turbo","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Turbo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Inference.net: Schematron V2 Turbo","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","expiration_date":null,"id":"inference-net/schematron-v2-turbo","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Turbo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"kilo-auto/balanced\"]":{"classification":"unknown","cost":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"kilo-auto/balanced","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Great balance of price and capability.","id":"kilo-auto/balanced","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Balanced","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Auto Balanced","raw":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Great balance of price and capability.","id":"kilo-auto/balanced","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Balanced","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"kilo-auto/efficient\"]":{"classification":"unknown","cost":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"kilo-auto/efficient","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","id":"kilo-auto/efficient","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Efficient","opencode":{},"preferredIndex":0,"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Auto Efficient","raw":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","id":"kilo-auto/efficient","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Efficient","opencode":{},"preferredIndex":0,"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"kilo-auto/free\"]":{"classification":"free","cost":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"kilo-auto/free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["dots-studio/dots-3-note-preview:free","nvidia/nemotron-3.5-super-vl:free","reflection/beam-free","stealth/glyph-cluster"]},"context_length":256000,"created":0,"description":"Rotates through available free models. Limited capability and no credits required. [Learn more](https://kilo.ai/docs/code-with-ai/agents/auto-model)\n\n**Warning** Prompts may be logged by the upstream provider and used to improve their services. Not suitable for production or sensitive data workloads.","id":"kilo-auto/free","inference_provider_ids":[],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Auto Free","opencode":{},"preferredIndex":1,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Auto Free","raw":{"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["dots-studio/dots-3-note-preview:free","nvidia/nemotron-3.5-super-vl:free","reflection/beam-free","stealth/glyph-cluster"]},"context_length":256000,"created":0,"description":"Rotates through available free models. Limited capability and no credits required. [Learn more](https://kilo.ai/docs/code-with-ai/agents/auto-model)\n\n**Warning** Prompts may be logged by the upstream provider and used to improve their services. Not suitable for production or sensitive data workloads.","id":"kilo-auto/free","inference_provider_ids":[],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Auto Free","opencode":{},"preferredIndex":1,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"kilo-auto/frontier\"]":{"classification":"unknown","cost":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"kilo-auto/frontier","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-fable-5.1","anthropic/claude-opus-5.5","anthropic/claude-sonnet-5.5","google/gemini-4-argon","meta/muse-wonder","moonshotai/kimi-k3","moonshotai/kimi-k3.1-pro","openai/gpt-6-astra","openai/gpt-6.1-sol","openai/gpt-6.1-terra","x-ai/grok-4.7"]},"context_length":1000000,"created":0,"description":"Highest performance and capability for any task.","id":"kilo-auto/frontier","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Frontier","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Auto Frontier","raw":{"architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-fable-5.1","anthropic/claude-opus-5.5","anthropic/claude-sonnet-5.5","google/gemini-4-argon","meta/muse-wonder","moonshotai/kimi-k3","moonshotai/kimi-k3.1-pro","openai/gpt-6-astra","openai/gpt-6.1-sol","openai/gpt-6.1-terra","x-ai/grok-4.7"]},"context_length":1000000,"created":0,"description":"Highest performance and capability for any task.","id":"kilo-auto/frontier","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Frontier","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"kilo-auto/small\"]":{"classification":"paid","cost":{"completion":"0.0000004","image":"0","input_cache_read":"0.000000005","internal_reasoning":"0","prompt":"0.00000005","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"kilo-auto/small","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["google/gemma-4-26b-a4b-it"]},"context_length":262144,"created":0,"description":"Automatically routes your request to a small model.","id":"kilo-auto/small","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Small","opencode":{},"pricing":{"completion":"0.0000004","image":"0","input_cache_read":"0.000000005","internal_reasoning":"0","prompt":"0.00000005","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Auto Small","raw":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["google/gemma-4-26b-a4b-it"]},"context_length":262144,"created":0,"description":"Automatically routes your request to a small model.","id":"kilo-auto/small","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Small","opencode":{},"pricing":{"completion":"0.0000004","image":"0","input_cache_read":"0.000000005","internal_reasoning":"0","prompt":"0.00000005","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"liquid/lfm-2.5-2.6b\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000035"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-24T22:31:11.700Z","fresh":true,"id":"liquid/lfm-2.5-2.6b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","expiration_date":null,"id":"liquid/lfm-2.5-2.6b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-2.6B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000035"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"LiquidAI: LFM2.5-2.6B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","expiration_date":null,"id":"liquid/lfm-2.5-2.6b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-2.6B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000035"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"liquid/lfm-2.5-2.6b:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"liquid/lfm-2.5-2.6b:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","expiration_date":null,"id":"liquid/lfm-2.5-2.6b:free","inference_provider_ids":["liquid"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-2.6B (free)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"LiquidAI: LFM2.5-2.6B (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","expiration_date":null,"id":"liquid/lfm-2.5-2.6b:free","inference_provider_ids":["liquid"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-2.6B (free)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"liquid/lfm-2.5-24b-a2b\"]":{"classification":"paid","cost":{"completion":"0.0000007","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"liquid/lfm-2.5-24b-a2b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","expiration_date":null,"id":"liquid/lfm-2.5-24b-a2b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-24B-A2B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000007","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"LiquidAI: LFM2.5-24B-A2B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","expiration_date":null,"id":"liquid/lfm-2.5-24b-a2b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-24B-A2B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000007","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mancer/weaver\"]":{"classification":"paid","cost":{"completion":"0.00000075","discount":0,"prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mancer/weaver","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8000,"created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","expiration_date":null,"id":"mancer/weaver","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mancer: Weaver (alpha)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8000,"is_moderated":false,"max_completion_tokens":6000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mancer: Weaver (alpha)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8000,"created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","expiration_date":null,"id":"mancer/weaver","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mancer: Weaver (alpha)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8000,"is_moderated":false,"max_completion_tokens":6000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meituan/longcat-2.0\"]":{"classification":"paid","cost":{"completion":"0.000003000000","input_cache_read":"0.000000015000","prompt":"0.000000750000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meituan/longcat-2.0","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048756,"created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","expiration_date":null,"id":"meituan/longcat-2.0","inference_provider_ids":["atlas-cloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meituan: LongCat 2.0","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003000000","input_cache_read":"0.000000015000","prompt":"0.000000750000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048756,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meituan: LongCat 2.0","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048756,"created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","expiration_date":null,"id":"meituan/longcat-2.0","inference_provider_ids":["atlas-cloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meituan: LongCat 2.0","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003000000","input_cache_read":"0.000000015000","prompt":"0.000000750000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048756,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-3.1-70b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000072","discount":0,"prompt":"0.00000072"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-3.1-70b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","expiration_date":null,"id":"meta-llama/llama-3.1-70b-instruct","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000072","discount":0,"prompt":"0.00000072"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":true,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 3.1 70B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","expiration_date":null,"id":"meta-llama/llama-3.1-70b-instruct","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000072","discount":0,"prompt":"0.00000072"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":true,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-3.1-8b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000004","discount":0,"prompt":"0.00000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-3.1-8b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","enkrypt":{"bias_score":81.65,"cbrn_score":16.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":50.67,"jailbreak_score":25.3947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.1-8B-Instruct","nist_score":38,"owasp_score":44,"provider":"openai_compatible","risk_score":38.2035,"robustness_score":null,"safety_score":25.9653,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":15.86},"expiration_date":null,"id":"meta-llama/llama-3.1-8b-instruct","inference_provider_ids":["amazon-bedrock","cloudflare","coreweave","deepinfra","groq","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000004","discount":0,"prompt":"0.00000002"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 3.1 8B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","enkrypt":{"bias_score":81.65,"cbrn_score":16.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":50.67,"jailbreak_score":25.3947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.1-8B-Instruct","nist_score":38,"owasp_score":44,"provider":"openai_compatible","risk_score":38.2035,"robustness_score":null,"safety_score":25.9653,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":15.86},"expiration_date":null,"id":"meta-llama/llama-3.1-8b-instruct","inference_provider_ids":["amazon-bedrock","cloudflare","coreweave","deepinfra","groq","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000004","discount":0,"prompt":"0.00000002"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-3.2-1b-instruct\"]":{"classification":"paid","cost":{"completion":"0.000000201","discount":0,"prompt":"0.000000027"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-3.2-1b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":60000,"created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","enkrypt":{"bias_score":95.87,"cbrn_score":11.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":69.78,"jailbreak_score":3.22368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-1B-Instruct","nist_score":37,"owasp_score":48,"provider":"Hugging Face","risk_score":37.4762,"robustness_score":null,"safety_score":28.5232,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.18},"expiration_date":null,"id":"meta-llama/llama-3.2-1b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 1B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000201","discount":0,"prompt":"0.000000027"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":60000,"is_moderated":false,"max_completion_tokens":54000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 3.2 1B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":60000,"created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","enkrypt":{"bias_score":95.87,"cbrn_score":11.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":69.78,"jailbreak_score":3.22368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-1B-Instruct","nist_score":37,"owasp_score":48,"provider":"Hugging Face","risk_score":37.4762,"robustness_score":null,"safety_score":28.5232,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.18},"expiration_date":null,"id":"meta-llama/llama-3.2-1b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 1B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000201","discount":0,"prompt":"0.000000027"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":60000,"is_moderated":false,"max_completion_tokens":54000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-3.2-3b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000033","discount":0,"prompt":"0.00000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-3.2-3b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","enkrypt":{"bias_score":88.89,"cbrn_score":14.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":68.89,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-3B-Instruct","nist_score":38,"owasp_score":48,"provider":"Hugging Face","risk_score":38.3222,"robustness_score":null,"safety_score":28.4749,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.5},"expiration_date":null,"id":"meta-llama/llama-3.2-3b-instruct","inference_provider_ids":["cloudflare","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":80000,"is_moderated":false,"max_completion_tokens":72000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 3.2 3B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","enkrypt":{"bias_score":88.89,"cbrn_score":14.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":68.89,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-3B-Instruct","nist_score":38,"owasp_score":48,"provider":"Hugging Face","risk_score":38.3222,"robustness_score":null,"safety_score":28.4749,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.5},"expiration_date":null,"id":"meta-llama/llama-3.2-3b-instruct","inference_provider_ids":["cloudflare","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":80000,"is_moderated":false,"max_completion_tokens":72000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-3.3-70b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000032","discount":0,"prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-3.3-70b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","expiration_date":null,"id":"meta-llama/llama-3.3-70b-instruct","inference_provider_ids":["akashml","amazon-bedrock","cloudflare","coreweave","deepinfra","google-vertex","groq","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.3 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000032","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 3.3 70B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","expiration_date":null,"id":"meta-llama/llama-3.3-70b-instruct","inference_provider_ids":["akashml","amazon-bedrock","cloudflare","coreweave","deepinfra","google-vertex","groq","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.3 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000032","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-4-maverick\"]":{"classification":"paid","cost":{"completion":"0.0000006525","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001875"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-4-maverick","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":524288,"created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","expiration_date":null,"id":"meta-llama/llama-4-maverick","inference_provider_ids":["amazon-bedrock","digitalocean","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Maverick","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006525","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 4 Maverick","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":524288,"created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","expiration_date":null,"id":"meta-llama/llama-4-maverick","inference_provider_ids":["amazon-bedrock","digitalocean","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Maverick","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006525","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-4-scout\"]":{"classification":"paid","cost":{"completion":"0.00000024","discount":0,"prompt":"0.00000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-4-scout","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":1310720,"created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","expiration_date":null,"id":"meta-llama/llama-4-scout","inference_provider_ids":["amazon-bedrock","deepinfra","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Scout","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":327680,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama 4 Scout","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":1310720,"created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","expiration_date":null,"id":"meta-llama/llama-4-scout","inference_provider_ids":["amazon-bedrock","deepinfra","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Scout","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":327680,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta-llama/llama-guard-4-12b\"]":{"classification":"paid","cost":{"completion":"0.000000144","discount":0,"prompt":"0.000000144"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta-llama/llama-guard-4-12b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":163840,"created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","expiration_date":null,"id":"meta-llama/llama-guard-4-12b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama Guard 4 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000144","discount":0,"prompt":"0.000000144"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Llama Guard 4 12B","raw":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":163840,"created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","expiration_date":null,"id":"meta-llama/llama-guard-4-12b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama Guard 4 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000144","discount":0,"prompt":"0.000000144"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-glimmer-30b\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-glimmer-30b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","expiration_date":null,"id":"meta/muse-glimmer-30b","inference_provider_ids":["deepinfra","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Glimmer 30B","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Glimmer 30B","raw":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","expiration_date":null,"id":"meta/muse-glimmer-30b","inference_provider_ids":["deepinfra","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Glimmer 30B","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-1.1\"]":{"classification":"paid","cost":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-1.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","enkrypt":{"bias_score":50.13,"cbrn_score":6.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.11,"jailbreak_score":1.43885,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"muse-spark-1.1","nist_score":16,"owasp_score":20,"provider":"openai_compatible","risk_score":15.9875,"robustness_score":null,"safety_score":23.1756,"source":"Meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"meta/muse-spark-1.1","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":30.153412199999998,"overallScore":0.59775281},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark 1.1","raw":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","enkrypt":{"bias_score":50.13,"cbrn_score":6.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.11,"jailbreak_score":1.43885,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"muse-spark-1.1","nist_score":16,"owasp_score":20,"provider":"openai_compatible","risk_score":15.9875,"robustness_score":null,"safety_score":23.1756,"source":"Meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"meta/muse-spark-1.1","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":30.153412199999998,"overallScore":0.59775281},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-1.2\"]":{"classification":"paid","cost":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-1.2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","expiration_date":null,"id":"meta/muse-spark-1.2","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":44.68511,"overallScore":0.51460674},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark 1.2","raw":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","expiration_date":null,"id":"meta/muse-spark-1.2","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":44.68511,"overallScore":0.51460674},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-1.2-contributor\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-1.2-contributor","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","expiration_date":null,"id":"meta/muse-spark-1.2-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.2 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark 1.2 Contributor","raw":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","expiration_date":null,"id":"meta/muse-spark-1.2-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.2 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-1.3\"]":{"classification":"paid","cost":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-1.3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","expiration_date":null,"id":"meta/muse-spark-1.3","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark 1.3","raw":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","expiration_date":null,"id":"meta/muse-spark-1.3","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-1.3-contributor\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-1.3-contributor","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","expiration_date":null,"id":"meta/muse-spark-1.3-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.3 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark 1.3 Contributor","raw":{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","expiration_date":null,"id":"meta/muse-spark-1.3-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.3 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-spark-open\"]":{"classification":"paid","cost":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-spark-open","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","expiration_date":null,"id":"meta/muse-spark-open","inference_provider_ids":["baseten","fireworks","makora","modal","nebius","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark Open","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Spark Open","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","expiration_date":null,"id":"meta/muse-spark-open","inference_provider_ids":["baseten","fireworks","makora","modal","nebius","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark Open","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"meta/muse-wonder\"]":{"classification":"paid","cost":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000004","web_search":"0.0025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"meta/muse-wonder","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","expiration_date":null,"id":"meta/muse-wonder","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Wonder","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000004","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Meta: Muse Wonder","raw":{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","expiration_date":null,"id":"meta/muse-wonder","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Wonder","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000004","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"microsoft/phi-4\"]":{"classification":"paid","cost":{"completion":"0.000000112","discount":0,"prompt":"0.000000056"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"microsoft/phi-4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","enkrypt":{"bias_score":83.2,"cbrn_score":5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":3.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16,"jailbreak_score":2.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"phi-4","nist_score":22,"owasp_score":28,"provider":"HuggingFace","risk_score":21.6711,"robustness_score":null,"safety_score":18.2915,"source":"Microsoft","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.82},"expiration_date":null,"id":"microsoft/phi-4","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Microsoft: Phi 4","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000112","discount":0,"prompt":"0.000000056"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Microsoft: Phi 4","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","enkrypt":{"bias_score":83.2,"cbrn_score":5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":3.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16,"jailbreak_score":2.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"phi-4","nist_score":22,"owasp_score":28,"provider":"HuggingFace","risk_score":21.6711,"robustness_score":null,"safety_score":18.2915,"source":"Microsoft","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.82},"expiration_date":null,"id":"microsoft/phi-4","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Microsoft: Phi 4","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000112","discount":0,"prompt":"0.000000056"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-01\"]":{"classification":"paid","cost":{"completion":"0.0000011","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-01","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000192,"created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","expiration_date":"2026-11-05","id":"minimax/minimax-01","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax-01 (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","prompt":"0.0000002"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":1000192,"is_moderated":false,"max_completion_tokens":900172}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax-01 (retires Nov 5)","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000192,"created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","expiration_date":"2026-11-05","id":"minimax/minimax-01","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax-01 (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","prompt":"0.0000002"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":1000192,"is_moderated":false,"max_completion_tokens":900172}},"retirementDates":["2026-11-05"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m1\"]":{"classification":"paid","cost":{"completion":"0.0000022","discount":0,"prompt":"0.00000055"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","expiration_date":null,"id":"minimax/minimax-m1","inference_provider_ids":["minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","discount":0,"prompt":"0.00000055"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":40000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M1","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","expiration_date":null,"id":"minimax/minimax-m1","inference_provider_ids":["minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","discount":0,"prompt":"0.00000055"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":40000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m2\"]":{"classification":"paid","cost":{"completion":"0.00000102","prompt":"0.000000255"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","enkrypt":{"bias_score":48.06,"cbrn_score":14,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":10.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":5.89928,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2","nist_score":18,"owasp_score":21,"provider":"novita","risk_score":17.6387,"robustness_score":null,"safety_score":22.935,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.91},"expiration_date":"2026-11-05","id":"minimax/minimax-m2","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000102","prompt":"0.000000255"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M2 (retires Nov 5)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","enkrypt":{"bias_score":48.06,"cbrn_score":14,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":10.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":5.89928,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2","nist_score":18,"owasp_score":21,"provider":"novita","risk_score":17.6387,"robustness_score":null,"safety_score":22.935,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.91},"expiration_date":"2026-11-05","id":"minimax/minimax-m2","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000102","prompt":"0.000000255"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-11-05"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m2-her\"]":{"classification":"paid","cost":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m2-her","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","expiration_date":"2026-11-05","id":"minimax/minimax-m2-her","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2-her (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":2048}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M2-her (retires Nov 5)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","expiration_date":"2026-11-05","id":"minimax/minimax-m2-her","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2-her (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":2048}},"retirementDates":["2026-11-05"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m2.1\"]":{"classification":"paid","cost":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m2.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","expiration_date":"2026-11-05","id":"minimax/minimax-m2.1","inference_provider_ids":["amazon-bedrock","minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.1 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M2.1 (retires Nov 5)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","expiration_date":"2026-11-05","id":"minimax/minimax-m2.1","inference_provider_ids":["amazon-bedrock","minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.1 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-11-05"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m2.5\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m2.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","expiration_date":null,"id":"minimax/minimax-m2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","digitalocean","gmicloud","minimax","novita","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.5","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":198000,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M2.5","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","expiration_date":null,"id":"minimax/minimax-m2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","digitalocean","gmicloud","minimax","novita","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.5","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":198000,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m2.7\"]":{"classification":"paid","cost":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m2.7","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","enkrypt":{"bias_score":45.48,"cbrn_score":15,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0.89,"jailbreak_score":2.15827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2.7","nist_score":13,"owasp_score":15,"provider":"novita","risk_score":13.0815,"robustness_score":null,"safety_score":21.4114,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":"2026-11-05","id":"minimax/minimax-m2.7","inference_provider_ids":["atlas-cloud","gmicloud","groq","minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.7 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M2.7 (retires Nov 5)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","enkrypt":{"bias_score":45.48,"cbrn_score":15,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0.89,"jailbreak_score":2.15827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2.7","nist_score":13,"owasp_score":15,"provider":"novita","risk_score":13.0815,"robustness_score":null,"safety_score":21.4114,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":"2026-11-05","id":"minimax/minimax-m2.7","inference_provider_ids":["atlas-cloud","gmicloud","groq","minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.7 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-11-05"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m3\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","enkrypt":{"bias_score":79.59,"cbrn_score":49.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":20,"jailbreak_score":26.3309,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m3","nist_score":31,"owasp_score":35,"provider":"openai_compatible","risk_score":31.3345,"robustness_score":null,"safety_score":39.1339,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.36},"expiration_date":null,"id":"minimax/minimax-m3","inference_provider_ids":["atlas-cloud","coreweave","deepinfra","fireworks","gmicloud","mara","minimax","modelrun","nebius","novita","parasail","streamlake","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":10.350343800000001,"overallScore":0.47640449},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":512000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M3","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","enkrypt":{"bias_score":79.59,"cbrn_score":49.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":20,"jailbreak_score":26.3309,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m3","nist_score":31,"owasp_score":35,"provider":"openai_compatible","risk_score":31.3345,"robustness_score":null,"safety_score":39.1339,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.36},"expiration_date":null,"id":"minimax/minimax-m3","inference_provider_ids":["atlas-cloud","coreweave","deepinfra","fireworks","gmicloud","mara","minimax","modelrun","nebius","novita","parasail","streamlake","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":10.350343800000001,"overallScore":0.47640449},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":512000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"minimax/minimax-m3.1-flash\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"minimax/minimax-m3.1-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","expiration_date":null,"id":"minimax/minimax-m3.1-flash","inference_provider_ids":["digitalocean","fireworks","gmicloud","inference-net","minimax","modelrun","nebius","novita","parasail","sambanova","streamlake","tenstorrent","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":524288}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MiniMax: MiniMax M3.1 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","expiration_date":null,"id":"minimax/minimax-m3.1-flash","inference_provider_ids":["digitalocean","fireworks","gmicloud","inference-net","minimax","modelrun","nebius","novita","parasail","sambanova","streamlake","tenstorrent","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":524288}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/codestral-2508\"]":{"classification":"paid","cost":{"completion":"0.0000009","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/codestral-2508","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","expiration_date":null,"id":"mistralai/codestral-2508","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Codestral 2508","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":204800}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Codestral 2508","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","expiration_date":null,"id":"mistralai/codestral-2508","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Codestral 2508","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":204800}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/devstral-2512\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/devstral-2512","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","expiration_date":null,"id":"mistralai/devstral-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Devstral 2 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Devstral 2 2512","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","expiration_date":null,"id":"mistralai/devstral-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Devstral 2 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/ministral-14b-2512\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/ministral-14b-2512","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","expiration_date":null,"id":"mistralai/ministral-14b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 14B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Ministral 3 14B 2512","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","expiration_date":null,"id":"mistralai/ministral-14b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 14B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/ministral-3b-2512\"]":{"classification":"paid","cost":{"completion":"0.0000001","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/ministral-3b-2512","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-3b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 3B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Ministral 3 3B 2512","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-3b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 3B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/ministral-8b-2512\"]":{"classification":"paid","cost":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/ministral-8b-2512","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-8b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 8B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Ministral 3 8B 2512","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-8b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 8B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-large\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-large","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral Large","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-large-2407\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-large-2407","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large-2407","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large 2407","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral Large 2407","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large-2407","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large 2407","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-large-2512\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-large-2512","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","expiration_date":null,"id":"mistralai/mistral-large-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 3 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Large 3 2512","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","expiration_date":null,"id":"mistralai/mistral-large-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 3 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-large-4-0\"]":{"classification":"paid","cost":{"completion":"0.0000021","discount":0,"input_cache_read":"0.00000007","prompt":"0.0000007"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-large-4-0","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1048576,"created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","expiration_date":null,"id":"mistralai/mistral-large-4-0","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000021","discount":0,"input_cache_read":"0.00000007","prompt":"0.0000007"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Large 4","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1048576,"created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","expiration_date":null,"id":"mistralai/mistral-large-4-0","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000021","discount":0,"input_cache_read":"0.00000007","prompt":"0.0000007"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-medium-3\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-medium-3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","expiration_date":null,"id":"mistralai/mistral-medium-3","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Medium 3","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","expiration_date":null,"id":"mistralai/mistral-medium-3","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-medium-3-5\"]":{"classification":"paid","cost":{"completion":"0.0000075","discount":0,"prompt":"0.0000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-medium-3-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","expiration_date":null,"id":"mistralai/mistral-medium-3-5","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Medium 3.5","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","expiration_date":null,"id":"mistralai/mistral-medium-3-5","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-medium-3.1\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-medium-3.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","expiration_date":null,"id":"mistralai/mistral-medium-3.1","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Medium 3.1","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","expiration_date":null,"id":"mistralai/mistral-medium-3.1","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-nemo\"]":{"classification":"paid","cost":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-nemo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","expiration_date":null,"id":"mistralai/mistral-nemo","inference_provider_ids":["deepinfra","dekallm","io-net","mistral","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Nemo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Nemo","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","expiration_date":null,"id":"mistralai/mistral-nemo","inference_provider_ids":["deepinfra","dekallm","io-net","mistral","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Nemo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-saba\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-saba","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","expiration_date":null,"id":"mistralai/mistral-saba","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Saba","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Saba","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","expiration_date":null,"id":"mistralai/mistral-saba","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Saba","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-small-24b-instruct-2501\"]":{"classification":"paid","cost":{"completion":"0.00000008","prompt":"0.00000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-small-24b-instruct-2501","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","enkrypt":{"bias_score":84.75,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":45.78,"jailbreak_score":9.60526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Mistral-Small-24B-Instruct-2501","nist_score":40,"owasp_score":45,"provider":"Together","risk_score":39.5529,"robustness_score":null,"safety_score":24.8552,"source":"Mistral","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.45},"expiration_date":null,"id":"mistralai/mistral-small-24b-instruct-2501","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000008","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Small 3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","enkrypt":{"bias_score":84.75,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":45.78,"jailbreak_score":9.60526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Mistral-Small-24B-Instruct-2501","nist_score":40,"owasp_score":45,"provider":"Together","risk_score":39.5529,"robustness_score":null,"safety_score":24.8552,"source":"Mistral","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.45},"expiration_date":null,"id":"mistralai/mistral-small-24b-instruct-2501","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000008","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-small-2603\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-small-2603","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","expiration_date":null,"id":"mistralai/mistral-small-2603","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Small 4","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","expiration_date":null,"id":"mistralai/mistral-small-2603","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-small-3.1-24b-instruct\"]":{"classification":"paid","cost":{"completion":"0.000000555","prompt":"0.000000351"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-small-3.1-24b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","expiration_date":null,"id":"mistralai/mistral-small-3.1-24b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.1 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000555","prompt":"0.000000351"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Small 3.1 24B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","expiration_date":null,"id":"mistralai/mistral-small-3.1-24b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.1 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000555","prompt":"0.000000351"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mistral-small-3.2-24b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mistral-small-3.2-24b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","expiration_date":null,"id":"mistralai/mistral-small-3.2-24b-instruct","inference_provider_ids":["deepinfra","mistral","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.2 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mistral Small 3.2 24B","raw":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","expiration_date":null,"id":"mistralai/mistral-small-3.2-24b-instruct","inference_provider_ids":["deepinfra","mistral","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.2 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/mixtral-8x22b-instruct\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/mixtral-8x22b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":65536,"created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","expiration_date":null,"id":"mistralai/mixtral-8x22b-instruct","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mixtral 8x22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":52428}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Mixtral 8x22B Instruct","raw":{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":65536,"created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","expiration_date":null,"id":"mistralai/mixtral-8x22b-instruct","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mixtral 8x22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":52428}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"mistralai/voxtral-small-24b-2507\"]":{"classification":"paid","cost":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"mistralai/voxtral-small-24b-2507","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","file"],"modality":"text+file+audio->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","expiration_date":null,"id":"mistralai/voxtral-small-24b-2507","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Voxtral Small 24B 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Mistral: Voxtral Small 24B 2507","raw":{"architecture":{"input_modalities":["text","audio","file"],"modality":"text+file+audio->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","expiration_date":null,"id":"mistralai/voxtral-small-24b-2507","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Voxtral Small 24B 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moondream/moondream3-preview\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moondream/moondream3-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","expiration_date":null,"id":"moondream/moondream3-preview","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3 Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Moondream: Moondream 3 Preview","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","expiration_date":null,"id":"moondream/moondream3-preview","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3 Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moondream/moondream3.1-9b-a2b\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moondream/moondream3.1-9b-a2b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","expiration_date":null,"id":"moondream/moondream3.1-9b-a2b","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Moondream: Moondream 3.1","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","expiration_date":null,"id":"moondream/moondream3.1-9b-a2b","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2\"]":{"classification":"paid","cost":{"completion":"0.0000023","prompt":"0.00000057"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","expiration_date":null,"id":"moonshotai/kimi-k2","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0711","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000023","prompt":"0.00000057"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2 0711","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","expiration_date":null,"id":"moonshotai/kimi-k2","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0711","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000023","prompt":"0.00000057"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2-0905\"]":{"classification":"paid","cost":{"completion":"0.0000025","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2-0905","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","expiration_date":null,"id":"moonshotai/kimi-k2-0905","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0905","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2 0905","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","expiration_date":null,"id":"moonshotai/kimi-k2-0905","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0905","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2-thinking\"]":{"classification":"paid","cost":{"completion":"0.0000025","input_cache_read":"0.00000015","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2-thinking","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","enkrypt":{"bias_score":67.44,"cbrn_score":24.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.56,"jailbreak_score":11.6456,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2-thinking","nist_score":28,"owasp_score":31,"provider":"novita","risk_score":28.0702,"robustness_score":null,"safety_score":31.676,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2-thinking","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2 Thinking","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","enkrypt":{"bias_score":67.44,"cbrn_score":24.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.56,"jailbreak_score":11.6456,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2-thinking","nist_score":28,"owasp_score":31,"provider":"novita","risk_score":28.0702,"robustness_score":null,"safety_score":31.676,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2-thinking","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2.5\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","enkrypt":{"bias_score":83.72,"cbrn_score":33.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.5","nist_score":26,"owasp_score":30,"provider":"novita","risk_score":26.3715,"robustness_score":null,"safety_score":33.8412,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"moonshotai/kimi-k2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","novita","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2.5","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","enkrypt":{"bias_score":83.72,"cbrn_score":33.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.5","nist_score":26,"owasp_score":30,"provider":"novita","risk_score":26.3715,"robustness_score":null,"safety_score":33.8412,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"moonshotai/kimi-k2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","novita","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2.6\"]":{"classification":"paid","cost":{"completion":"0.00000341","input_cache_read":"0.00000015","prompt":"0.00000065"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","enkrypt":{"bias_score":71.32,"cbrn_score":48.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.44,"jailbreak_score":27.0504,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.6","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2868,"robustness_score":null,"safety_score":36.0866,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.73},"expiration_date":null,"id":"moonshotai/kimi-k2.6","inference_provider_ids":["atlas-cloud","baidu","chutes","cloudflare","coreweave","crusoe","deepinfra","digitalocean","gmicloud","inceptron","moonshotai","novita","parasail","phala","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000341","input_cache_read":"0.00000015","prompt":"0.00000065"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":24.844050600000003,"overallScore":0.54382022},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2.6","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","enkrypt":{"bias_score":71.32,"cbrn_score":48.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.44,"jailbreak_score":27.0504,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.6","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2868,"robustness_score":null,"safety_score":36.0866,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.73},"expiration_date":null,"id":"moonshotai/kimi-k2.6","inference_provider_ids":["atlas-cloud","baidu","chutes","cloudflare","coreweave","crusoe","deepinfra","digitalocean","gmicloud","inceptron","moonshotai","novita","parasail","phala","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000341","input_cache_read":"0.00000015","prompt":"0.00000065"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":24.844050600000003,"overallScore":0.54382022},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k2.7-code\"]":{"classification":"paid","cost":{"completion":"0.0000035","input_cache_read":"0.00000015","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k2.7-code","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","enkrypt":{"bias_score":84.24,"cbrn_score":42,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":7.56,"jailbreak_score":21.5827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.7-code","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.6738,"robustness_score":null,"safety_score":37.2093,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2.7-code","inference_provider_ids":["alibaba","cloudflare","coreweave","gmicloud","inceptron","moonshotai","novita","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.7 Code","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":32.940153,"overallScore":0.60674157},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K2.7 Code","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","enkrypt":{"bias_score":84.24,"cbrn_score":42,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":7.56,"jailbreak_score":21.5827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.7-code","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.6738,"robustness_score":null,"safety_score":37.2093,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2.7-code","inference_provider_ids":["alibaba","cloudflare","coreweave","gmicloud","inceptron","moonshotai","novita","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.7 Code","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":32.940153,"overallScore":0.60674157},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k3\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"moonshotai/kimi-k3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","expiration_date":null,"id":"moonshotai/kimi-k3","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":48.378817,"overallScore":0.72808989},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K3","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","expiration_date":null,"id":"moonshotai/kimi-k3","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":48.378817,"overallScore":0.72808989},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"moonshotai/kimi-k3.1-pro\"]":{"classification":"paid","cost":{"completion":"0.00001","input_cache_read":"0.0000002","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-23T18:22:11.920Z","fresh":true,"id":"moonshotai/kimi-k3.1-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","expiration_date":null,"id":"moonshotai/kimi-k3.1-pro","inference_provider_ids":["alibaba","baseten","fireworks","inference-net","modal","moonshotai","morph","nebius","parasail","phala","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3.1 Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi K3.1 Pro","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","expiration_date":null,"id":"moonshotai/kimi-k3.1-pro","inference_provider_ids":["alibaba","baseten","fireworks","inference-net","modal","moonshotai","morph","nebius","parasail","phala","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3.1 Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"morph/morph-v3-fast\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"morph/morph-v3-fast","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","expiration_date":null,"id":"morph/morph-v3-fast","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Fast","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"prompt":"0.0000008"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Morph: Morph V3 Fast","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","expiration_date":null,"id":"morph/morph-v3-fast","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Fast","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"prompt":"0.0000008"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"morph/morph-v3-large\"]":{"classification":"paid","cost":{"completion":"0.0000019","discount":0,"prompt":"0.0000009"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"morph/morph-v3-large","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","expiration_date":null,"id":"morph/morph-v3-large","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","discount":0,"prompt":"0.0000009"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Morph: Morph V3 Large","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","expiration_date":null,"id":"morph/morph-v3-large","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","discount":0,"prompt":"0.0000009"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nex-agi/nex-n2.5-mini\"]":{"classification":"paid","cost":{"completion":"0.0000001","discount":0,"input_cache_read":"0.0000000025","prompt":"0.000000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nex-agi/nex-n2.5-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-mini","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.0000000025","prompt":"0.000000025"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Nex AGI: Nex-N2.5-Mini","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-mini","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.0000000025","prompt":"0.000000025"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nex-agi/nex-n2.5-pro\"]":{"classification":"paid","cost":{"completion":"0.00000025","discount":0,"input_cache_read":"0.000000015","prompt":"0.000000075"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nex-agi/nex-n2.5-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-pro","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","discount":0,"input_cache_read":"0.000000015","prompt":"0.000000075"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Nex AGI: Nex-N2.5-Pro","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-pro","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","discount":0,"input_cache_read":"0.000000015","prompt":"0.000000075"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nousresearch/hermes-3-llama-3.1-405b\"]":{"classification":"paid","cost":{"completion":"0.000001","discount":0,"prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"nousresearch/hermes-3-llama-3.1-405b","lastListed":"2026-11-02T12:41:42.516Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1723766400,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","expiration_date":"2026-11-02","id":"nousresearch/hermes-3-llama-3.1-405b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 3 405B Instruct (retires Nov 2)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"prompt":"0.000001"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-02T12:41:42.516Z","source":"kilo"},"metadataRetained":true,"name":"Nous: Hermes 3 405B Instruct (retires Nov 2)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1723766400,"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","expiration_date":"2026-11-02","id":"nousresearch/hermes-3-llama-3.1-405b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 3 405B Instruct (retires Nov 2)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"prompt":"0.000001"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":["2026-11-02"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nousresearch/hermes-3-llama-3.1-70b\"]":{"classification":"paid","cost":{"completion":"0.0000007","discount":0,"prompt":"0.0000007"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"nousresearch/hermes-3-llama-3.1-70b","lastListed":"2026-11-02T12:41:42.516Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1723939200,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","expiration_date":"2026-11-02","id":"nousresearch/hermes-3-llama-3.1-70b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 3 70B Instruct (retires Nov 2)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000007","discount":0,"prompt":"0.0000007"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-02T12:41:42.516Z","source":"kilo"},"metadataRetained":true,"name":"Nous: Hermes 3 70B Instruct (retires Nov 2)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1723939200,"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","expiration_date":"2026-11-02","id":"nousresearch/hermes-3-llama-3.1-70b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 3 70B Instruct (retires Nov 2)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000007","discount":0,"prompt":"0.0000007"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":["2026-11-02"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nousresearch/hermes-4-405b\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nousresearch/hermes-4-405b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","expiration_date":null,"id":"nousresearch/hermes-4-405b","inference_provider_ids":["nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 4 405B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Nous: Hermes 4 405B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","expiration_date":null,"id":"nousresearch/hermes-4-405b","inference_provider_ids":["nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 4 405B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3-nano-30b-a3b\"]":{"classification":"paid","cost":{"completion":"0.00000024","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3-nano-30b-a3b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","expiration_date":null,"id":"nvidia/nemotron-3-nano-30b-a3b","inference_provider_ids":["deepinfra","nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","expiration_date":null,"id":"nvidia/nemotron-3-nano-30b-a3b","inference_provider_ids":["deepinfra","nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1777393095,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","raw":{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1777393095,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/nemotron-3-super-120b-a12b\"]":{"classification":"paid","cost":{"completion":"0.0000004","discount":0,"prompt":"0.000000075"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3-super-120b-a12b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","expiration_date":null,"id":"nvidia/nemotron-3-super-120b-a12b","inference_provider_ids":["amazon-bedrock","crusoe","deepinfra","dekallm"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Super","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3 Super","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","expiration_date":null,"id":"nvidia/nemotron-3-super-120b-a12b","inference_provider_ids":["amazon-bedrock","crusoe","deepinfra","dekallm"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Super","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3-super-120b-a12b:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"nvidia/nemotron-3-super-120b-a12b:free","lastListed":"2026-10-27T09:09:11.295Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-super-120b-a12b:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Super (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":0,"overallScore":0.15505618},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-10-27T09:09:11.295Z","source":"kilo"},"metadataRetained":true,"name":"NVIDIA: Nemotron 3 Super (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-super-120b-a12b:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Super (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":0,"overallScore":0.15505618},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/nemotron-3-ultra-550b-a55b\"]":{"classification":"paid","cost":{"completion":"0.00000176","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3-ultra-550b-a55b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","enkrypt":{"bias_score":87.34,"cbrn_score":52.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":6.22,"jailbreak_score":27.1942,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"nemotron-3-ultra-550b-a55b","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.0435,"robustness_score":null,"safety_score":41.7803,"source":"nvidia","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","inference_provider_ids":["baseten","deepinfra","fireworks","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000176","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":101.8186902,"overallScore":0.19101124},"top_provider":{"context_length":202800,"is_moderated":false,"max_completion_tokens":182520}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3 Ultra","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","enkrypt":{"bias_score":87.34,"cbrn_score":52.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":6.22,"jailbreak_score":27.1942,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"nemotron-3-ultra-550b-a55b","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.0435,"robustness_score":null,"safety_score":41.7803,"source":"nvidia","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","inference_provider_ids":["baseten","deepinfra","fireworks","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000176","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":101.8186902,"overallScore":0.19101124},"top_provider":{"context_length":202800,"is_moderated":false,"max_completion_tokens":182520}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3-ultra-550b-a55b:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Ultra (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3 Ultra (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Ultra (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/nemotron-3.5-content-safety\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3.5-content-safety","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","expiration_date":null,"id":"nvidia/nemotron-3.5-content-safety","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Content Safety","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3.5 Content Safety","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","expiration_date":null,"id":"nvidia/nemotron-3.5-content-safety","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Content Safety","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3.5-content-safety:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"nvidia/nemotron-3.5-content-safety:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-content-safety:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-content-safety:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/nemotron-3.5-lightning\"]":{"classification":"paid","cost":{"completion":"0.00000012","discount":0,"input_cache_read":"0.0000000125","prompt":"0.000000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3.5-lightning","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning","inference_provider_ids":["coreweave","darkbloom","deepinfra","fireworks","io-net","runinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Lightning","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"input_cache_read":"0.0000000125","prompt":"0.000000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3.5 Lightning","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning","inference_provider_ids":["coreweave","darkbloom","deepinfra","fireworks","io-net","runinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Lightning","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"input_cache_read":"0.0000000125","prompt":"0.000000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3.5-lightning:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3.5-lightning:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Lightning (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3.5 Lightning (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Lightning (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/nemotron-3.5-super-vl\"]":{"classification":"paid","cost":{"completion":"0.00000035","discount":0,"input_cache_read":"0.00000001","prompt":"0.00000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3.5-super-vl","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl","inference_provider_ids":["baseten","coreweave","crusoe","darkbloom","deepinfra","io-net","nebius","primeintellect","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Super VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000035","discount":0,"input_cache_read":"0.00000001","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3.5 Super VL","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl","inference_provider_ids":["baseten","coreweave","crusoe","darkbloom","deepinfra","io-net","nebius","primeintellect","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Super VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000035","discount":0,"input_cache_read":"0.00000001","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"nvidia/nemotron-3.5-super-vl:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/nemotron-3.5-super-vl:free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Super VL (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"preferredIndex":2,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Nemotron 3.5 Super VL (free)","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Super VL (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"preferredIndex":2,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"nvidia/switchyard\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvidia/switchyard","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790025947,"description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","expiration_date":null,"id":"nvidia/switchyard","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Switchyard","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"NVIDIA: Switchyard","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790025947,"description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","expiration_date":null,"id":"nvidia/switchyard","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Switchyard","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-3.5-turbo\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/gpt-3.5-turbo","lastListed":"2026-10-24T17:36:40.089Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":16385,"created":1685232000,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","enkrypt":{"bias_score":89.92,"cbrn_score":12.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":62.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":39.11,"jailbreak_score":10.7237,"lastCheckedAt":"2026-10-24T04:00:24.363Z","model_name":"gpt-3.5-turbo","nist_score":43,"owasp_score":48,"provider":"OpenAI","risk_score":43.0926,"robustness_score":null,"safety_score":33.832,"source":"OpenAI","staleAfter":"2026-10-25T06:00:24.363Z","toxicity_score":10.82},"expiration_date":null,"id":"openai/gpt-3.5-turbo","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16385,"is_moderated":true,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-10-24T17:36:40.089Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: GPT-3.5 Turbo","raw":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":16385,"created":1685232000,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","enkrypt":{"bias_score":89.92,"cbrn_score":12.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":62.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":39.11,"jailbreak_score":10.7237,"lastCheckedAt":"2026-10-24T04:00:24.363Z","model_name":"gpt-3.5-turbo","nist_score":43,"owasp_score":48,"provider":"OpenAI","risk_score":43.0926,"robustness_score":null,"safety_score":33.832,"source":"OpenAI","staleAfter":"2026-10-25T06:00:24.363Z","toxicity_score":10.82},"expiration_date":null,"id":"openai/gpt-3.5-turbo","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16385,"is_moderated":true,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-3.5-turbo-0613\"]":{"classification":"paid","cost":{"completion":"0.000002","prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-3.5-turbo-0613","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":4095,"created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","expiration_date":null,"id":"openai/gpt-3.5-turbo-0613","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":4095,"is_moderated":false,"max_completion_tokens":3685}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","raw":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":4095,"created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","expiration_date":null,"id":"openai/gpt-3.5-turbo-0613","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":4095,"is_moderated":false,"max_completion_tokens":3685}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-3.5-turbo-16k\"]":{"classification":"paid","cost":{"completion":"0.000004","prompt":"0.000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-3.5-turbo-16k","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":16385,"created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","expiration_date":null,"id":"openai/gpt-3.5-turbo-16k","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo 16k","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000004","prompt":"0.000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16385,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-3.5 Turbo 16k","raw":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":16385,"created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","expiration_date":null,"id":"openai/gpt-3.5-turbo-16k","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo 16k","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000004","prompt":"0.000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16385,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-3.5-turbo-instruct\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"prompt":"0.0000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/gpt-3.5-turbo-instruct","lastListed":"2026-10-24T17:36:40.089Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":4095,"created":1695859200,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","expiration_date":null,"id":"openai/gpt-3.5-turbo-instruct","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo Instruct","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.0000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":4095,"is_moderated":true,"max_completion_tokens":3685}},"metadataProvenance":{"fetchedAt":"2026-10-24T17:36:40.089Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: GPT-3.5 Turbo Instruct","raw":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":4095,"created":1695859200,"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","expiration_date":null,"id":"openai/gpt-3.5-turbo-instruct","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo Instruct","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.0000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":4095,"is_moderated":true,"max_completion_tokens":3685}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4\"]":{"classification":"paid","cost":{"completion":"0.00006","prompt":"0.00003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":8191,"created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","enkrypt":{"bias_score":84.75,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16.89,"jailbreak_score":4.47368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4","nist_score":27,"owasp_score":32,"provider":"OpenAI","risk_score":27.3327,"robustness_score":null,"safety_score":25.917,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.91},"expiration_date":null,"id":"openai/gpt-4","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4 ($$$$)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00006","prompt":"0.00003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":8191,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4 ($$$$)","raw":{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":8191,"created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","enkrypt":{"bias_score":84.75,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16.89,"jailbreak_score":4.47368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4","nist_score":27,"owasp_score":32,"provider":"OpenAI","risk_score":27.3327,"robustness_score":null,"safety_score":25.917,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.91},"expiration_date":null,"id":"openai/gpt-4","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4 ($$$$)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00006","prompt":"0.00003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":8191,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4-turbo\"]":{"classification":"paid","cost":{"completion":"0.00003","discount":0,"prompt":"0.00001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/gpt-4-turbo","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","enkrypt":{"bias_score":82.43,"cbrn_score":6,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":20,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16,"jailbreak_score":3.15789,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"gpt-4-turbo","nist_score":25,"owasp_score":30,"provider":"OpenAI","risk_score":25.1949,"robustness_score":null,"safety_score":19.9324,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":1.55},"expiration_date":null,"id":"openai/gpt-4-turbo","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4 Turbo ($$$$)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"prompt":"0.00001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: GPT-4 Turbo ($$$$)","raw":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","enkrypt":{"bias_score":82.43,"cbrn_score":6,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":20,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16,"jailbreak_score":3.15789,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"gpt-4-turbo","nist_score":25,"owasp_score":30,"provider":"OpenAI","risk_score":25.1949,"robustness_score":null,"safety_score":19.9324,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":1.55},"expiration_date":null,"id":"openai/gpt-4-turbo","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4 Turbo ($$$$)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"prompt":"0.00001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4.1\"]":{"classification":"paid","cost":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","enkrypt":{"bias_score":82.17,"cbrn_score":10,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.11,"jailbreak_score":7.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1","nist_score":27,"owasp_score":31,"provider":"openai","risk_score":26.7472,"robustness_score":null,"safety_score":22.1525,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"openai/gpt-4.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4.1","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","enkrypt":{"bias_score":82.17,"cbrn_score":10,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.11,"jailbreak_score":7.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1","nist_score":27,"owasp_score":31,"provider":"openai","risk_score":26.7472,"robustness_score":null,"safety_score":22.1525,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"openai/gpt-4.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4.1-mini\"]":{"classification":"paid","cost":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000004","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4.1-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","enkrypt":{"bias_score":84.5,"cbrn_score":11.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":10.7895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-mini","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":31.3871,"robustness_score":null,"safety_score":21.4286,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.77},"expiration_date":null,"id":"openai/gpt-4.1-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000004","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4.1 Mini","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","enkrypt":{"bias_score":84.5,"cbrn_score":11.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":10.7895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-mini","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":31.3871,"robustness_score":null,"safety_score":21.4286,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.77},"expiration_date":null,"id":"openai/gpt-4.1-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000004","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4.1-nano\"]":{"classification":"paid","cost":{"completion":"0.0000004","input_cache_read":"0.00000003","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4.1-nano","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","enkrypt":{"bias_score":87.08,"cbrn_score":10.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12.44,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-nano","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":30.7776,"robustness_score":null,"safety_score":21.139,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.86},"expiration_date":null,"id":"openai/gpt-4.1-nano","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Nano","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.00000003","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":false,"max_completion_tokens":942818}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4.1 Nano","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","enkrypt":{"bias_score":87.08,"cbrn_score":10.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12.44,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-nano","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":30.7776,"robustness_score":null,"safety_score":21.139,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.86},"expiration_date":null,"id":"openai/gpt-4.1-nano","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Nano","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.00000003","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":false,"max_completion_tokens":942818}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","enkrypt":{"bias_score":83.46,"cbrn_score":5.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":3.68421,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o","nist_score":26,"owasp_score":30,"provider":"OpenAI","risk_score":25.7279,"robustness_score":null,"safety_score":19.5946,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"openai/gpt-4o","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","enkrypt":{"bias_score":83.46,"cbrn_score":5.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":3.68421,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o","nist_score":26,"owasp_score":30,"provider":"OpenAI","risk_score":25.7279,"robustness_score":null,"safety_score":19.5946,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"openai/gpt-4o","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o-2024-05-13\"]":{"classification":"paid","cost":{"completion":"0.000015","prompt":"0.000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o-2024-05-13","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","expiration_date":null,"id":"openai/gpt-4o-2024-05-13","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-05-13)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000015","prompt":"0.000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o (2024-05-13)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","expiration_date":null,"id":"openai/gpt-4o-2024-05-13","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-05-13)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000015","prompt":"0.000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o-2024-08-06\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o-2024-08-06","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","enkrypt":{"bias_score":79.33,"cbrn_score":6.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":32.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":5.19737,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-2024-08-06","nist_score":26,"owasp_score":30,"provider":"openai","risk_score":25.9949,"robustness_score":null,"safety_score":18.4363,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.59},"expiration_date":null,"id":"openai/gpt-4o-2024-08-06","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-08-06)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o (2024-08-06)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","enkrypt":{"bias_score":79.33,"cbrn_score":6.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":32.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":5.19737,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-2024-08-06","nist_score":26,"owasp_score":30,"provider":"openai","risk_score":25.9949,"robustness_score":null,"safety_score":18.4363,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.59},"expiration_date":null,"id":"openai/gpt-4o-2024-08-06","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-08-06)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o-2024-11-20\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o-2024-11-20","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","expiration_date":null,"id":"openai/gpt-4o-2024-11-20","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-11-20)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o (2024-11-20)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","expiration_date":null,"id":"openai/gpt-4o-2024-11-20","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-11-20)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o-mini\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","enkrypt":{"bias_score":86.3,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":39.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.67,"jailbreak_score":5.85526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-mini","nist_score":31,"owasp_score":35,"provider":"OpenAI","risk_score":30.8832,"robustness_score":null,"safety_score":21.7181,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"openai/gpt-4o-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o-mini","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","enkrypt":{"bias_score":86.3,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":39.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.67,"jailbreak_score":5.85526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-mini","nist_score":31,"owasp_score":35,"provider":"OpenAI","risk_score":30.8832,"robustness_score":null,"safety_score":21.7181,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"openai/gpt-4o-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-4o-mini-2024-07-18\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-4o-mini-2024-07-18","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","expiration_date":null,"id":"openai/gpt-4o-mini-2024-07-18","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini (2024-07-18)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-4o-mini (2024-07-18)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","expiration_date":null,"id":"openai/gpt-4o-mini-2024-07-18","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini (2024-07-18)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","enkrypt":{"bias_score":40.05,"cbrn_score":7.11,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":2.07317,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5","nist_score":12,"owasp_score":14,"provider":"openai","risk_score":11.7922,"robustness_score":null,"safety_score":14.389,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"openai/gpt-5","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","enkrypt":{"bias_score":40.05,"cbrn_score":7.11,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":2.07317,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5","nist_score":12,"owasp_score":14,"provider":"openai","risk_score":11.7922,"robustness_score":null,"safety_score":14.389,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"openai/gpt-5","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5-image\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5-image","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","expiration_date":null,"id":"openai/gpt-5-image","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5 Image ($$$$)","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","expiration_date":null,"id":"openai/gpt-5-image","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5-image-mini\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5-image-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","expiration_date":null,"id":"openai/gpt-5-image-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5 Image Mini","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","expiration_date":null,"id":"openai/gpt-5-image-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5-mini\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","enkrypt":{"bias_score":58.91,"cbrn_score":3.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.11,"jailbreak_score":2.57576,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-mini","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":15.7763,"robustness_score":null,"safety_score":16.0232,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.8},"expiration_date":null,"id":"openai/gpt-5-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5 Mini","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","enkrypt":{"bias_score":58.91,"cbrn_score":3.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.11,"jailbreak_score":2.57576,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-mini","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":15.7763,"robustness_score":null,"safety_score":16.0232,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.8},"expiration_date":null,"id":"openai/gpt-5-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5-nano\"]":{"classification":"paid","cost":{"completion":"0.0000004","discount":0,"input_cache_read":"0.000000005","prompt":"0.00000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5-nano","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","enkrypt":{"bias_score":60.98,"cbrn_score":2,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":1.85567,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-nano","nist_score":15,"owasp_score":18,"provider":"openai","risk_score":14.9257,"robustness_score":null,"safety_score":14.334,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-5-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"input_cache_read":"0.000000005","prompt":"0.00000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5 Nano","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","enkrypt":{"bias_score":60.98,"cbrn_score":2,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":1.85567,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-nano","nist_score":15,"owasp_score":18,"provider":"openai","risk_score":14.9257,"robustness_score":null,"safety_score":14.334,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-5-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"input_cache_read":"0.000000005","prompt":"0.00000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5-pro\"]":{"classification":"paid","cost":{"completion":"0.00012","discount":0,"prompt":"0.000015","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","expiration_date":null,"id":"openai/gpt-5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00012","discount":0,"prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5 Pro ($$$$)","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","expiration_date":null,"id":"openai/gpt-5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00012","discount":0,"prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.1\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","enkrypt":{"bias_score":56.33,"cbrn_score":6.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":16.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4,"jailbreak_score":7.19424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.1","nist_score":17,"owasp_score":20,"provider":"openai","risk_score":17.4611,"robustness_score":null,"safety_score":21.5718,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"openai/gpt-5.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.1","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","enkrypt":{"bias_score":56.33,"cbrn_score":6.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":16.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4,"jailbreak_score":7.19424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.1","nist_score":17,"owasp_score":20,"provider":"openai","risk_score":17.4611,"robustness_score":null,"safety_score":21.5718,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"openai/gpt-5.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.1-codex\"]":{"classification":"paid","cost":{"completion":"0.00001","input_cache_read":"0.00000013","prompt":"0.00000125","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.1-codex","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.1-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.00000013","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.1-Codex","raw":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.1-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.00000013","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.1-codex-max\"]":{"classification":"paid","cost":{"completion":"0.00001","input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.1-codex-max","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","expiration_date":null,"id":"openai/gpt-5.1-codex-max","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Max","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.1-Codex-Max","raw":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","expiration_date":null,"id":"openai/gpt-5.1-codex-max","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Max","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.1-codex-mini\"]":{"classification":"paid","cost":{"completion":"0.000002","input_cache_read":"0.00000003","prompt":"0.00000025","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.1-codex-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","expiration_date":null,"id":"openai/gpt-5.1-codex-mini","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.00000003","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.1-Codex-Mini","raw":{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","expiration_date":null,"id":"openai/gpt-5.1-codex-mini","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.00000003","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.2\"]":{"classification":"paid","cost":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","enkrypt":{"bias_score":58.4,"cbrn_score":10.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":4.02878,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.2","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":16.0341,"robustness_score":null,"safety_score":23.4162,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"openai/gpt-5.2","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.2","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","enkrypt":{"bias_score":58.4,"cbrn_score":10.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":4.02878,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.2","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":16.0341,"robustness_score":null,"safety_score":23.4162,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"openai/gpt-5.2","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.2-chat\"]":{"classification":"paid","cost":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/gpt-5.2-chat","lastListed":"2026-10-28T19:28:01.390Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","expiration_date":null,"id":"openai/gpt-5.2-chat","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2 Chat","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":32000}},"metadataProvenance":{"fetchedAt":"2026-10-28T19:28:01.390Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: GPT-5.2 Chat","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","expiration_date":null,"id":"openai/gpt-5.2-chat","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2 Chat","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":32000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.2-codex\"]":{"classification":"paid","cost":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.2-codex","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.2-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.2-Codex","raw":{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.2-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.2-pro\"]":{"classification":"paid","cost":{"completion":"0.000168","discount":0,"prompt":"0.000021","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.2-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","expiration_date":null,"id":"openai/gpt-5.2-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000168","discount":0,"prompt":"0.000021","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.2 Pro ($$$$)","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","expiration_date":null,"id":"openai/gpt-5.2-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000168","discount":0,"prompt":"0.000021","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.3-codex\"]":{"classification":"paid","cost":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.3-codex","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","expiration_date":null,"id":"openai/gpt-5.3-codex","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.3-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.3-Codex","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","expiration_date":null,"id":"openai/gpt-5.3-codex","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.3-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.4\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.4","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.4","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.4","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.4-image-2\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"input_cache_read":"0.000002","prompt":"0.000008","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.4-image-2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":272000,"created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","expiration_date":null,"id":"openai/gpt-5.4-image-2","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Image 2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.000002","prompt":"0.000008","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","top_logprobs","verbosity"],"top_provider":{"context_length":272000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.4 Image 2","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":272000,"created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","expiration_date":null,"id":"openai/gpt-5.4-image-2","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Image 2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.000002","prompt":"0.000008","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","top_logprobs","verbosity"],"top_provider":{"context_length":272000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.4-mini\"]":{"classification":"paid","cost":{"completion":"0.0000045","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.4-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","expiration_date":null,"id":"openai/gpt-5.4-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.4 Mini","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","expiration_date":null,"id":"openai/gpt-5.4-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.4-nano\"]":{"classification":"paid","cost":{"completion":"0.00000125","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.4-nano","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","expiration_date":null,"id":"openai/gpt-5.4-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.4 Nano","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","expiration_date":null,"id":"openai/gpt-5.4-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.4-pro\"]":{"classification":"paid","cost":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.4-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","expiration_date":null,"id":"openai/gpt-5.4-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.4 Pro ($$$$)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","expiration_date":null,"id":"openai/gpt-5.4-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.5\"]":{"classification":"paid","cost":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","enkrypt":{"bias_score":61.5,"cbrn_score":20.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.33,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.5","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.2109,"robustness_score":null,"safety_score":28.4683,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8},"expiration_date":null,"id":"openai/gpt-5.5","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":72.62918640000001,"overallScore":0.74157303},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.5","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","enkrypt":{"bias_score":61.5,"cbrn_score":20.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.33,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.5","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.2109,"robustness_score":null,"safety_score":28.4683,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8},"expiration_date":null,"id":"openai/gpt-5.5","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":72.62918640000001,"overallScore":0.74157303},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.5-pro\"]":{"classification":"paid","cost":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.5-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.5 Pro ($$$$)","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-luna\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-luna","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","enkrypt":{"bias_score":78.04,"cbrn_score":22.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":9.64029,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-luna","nist_score":23,"owasp_score":27,"provider":"openai","risk_score":22.8769,"robustness_score":null,"safety_score":33.6808,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"openai/gpt-5.6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Luna","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","enkrypt":{"bias_score":78.04,"cbrn_score":22.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":9.64029,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-luna","nist_score":23,"owasp_score":27,"provider":"openai","risk_score":22.8769,"robustness_score":null,"safety_score":33.6808,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"openai/gpt-5.6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-luna-pro\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-luna-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Luna Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-sol\"]":{"classification":"paid","cost":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-sol","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","enkrypt":{"bias_score":72.09,"cbrn_score":19.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-sol","nist_score":22,"owasp_score":25,"provider":"openai","risk_score":21.5671,"robustness_score":null,"safety_score":31.7562,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.91},"expiration_date":null,"id":"openai/gpt-5.6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.40998859999999,"overallScore":0.76179775},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Sol","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","enkrypt":{"bias_score":72.09,"cbrn_score":19.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-sol","nist_score":22,"owasp_score":25,"provider":"openai","risk_score":21.5671,"robustness_score":null,"safety_score":31.7562,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.91},"expiration_date":null,"id":"openai/gpt-5.6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.40998859999999,"overallScore":0.76179775},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-sol-pro\"]":{"classification":"paid","cost":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-sol-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Sol Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-terra\"]":{"classification":"paid","cost":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-terra","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","enkrypt":{"bias_score":60.72,"cbrn_score":20,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4.44,"jailbreak_score":8.48921,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-terra","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.0053,"robustness_score":null,"safety_score":28.2277,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.64},"expiration_date":null,"id":"openai/gpt-5.6-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Terra","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","enkrypt":{"bias_score":60.72,"cbrn_score":20,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4.44,"jailbreak_score":8.48921,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-terra","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.0053,"robustness_score":null,"safety_score":28.2277,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.64},"expiration_date":null,"id":"openai/gpt-5.6-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-5.6-terra-pro\"]":{"classification":"paid","cost":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-5.6-terra-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-5.6 Terra Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-astra\"]":{"classification":"paid","cost":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-astra","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","expiration_date":null,"id":"openai/gpt-6-astra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":107.293192,"overallScore":0.79325843},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Astra ($$$$)","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","expiration_date":null,"id":"openai/gpt-6-astra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":107.293192,"overallScore":0.79325843},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-astra-pro\"]":{"classification":"paid","cost":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-astra-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-astra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Astra Pro ($$$$)","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-astra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-luna\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-luna","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","expiration_date":null,"id":"openai/gpt-6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Luna","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","expiration_date":null,"id":"openai/gpt-6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-luna-pro\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-luna-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Luna Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-sol\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-sol","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","expiration_date":null,"id":"openai/gpt-6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Sol","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","expiration_date":null,"id":"openai/gpt-6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6-sol-pro\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6-sol-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6 Sol Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6.1-sol\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6.1-sol","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","expiration_date":null,"id":"openai/gpt-6.1-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":6,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6.1 Sol","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","expiration_date":null,"id":"openai/gpt-6.1-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":6,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6.1-sol-pro\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-6.1-sol-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6.1 Sol Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6.1-terra\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-26T19:11:32.182Z","fresh":true,"id":"openai/gpt-6.1-terra","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","expiration_date":null,"id":"openai/gpt-6.1-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6.1 Terra","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","expiration_date":null,"id":"openai/gpt-6.1-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-6.1-terra-pro\"]":{"classification":"paid","cost":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-27T01:15:53.771Z","fresh":true,"id":"openai/gpt-6.1-terra-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT-6.1 Terra Pro","raw":{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-audio\"]":{"classification":"paid","cost":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-audio","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","expiration_date":null,"id":"openai/gpt-audio","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Audio","raw":{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","expiration_date":null,"id":"openai/gpt-audio","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-audio-mini\"]":{"classification":"paid","cost":{"completion":"0.0000024","discount":0,"prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-audio-mini","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","expiration_date":null,"id":"openai/gpt-audio-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000024","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Audio Mini","raw":{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","expiration_date":null,"id":"openai/gpt-audio-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000024","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-chat-latest\"]":{"classification":"paid","cost":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-chat-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","expiration_date":null,"id":"openai/gpt-chat-latest","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Chat Latest","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Chat Latest","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","expiration_date":null,"id":"openai/gpt-chat-latest","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Chat Latest","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-oss-120b\"]":{"classification":"paid","cost":{"completion":"0.000000089","discount":0,"input_cache_read":"0.000000022","prompt":"0.000000024"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-oss-120b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","enkrypt":{"bias_score":60.21,"cbrn_score":13.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":14.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":18.8679,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-120b","nist_score":20,"owasp_score":22,"provider":"fireworks","risk_score":20.1454,"robustness_score":null,"safety_score":24.8614,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.91},"expiration_date":null,"id":"openai/gpt-oss-120b","inference_provider_ids":["akashml","amazon-bedrock","baseten","cerebras","coreweave","crusoe","deepinfra","dekallm","digitalocean","fireworks","google-vertex","groq","mancer","mara","near-ai","nebius","parasail","phala","primeintellect","sail-research","sambanova","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-120b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000089","discount":0,"input_cache_read":"0.000000022","prompt":"0.000000024"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: gpt-oss-120b","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","enkrypt":{"bias_score":60.21,"cbrn_score":13.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":14.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":18.8679,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-120b","nist_score":20,"owasp_score":22,"provider":"fireworks","risk_score":20.1454,"robustness_score":null,"safety_score":24.8614,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.91},"expiration_date":null,"id":"openai/gpt-oss-120b","inference_provider_ids":["akashml","amazon-bedrock","baseten","cerebras","coreweave","crusoe","deepinfra","dekallm","digitalocean","fireworks","google-vertex","groq","mancer","mara","near-ai","nebius","parasail","phala","primeintellect","sail-research","sambanova","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-120b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000089","discount":0,"input_cache_read":"0.000000022","prompt":"0.000000024"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-oss-20b\"]":{"classification":"paid","cost":{"completion":"0.00000009","discount":0,"input_cache_read":"0.000000009","prompt":"0.000000018"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-oss-20b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","enkrypt":{"bias_score":72.35,"cbrn_score":19,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":27.1698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-20b","nist_score":28,"owasp_score":30,"provider":"fireworks","risk_score":27.6703,"robustness_score":null,"safety_score":31.9778,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":20},"expiration_date":null,"id":"openai/gpt-oss-20b","inference_provider_ids":["akashml","amazon-bedrock","coreweave","darkbloom","deepinfra","dekallm","groq","parasail","primeintellect","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-20b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000009","discount":0,"input_cache_read":"0.000000009","prompt":"0.000000018"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: gpt-oss-20b","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","enkrypt":{"bias_score":72.35,"cbrn_score":19,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":27.1698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-20b","nist_score":28,"owasp_score":30,"provider":"fireworks","risk_score":27.6703,"robustness_score":null,"safety_score":31.9778,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":20},"expiration_date":null,"id":"openai/gpt-oss-20b","inference_provider_ids":["akashml","amazon-bedrock","coreweave","darkbloom","deepinfra","dekallm","groq","parasail","primeintellect","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-20b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000009","discount":0,"input_cache_read":"0.000000009","prompt":"0.000000018"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/gpt-oss-safeguard-20b\"]":{"classification":"paid","cost":{"completion":"0.0000003","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/gpt-oss-safeguard-20b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","enkrypt":{"bias_score":74.42,"cbrn_score":18,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":17.1223,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-safeguard-20b","nist_score":26,"owasp_score":29,"provider":"groq","risk_score":25.7241,"robustness_score":null,"safety_score":28.6287,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-oss-safeguard-20b","inference_provider_ids":["amazon-bedrock","groq"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-safeguard-20b","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: gpt-oss-safeguard-20b","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","enkrypt":{"bias_score":74.42,"cbrn_score":18,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":17.1223,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-safeguard-20b","nist_score":26,"owasp_score":29,"provider":"groq","risk_score":25.7241,"robustness_score":null,"safety_score":28.6287,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-oss-safeguard-20b","inference_provider_ids":["amazon-bedrock","groq"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-safeguard-20b","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o1\"]":{"classification":"paid","cost":{"completion":"0.00006","discount":0,"input_cache_read":"0.0000075","prompt":"0.000015","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o1","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1734459999,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","enkrypt":{"bias_score":82.17,"cbrn_score":3.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":3.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.11,"jailbreak_score":0.921053,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o1","nist_score":21,"owasp_score":26,"provider":"openai","risk_score":20.6856,"robustness_score":null,"safety_score":20.029,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":2.59},"expiration_date":null,"id":"openai/o1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o1 ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00006","discount":0,"input_cache_read":"0.0000075","prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o1 ($$$$)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1734459999,"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","enkrypt":{"bias_score":82.17,"cbrn_score":3.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":3.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.11,"jailbreak_score":0.921053,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o1","nist_score":21,"owasp_score":26,"provider":"openai","risk_score":20.6856,"robustness_score":null,"safety_score":20.029,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":2.59},"expiration_date":null,"id":"openai/o1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o1 ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00006","discount":0,"input_cache_read":"0.0000075","prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o1-pro\"]":{"classification":"paid","cost":{"completion":"0.0006","discount":0,"prompt":"0.00015","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o1-pro","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1742423211,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...","expiration_date":null,"id":"openai/o1-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o1-pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0006","discount":0,"prompt":"0.00015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o1-pro ($$$$)","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1742423211,"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...","expiration_date":null,"id":"openai/o1-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o1-pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0006","discount":0,"prompt":"0.00015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o3\"]":{"classification":"paid","cost":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/o3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","enkrypt":{"bias_score":77,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":2.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"o3","nist_score":21,"owasp_score":25,"provider":"openai","risk_score":20.9692,"robustness_score":null,"safety_score":22.249,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"openai/o3","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: o3","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","enkrypt":{"bias_score":77,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":2.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"o3","nist_score":21,"owasp_score":25,"provider":"openai","risk_score":20.9692,"robustness_score":null,"safety_score":22.249,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"openai/o3","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o3-mini\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o3-mini","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file","pdf"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","enkrypt":{"bias_score":81.91,"cbrn_score":8.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16.89,"jailbreak_score":4.07895,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o3-mini","nist_score":25,"owasp_score":30,"provider":"OpenAI","risk_score":25.4653,"robustness_score":null,"safety_score":22.8282,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":4.64},"expiration_date":null,"id":"openai/o3-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o3 Mini","raw":{"architecture":{"input_modalities":["text","file","pdf"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","enkrypt":{"bias_score":81.91,"cbrn_score":8.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16.89,"jailbreak_score":4.07895,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o3-mini","nist_score":25,"owasp_score":30,"provider":"OpenAI","risk_score":25.4653,"robustness_score":null,"safety_score":22.8282,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":4.64},"expiration_date":null,"id":"openai/o3-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o3-mini-high\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o3-mini-high","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file","pdf"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1739372611,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","expiration_date":null,"id":"openai/o3-mini-high","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Mini High","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o3 Mini High","raw":{"architecture":{"input_modalities":["text","file","pdf"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1739372611,"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","expiration_date":null,"id":"openai/o3-mini-high","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Mini High","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000055","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o3-pro\"]":{"classification":"paid","cost":{"completion":"0.00008","discount":0,"prompt":"0.00002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openai/o3-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","file","image","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","expiration_date":null,"id":"openai/o3-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00008","discount":0,"prompt":"0.00002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: o3 Pro ($$$$)","raw":{"architecture":{"input_modalities":["text","file","image","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","expiration_date":null,"id":"openai/o3-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00008","discount":0,"prompt":"0.00002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o4-mini\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o4-mini","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","enkrypt":{"bias_score":79.84,"cbrn_score":12.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12.44,"jailbreak_score":5.39474,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o4-mini","nist_score":25,"owasp_score":30,"provider":"openai","risk_score":25.3367,"robustness_score":null,"safety_score":24.4208,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":6.73},"expiration_date":null,"id":"openai/o4-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o4 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o4 Mini","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","enkrypt":{"bias_score":79.84,"cbrn_score":12.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12.44,"jailbreak_score":5.39474,"lastCheckedAt":"2026-10-28T04:00:23.845Z","model_name":"o4-mini","nist_score":25,"owasp_score":30,"provider":"openai","risk_score":25.3367,"robustness_score":null,"safety_score":24.4208,"source":"OpenAI","staleAfter":"2026-10-29T06:00:23.845Z","toxicity_score":6.73},"expiration_date":null,"id":"openai/o4-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o4 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openai/o4-mini-high\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"openai/o4-mini-high","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744824212,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","expiration_date":null,"id":"openai/o4-mini-high","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o4 Mini High","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"OpenAI: o4 Mini High","raw":{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744824212,"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","expiration_date":null,"id":"openai/o4-mini-high","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o4 Mini High","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.000000275","prompt":"0.0000011","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openrouter/auto\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/auto","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1699401600,"description":"The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...","expiration_date":null,"id":"openrouter/auto","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter Auto Router","raw":{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1699401600,"description":"The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...","expiration_date":null,"id":"openrouter/auto","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openrouter/auto-beta\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/auto-beta","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1784311165,"description":"The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...","expiration_date":null,"id":"openrouter/auto-beta","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router (Beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter Auto Router (Beta)","raw":{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1784311165,"description":"The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...","expiration_date":null,"id":"openrouter/auto-beta","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router (Beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openrouter/bodybuilder\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/bodybuilder","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":128000,"created":1764903653,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","expiration_date":null,"id":"openrouter/bodybuilder","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Body Builder (beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter Body Builder (beta)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":128000,"created":1764903653,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","expiration_date":null,"id":"openrouter/bodybuilder","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Body Builder (beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openrouter/free\"]":{"classification":"free","cost":{"completion":"0","prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":200000,"created":1769917427,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","expiration_date":null,"id":"openrouter/free","inference_provider_ids":["virtual"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"OpenRouter Free Models Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter Free Models Router","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":200000,"created":1769917427,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","expiration_date":null,"id":"openrouter/free","inference_provider_ids":["virtual"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"OpenRouter Free Models Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"openrouter/fusion\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/fusion","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781371647,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","expiration_date":null,"id":"openrouter/fusion","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter: Fusion","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter: Fusion","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781371647,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","expiration_date":null,"id":"openrouter/fusion","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter: Fusion","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"openrouter/pareto-code\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"openrouter/pareto-code","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":2000000,"created":1776747900,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...","expiration_date":null,"id":"openrouter/pareto-code","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Pareto Code Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenRouter Pareto Code Router","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":2000000,"created":1776747900,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...","expiration_date":null,"id":"openrouter/pareto-code","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Pareto Code Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"particle-ai/particle-1\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.000000003","prompt":"0.00000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-28T20:19:03.403Z","fresh":true,"id":"particle-ai/particle-1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","expiration_date":null,"id":"particle-ai/particle-1","inference_provider_ids":["particle-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Particle AI: Particle-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.000000003","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Particle AI: Particle-1","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","expiration_date":null,"id":"particle-ai/particle-1","inference_provider_ids":["particle-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Particle AI: Particle-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.000000003","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perceptron/perceptron-mk1\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perceptron/perceptron-mk1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","expiration_date":null,"id":"perceptron/perceptron-mk1","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perceptron: Perceptron Mk1","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","expiration_date":null,"id":"perceptron/perceptron-mk1","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perceptron/perceptron-mk1.5\"]":{"classification":"paid","cost":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perceptron/perceptron-mk1.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":36864,"created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","expiration_date":null,"id":"perceptron/perceptron-mk1.5","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":36864,"is_moderated":false,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perceptron: Perceptron Mk1.5","raw":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":36864,"created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","expiration_date":null,"id":"perceptron/perceptron-mk1.5","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":36864,"is_moderated":false,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perplexity/sonar\"]":{"classification":"paid","cost":{"completion":"0.000001","discount":0,"prompt":"0.000001","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perplexity/sonar","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":127072,"created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","expiration_date":null,"id":"perplexity/sonar","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"prompt":"0.000001","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":127072,"is_moderated":false,"max_completion_tokens":114364}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perplexity: Sonar","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":127072,"created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","expiration_date":null,"id":"perplexity/sonar","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"prompt":"0.000001","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":127072,"is_moderated":false,"max_completion_tokens":114364}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perplexity/sonar-deep-research\"]":{"classification":"paid","cost":{"completion":"0.000008","discount":0,"internal_reasoning":"0.000003","prompt":"0.000002","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perplexity/sonar-deep-research","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","expiration_date":null,"id":"perplexity/sonar-deep-research","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Deep Research","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"internal_reasoning":"0.000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perplexity: Sonar Deep Research","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","expiration_date":null,"id":"perplexity/sonar-deep-research","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Deep Research","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"internal_reasoning":"0.000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perplexity/sonar-pro\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perplexity/sonar-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","expiration_date":null,"id":"perplexity/sonar-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perplexity: Sonar Pro","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","expiration_date":null,"id":"perplexity/sonar-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perplexity/sonar-pro-search\"]":{"classification":"paid","cost":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.018"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perplexity/sonar-pro-search","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","expiration_date":null,"id":"perplexity/sonar-pro-search","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro Search","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.018"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perplexity: Sonar Pro Search","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","expiration_date":null,"id":"perplexity/sonar-pro-search","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro Search","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.018"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"perplexity/sonar-reasoning-pro\"]":{"classification":"paid","cost":{"completion":"0.000008","discount":0,"prompt":"0.000002","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"perplexity/sonar-reasoning-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","expiration_date":null,"id":"perplexity/sonar-reasoning-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Reasoning Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Perplexity: Sonar Reasoning Pro","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","expiration_date":null,"id":"perplexity/sonar-reasoning-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Reasoning Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"poolside/laguna-s-2.1\"]":{"classification":"paid","cost":{"completion":"0.000000200000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"poolside/laguna-s-2.1","lastListed":"2026-10-31T12:49:44.267Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","enkrypt":{"bias_score":87.34,"cbrn_score":47.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":25.33,"jailbreak_score":30.9353,"lastCheckedAt":"2026-10-31T04:00:23.907Z","model_name":"laguna-s-2.1","nist_score":38,"owasp_score":41,"provider":"openai_compatible","risk_score":37.6465,"robustness_score":null,"safety_score":42.2614,"source":"xAI","staleAfter":"2026-11-01T06:00:23.907Z","toxicity_score":2.73},"expiration_date":"2026-10-31","id":"poolside/laguna-s-2.1","inference_provider_ids":["poolside"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna S 2.1 (retires Oct 31)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000200000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"terminalBench":{"avgAttemptCostUsd":1.8518518,"overallScore":0.31011236},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-10-31T12:49:44.267Z","source":"kilo"},"metadataRetained":true,"name":"Poolside: Laguna S 2.1 (retires Oct 31)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","enkrypt":{"bias_score":87.34,"cbrn_score":47.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":25.33,"jailbreak_score":30.9353,"lastCheckedAt":"2026-10-31T04:00:23.907Z","model_name":"laguna-s-2.1","nist_score":38,"owasp_score":41,"provider":"openai_compatible","risk_score":37.6465,"robustness_score":null,"safety_score":42.2614,"source":"xAI","staleAfter":"2026-11-01T06:00:23.907Z","toxicity_score":2.73},"expiration_date":"2026-10-31","id":"poolside/laguna-s-2.1","inference_provider_ids":["poolside"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna S 2.1 (retires Oct 31)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000200000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"terminalBench":{"avgAttemptCostUsd":1.8518518,"overallScore":0.31011236},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-10-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"poolside/laguna-s-2.1:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"poolside/laguna-s-2.1:free","lastListed":"2026-10-31T12:49:44.267Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","expiration_date":"2026-10-31","id":"poolside/laguna-s-2.1:free","inference_provider_ids":["poolside"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna S 2.1 (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-10-31T12:49:44.267Z","source":"kilo"},"metadataRetained":true,"name":"Poolside: Laguna S 2.1 (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1784652683,"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","expiration_date":"2026-10-31","id":"poolside/laguna-s-2.1:free","inference_provider_ids":["poolside"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna S 2.1 (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":["2026-10-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"poolside/laguna-xs-2.1\"]":{"classification":"paid","cost":{"completion":"0.000000200000","input_cache_read":"0.000000050000","prompt":"0.000000100000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"poolside/laguna-xs-2.1","lastListed":"2026-10-31T12:49:44.267Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","enkrypt":{"bias_score":87.34,"cbrn_score":52.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":41.33,"jailbreak_score":38.705,"lastCheckedAt":"2026-10-31T04:00:23.907Z","model_name":"laguna-xs-2.1","nist_score":46,"owasp_score":50,"provider":"openai_compatible","risk_score":46.0061,"robustness_score":null,"safety_score":46.271,"source":"poolside","staleAfter":"2026-11-01T06:00:23.907Z","toxicity_score":3.64},"expiration_date":"2026-10-31","id":"poolside/laguna-xs-2.1","inference_provider_ids":["poolside"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna XS 2.1 (retires Oct 31)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000200000","input_cache_read":"0.000000050000","prompt":"0.000000100000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"terminalBench":{"avgAttemptCostUsd":12.027956199999998,"overallScore":0.26741573},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-10-31T12:49:44.267Z","source":"kilo"},"metadataRetained":true,"name":"Poolside: Laguna XS 2.1 (retires Oct 31)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","enkrypt":{"bias_score":87.34,"cbrn_score":52.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":41.33,"jailbreak_score":38.705,"lastCheckedAt":"2026-10-31T04:00:23.907Z","model_name":"laguna-xs-2.1","nist_score":46,"owasp_score":50,"provider":"openai_compatible","risk_score":46.0061,"robustness_score":null,"safety_score":46.271,"source":"poolside","staleAfter":"2026-11-01T06:00:23.907Z","toxicity_score":3.64},"expiration_date":"2026-10-31","id":"poolside/laguna-xs-2.1","inference_provider_ids":["poolside"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna XS 2.1 (retires Oct 31)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000200000","input_cache_read":"0.000000050000","prompt":"0.000000100000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"terminalBench":{"avgAttemptCostUsd":12.027956199999998,"overallScore":0.26741573},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":["2026-10-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"poolside/laguna-xs-2.1:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"poolside/laguna-xs-2.1:free","lastListed":"2026-10-31T12:49:44.267Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","expiration_date":"2026-10-31","id":"poolside/laguna-xs-2.1:free","inference_provider_ids":["poolside"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna XS 2.1 (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-10-31T12:49:44.267Z","source":"kilo"},"metadataRetained":true,"name":"Poolside: Laguna XS 2.1 (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783002429,"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","expiration_date":"2026-10-31","id":"poolside/laguna-xs-2.1:free","inference_provider_ids":["poolside"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Poolside: Laguna XS 2.1 (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":["2026-10-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"prism-ml/ternary-bonsai-2-27b\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"prism-ml/ternary-bonsai-2-27b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-27b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","xhigh"]}],"variants":{"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"PrismML: Ternary Bonsai 2 27B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-27b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","xhigh"]}],"variants":{"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"prism-ml/ternary-bonsai-2-9b\"]":{"classification":"paid","cost":{"completion":"0.00000013","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-27T19:57:53.011Z","fresh":true,"id":"prism-ml/ternary-bonsai-2-9b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-9b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"PrismML: Ternary Bonsai 2 9B","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-9b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen-2.5-72b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000004","prompt":"0.00000036"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen-2.5-72b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-72b-instruct","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.00000036"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen2.5 72B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-72b-instruct","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.00000036"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen-2.5-7b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000002","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen-2.5-7b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-7b-instruct","inference_provider_ids":["phala"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 7B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen2.5 7B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-7b-instruct","inference_provider_ids":["phala"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 7B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen-2.5-coder-32b-instruct\"]":{"classification":"paid","cost":{"completion":"0.000001","prompt":"0.00000066"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen-2.5-coder-32b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","expiration_date":null,"id":"qwen/qwen-2.5-coder-32b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 Coder 32B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000066"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen2.5 Coder 32B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","expiration_date":null,"id":"qwen/qwen-2.5-coder-32b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 Coder 32B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000066"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen-plus\"]":{"classification":"paid","cost":{"completion":"0.00000078","discount":0,"input_cache_read":"0.000000052","input_cache_write":"0.000000325","prompt":"0.00000026"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen-plus","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","expiration_date":null,"id":"qwen/qwen-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen-Plus","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000078","discount":0,"input_cache_read":"0.000000052","input_cache_write":"0.000000325","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen-Plus","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","expiration_date":null,"id":"qwen/qwen-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen-Plus","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000078","discount":0,"input_cache_read":"0.000000052","input_cache_write":"0.000000325","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen2.5-vl-72b-instruct\"]":{"classification":"paid","cost":{"completion":"0.000001","input_cache_read":"0.0000004","prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen2.5-vl-72b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":128000,"created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","expiration_date":null,"id":"qwen/qwen2.5-vl-72b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 VL 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000004","prompt":"0.0000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen2.5 VL 72B Instruct","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":128000,"created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","expiration_date":null,"id":"qwen/qwen2.5-vl-72b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 VL 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000004","prompt":"0.0000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-14b\"]":{"classification":"paid","cost":{"completion":"0.00000024","prompt":"0.00000012"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-14b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-14b","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 14B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 14B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-14b","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 14B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-235b-a22b-2507\"]":{"classification":"paid","cost":{"completion":"0.0000008","input_cache_read":"0.00000005","prompt":"0.00000014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-235b-a22b-2507","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-2507","inference_provider_ids":["deepinfra","gmicloud","google-vertex","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000005","prompt":"0.00000014"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 235B A22B Instruct 2507","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-2507","inference_provider_ids":["deepinfra","gmicloud","google-vertex","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000005","prompt":"0.00000014"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-235b-a22b-thinking-2507\"]":{"classification":"paid","cost":{"completion":"0.0000035","prompt":"0.00000045"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-235b-a22b-thinking-2507","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":128000,"created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Thinking 2507","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 235B A22B Thinking 2507","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":128000,"created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Thinking 2507","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-30b-a3b\"]":{"classification":"paid","cost":{"completion":"0.0000005","prompt":"0.00000012"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-30b-a3b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","enkrypt":{"bias_score":91.47,"cbrn_score":55.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":61.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":37.33,"jailbreak_score":27.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-30b-a3b","nist_score":50,"owasp_score":53,"provider":"fireworks","risk_score":49.6461,"robustness_score":null,"safety_score":24.9517,"source":"Qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"qwen/qwen3-30b-a3b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 30B A3B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","enkrypt":{"bias_score":91.47,"cbrn_score":55.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":61.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":37.33,"jailbreak_score":27.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-30b-a3b","nist_score":50,"owasp_score":53,"provider":"fireworks","risk_score":49.6461,"robustness_score":null,"safety_score":24.9517,"source":"Qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"qwen/qwen3-30b-a3b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-30b-a3b-instruct-2507\"]":{"classification":"paid","cost":{"completion":"0.0000003","input_cache_read":"0.0000001","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-30b-a3b-instruct-2507","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","expiration_date":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","inference_provider_ids":["dekallm","nebius","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 30B A3B Instruct 2507","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","expiration_date":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","inference_provider_ids":["dekallm","nebius","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-32b\"]":{"classification":"paid","cost":{"completion":"0.00000028","prompt":"0.00000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-32b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":131072,"created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-32b","inference_provider_ids":["amazon-bedrock","deepinfra","siliconflow","tenstorrent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 32B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 32B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":131072,"created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-32b","inference_provider_ids":["amazon-bedrock","deepinfra","siliconflow","tenstorrent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 32B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-coder\"]":{"classification":"paid","cost":{"completion":"0.000001","input_cache_read":"0.0000001","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-coder","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","expiration_date":null,"id":"qwen/qwen3-coder","inference_provider_ids":["deepinfra","google-vertex","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 480B A35B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000001","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 Coder 480B A35B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","expiration_date":null,"id":"qwen/qwen3-coder","inference_provider_ids":["deepinfra","google-vertex","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 480B A35B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000001","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-coder-30b-a3b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000006","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-coder-30b-a3b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","expiration_date":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","inference_provider_ids":["amazon-bedrock","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":true,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","expiration_date":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","inference_provider_ids":["amazon-bedrock","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":true,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-coder-flash\"]":{"classification":"paid","cost":{"completion":"0.000000975","discount":0,"input_cache_read":"0.000000039","input_cache_write":"0.00000024375","prompt":"0.000000195"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-coder-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","expiration_date":null,"id":"qwen/qwen3-coder-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Flash","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000975","discount":0,"input_cache_read":"0.000000039","input_cache_write":"0.00000024375","prompt":"0.000000195"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 Coder Flash","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","expiration_date":null,"id":"qwen/qwen3-coder-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Flash","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000975","discount":0,"input_cache_read":"0.000000039","input_cache_write":"0.00000024375","prompt":"0.000000195"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-coder-next\"]":{"classification":"paid","cost":{"completion":"0.0000008","input_cache_read":"0.00000007","prompt":"0.00000012"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-coder-next","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","expiration_date":null,"id":"qwen/qwen3-coder-next","inference_provider_ids":["amazon-bedrock","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Next","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000007","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 Coder Next","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","expiration_date":null,"id":"qwen/qwen3-coder-next","inference_provider_ids":["amazon-bedrock","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Next","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000007","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-next-80b-a3b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000011","input_cache_read":"0.00000007","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-next-80b-a3b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","expiration_date":null,"id":"qwen/qwen3-next-80b-a3b-instruct","inference_provider_ids":["deepinfra","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Next 80B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","input_cache_read":"0.00000007","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 Next 80B A3B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","expiration_date":null,"id":"qwen/qwen3-next-80b-a3b-instruct","inference_provider_ids":["deepinfra","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Next 80B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","input_cache_read":"0.00000007","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-next-80b-a3b-thinking\"]":{"classification":"paid","cost":{"completion":"0.0000012","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"qwen/qwen3-next-80b-a3b-thinking","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1757612284,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","expiration_date":null,"id":"qwen/qwen3-next-80b-a3b-thinking","inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Next 80B A3B Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Qwen: Qwen3 Next 80B A3B Thinking","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1757612284,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","expiration_date":null,"id":"qwen/qwen3-next-80b-a3b-thinking","inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Next 80B A3B Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-vl-235b-a22b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000019","input_cache_read":"0.0000001","prompt":"0.00000021"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-vl-235b-a22b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","enkrypt":{"bias_score":72.61,"cbrn_score":17.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":29.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":9.78,"jailbreak_score":18.1295,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-vl-235b-a22b-instruct","nist_score":27,"owasp_score":30,"provider":"novita","risk_score":26.9573,"robustness_score":null,"safety_score":29.2702,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","inference_provider_ids":["deepinfra","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 235B A22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","input_cache_read":"0.0000001","prompt":"0.00000021"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 VL 235B A22B Instruct","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","enkrypt":{"bias_score":72.61,"cbrn_score":17.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":29.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":9.78,"jailbreak_score":18.1295,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-vl-235b-a22b-instruct","nist_score":27,"owasp_score":30,"provider":"novita","risk_score":26.9573,"robustness_score":null,"safety_score":29.2702,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","inference_provider_ids":["deepinfra","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 235B A22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","input_cache_read":"0.0000001","prompt":"0.00000021"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-vl-30b-a3b-instruct\"]":{"classification":"paid","cost":{"completion":"0.0000006","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-vl-30b-a3b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","inference_provider_ids":["deepinfra","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 VL 30B A3B Instruct","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","inference_provider_ids":["deepinfra","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-vl-30b-a3b-thinking\"]":{"classification":"paid","cost":{"completion":"0.000001","prompt":"0.00000029"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-vl-30b-a3b-thinking","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 VL 30B A3B Thinking","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3-vl-8b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000075","input_cache_read":"0.00000012","prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3-vl-8b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","expiration_date":null,"id":"qwen/qwen3-vl-8b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","input_cache_read":"0.00000012","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3 VL 8B Instruct","raw":{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","expiration_date":null,"id":"qwen/qwen3-vl-8b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","input_cache_read":"0.00000012","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-122b-a10b\"]":{"classification":"paid","cost":{"completion":"0.00000208","discount":0,"prompt":"0.00000026"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-122b-a10b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","enkrypt":{"bias_score":59.69,"cbrn_score":29.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":14.1007,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-122b-a10b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.4986,"robustness_score":null,"safety_score":28.2277,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-122b-a10b","inference_provider_ids":["alibaba","atlas-cloud","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-122B-A10B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000208","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5-122B-A10B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","enkrypt":{"bias_score":59.69,"cbrn_score":29.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":14.1007,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-122b-a10b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.4986,"robustness_score":null,"safety_score":28.2277,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-122b-a10b","inference_provider_ids":["alibaba","atlas-cloud","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-122B-A10B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000208","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-27b\"]":{"classification":"paid","cost":{"completion":"0.00000156","discount":0,"prompt":"0.000000195"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-27b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","enkrypt":{"bias_score":60.47,"cbrn_score":28.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":6.22,"jailbreak_score":13.9568,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-27b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.0536,"robustness_score":null,"safety_score":27.7466,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-27b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","novita","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.000000195"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5-27B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","enkrypt":{"bias_score":60.47,"cbrn_score":28.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":6.22,"jailbreak_score":13.9568,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-27b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.0536,"robustness_score":null,"safety_score":27.7466,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-27b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","novita","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.000000195"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-35b-a3b\"]":{"classification":"paid","cost":{"completion":"0.0000013","discount":0,"prompt":"0.0000001625"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-35b-a3b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","enkrypt":{"bias_score":73.39,"cbrn_score":26.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":13.3813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-35b-a3b","nist_score":22,"owasp_score":26,"provider":"novita","risk_score":22.3043,"robustness_score":null,"safety_score":30.6335,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.64},"expiration_date":null,"id":"qwen/qwen3.5-35b-a3b","inference_provider_ids":["alibaba","atlas-cloud","darkbloom","deepinfra","parasail","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-35B-A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000013","discount":0,"prompt":"0.0000001625"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5-35B-A3B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","enkrypt":{"bias_score":73.39,"cbrn_score":26.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":13.3813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-35b-a3b","nist_score":22,"owasp_score":26,"provider":"novita","risk_score":22.3043,"robustness_score":null,"safety_score":30.6335,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.64},"expiration_date":null,"id":"qwen/qwen3.5-35b-a3b","inference_provider_ids":["alibaba","atlas-cloud","darkbloom","deepinfra","parasail","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-35B-A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000013","discount":0,"prompt":"0.0000001625"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-397b-a17b\"]":{"classification":"paid","cost":{"completion":"0.00000234","discount":0,"prompt":"0.00000039"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-397b-a17b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","enkrypt":{"bias_score":49.61,"cbrn_score":24.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":11.6547,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-397b-a17b","nist_score":17,"owasp_score":19,"provider":"novita","risk_score":17.0427,"robustness_score":null,"safety_score":23.2558,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.55},"expiration_date":null,"id":"qwen/qwen3.5-397b-a17b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","digitalocean","gmicloud","novita","parasail","phala","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 397B A17B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000234","discount":0,"prompt":"0.00000039"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5 397B A17B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","enkrypt":{"bias_score":49.61,"cbrn_score":24.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":11.6547,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-397b-a17b","nist_score":17,"owasp_score":19,"provider":"novita","risk_score":17.0427,"robustness_score":null,"safety_score":23.2558,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.55},"expiration_date":null,"id":"qwen/qwen3.5-397b-a17b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","digitalocean","gmicloud","novita","parasail","phala","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 397B A17B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000234","discount":0,"prompt":"0.00000039"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-9b\"]":{"classification":"paid","cost":{"completion":"0.00000025","prompt":"0.00000017"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-9b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","expiration_date":null,"id":"qwen/qwen3.5-9b","inference_provider_ids":["darkbloom","deepinfra","parasail","primeintellect","siliconflow","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","prompt":"0.00000017"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5-9B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","expiration_date":null,"id":"qwen/qwen3.5-9b","inference_provider_ids":["darkbloom","deepinfra","parasail","primeintellect","siliconflow","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","prompt":"0.00000017"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-flash-02-23\"]":{"classification":"paid","cost":{"completion":"0.00000026","discount":0,"prompt":"0.000000065"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-flash-02-23","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","expiration_date":null,"id":"qwen/qwen3.5-flash-02-23","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000026","discount":0,"prompt":"0.000000065"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5-Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","expiration_date":null,"id":"qwen/qwen3.5-flash-02-23","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000026","discount":0,"prompt":"0.000000065"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-plus-02-15\"]":{"classification":"paid","cost":{"completion":"0.00000156","discount":0,"prompt":"0.00000026"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-plus-02-15","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","expiration_date":null,"id":"qwen/qwen3.5-plus-02-15","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-02-15","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5 Plus 2026-02-15","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","expiration_date":null,"id":"qwen/qwen3.5-plus-02-15","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-02-15","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.5-plus-20260420\"]":{"classification":"paid","cost":{"completion":"0.0000018","discount":0,"input_cache_write":"0.000000375","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.5-plus-20260420","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","expiration_date":null,"id":"qwen/qwen3.5-plus-20260420","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-04-20","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","discount":0,"input_cache_write":"0.000000375","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.5 Plus 2026-04-20","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","expiration_date":null,"id":"qwen/qwen3.5-plus-20260420","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-04-20","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","discount":0,"input_cache_write":"0.000000375","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.6-27b\"]":{"classification":"paid","cost":{"completion":"0.0000027","discount":0,"prompt":"0.00000045"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.6-27b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","expiration_date":null,"id":"qwen/qwen3.6-27b","inference_provider_ids":["alibaba","chutes","deepinfra","phala","reka","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.6 27B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","expiration_date":null,"id":"qwen/qwen3.6-27b","inference_provider_ids":["alibaba","chutes","deepinfra","phala","reka","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.6-35b-a3b\"]":{"classification":"paid","cost":{"completion":"0.0000009","input_cache_read":"0.000000025","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.6-35b-a3b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","expiration_date":null,"id":"qwen/qwen3.6-35b-a3b","inference_provider_ids":["akashml","atlas-cloud","coreweave","darkbloom","deepinfra","dekallm","parasail","phala","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 35B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000025","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.6 35B A3B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","expiration_date":null,"id":"qwen/qwen3.6-35b-a3b","inference_provider_ids":["akashml","atlas-cloud","coreweave","darkbloom","deepinfra","dekallm","parasail","phala","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 35B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000025","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.6-flash\"]":{"classification":"paid","cost":{"completion":"0.000001125","discount":0,"input_cache_write":"0.000000234375","prompt":"0.0000001875"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.6-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","expiration_date":null,"id":"qwen/qwen3.6-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001125","discount":0,"input_cache_write":"0.000000234375","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.6 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","expiration_date":null,"id":"qwen/qwen3.6-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001125","discount":0,"input_cache_write":"0.000000234375","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.6-plus\"]":{"classification":"paid","cost":{"completion":"0.00000195","discount":0,"input_cache_write":"0.00000040625","prompt":"0.000000325"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.6-plus","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","expiration_date":null,"id":"qwen/qwen3.6-plus","inference_provider_ids":["alibaba","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000195","discount":0,"input_cache_write":"0.00000040625","prompt":"0.000000325"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.6 Plus","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","expiration_date":null,"id":"qwen/qwen3.6-plus","inference_provider_ids":["alibaba","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000195","discount":0,"input_cache_write":"0.00000040625","prompt":"0.000000325"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.7-flash\"]":{"classification":"paid","cost":{"completion":"0.00000013","discount":0,"input_cache_read":"0.000000006","input_cache_write":"0.000000038","prompt":"0.00000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.7-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","expiration_date":null,"id":"qwen/qwen3.7-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.000000006","input_cache_write":"0.000000038","prompt":"0.00000003"},"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.7 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","expiration_date":null,"id":"qwen/qwen3.7-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.000000006","input_cache_write":"0.000000038","prompt":"0.00000003"},"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.7-max\"]":{"classification":"paid","cost":{"completion":"0.000004425","discount":0,"input_cache_read":"0.000000295","input_cache_write":"0.00000184375","prompt":"0.000001475"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.7-max","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","enkrypt":{"bias_score":74.42,"cbrn_score":49.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":8.89,"jailbreak_score":26.9065,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.7-max","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2787,"robustness_score":null,"safety_score":36.8885,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"qwen/qwen3.7-max","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Max","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004425","discount":0,"input_cache_read":"0.000000295","input_cache_write":"0.00000184375","prompt":"0.000001475"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":20.6499772,"overallScore":0.54606742},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.7 Max","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","enkrypt":{"bias_score":74.42,"cbrn_score":49.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":8.89,"jailbreak_score":26.9065,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.7-max","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2787,"robustness_score":null,"safety_score":36.8885,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"qwen/qwen3.7-max","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Max","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004425","discount":0,"input_cache_read":"0.000000295","input_cache_write":"0.00000184375","prompt":"0.000001475"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":20.6499772,"overallScore":0.54606742},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.7-plus\"]":{"classification":"paid","cost":{"completion":"0.00000128","discount":0,"input_cache_read":"0.000000064","input_cache_write":"0.0000004","prompt":"0.00000032"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.7-plus","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","expiration_date":null,"id":"qwen/qwen3.7-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000128","discount":0,"input_cache_read":"0.000000064","input_cache_write":"0.0000004","prompt":"0.00000032"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.7 Plus","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","expiration_date":null,"id":"qwen/qwen3.7-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000128","discount":0,"input_cache_read":"0.000000064","input_cache_write":"0.0000004","prompt":"0.00000032"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-2.4t-a95b\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-2.4t-a95b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1048576,"created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","expiration_date":null,"id":"qwen/qwen3.8-2.4t-a95b","inference_provider_ids":["alibaba","deepinfra","fireworks","gmicloud","modal","novita","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 2.4T A95B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 2.4T A95B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1048576,"created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","expiration_date":null,"id":"qwen/qwen3.8-2.4t-a95b","inference_provider_ids":["alibaba","deepinfra","fireworks","gmicloud","modal","novita","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 2.4T A95B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-27b\"]":{"classification":"paid","cost":{"completion":"0.00000255","discount":0,"input_cache_read":"0.000000085","input_cache_write":"0.00000053125","prompt":"0.000000425"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-27b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1024000,"created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","expiration_date":null,"id":"qwen/qwen3.8-27b","inference_provider_ids":["akashml","alibaba","cerebras","chutes","cloudflare","coreweave","darkbloom","deepinfra","dekallm","ionstream","mancer","modal","modelrun","near-ai","nebius","novita","parasail","phala","primeintellect","reka","runinfra","streamlake","tenstorrent","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000255","discount":0,"input_cache_read":"0.000000085","input_cache_write":"0.00000053125","prompt":"0.000000425"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 27B","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1024000,"created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","expiration_date":null,"id":"qwen/qwen3.8-27b","inference_provider_ids":["akashml","alibaba","cerebras","chutes","cloudflare","coreweave","darkbloom","deepinfra","dekallm","ionstream","mancer","modal","modelrun","near-ai","nebius","novita","parasail","phala","primeintellect","reka","runinfra","streamlake","tenstorrent","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000255","discount":0,"input_cache_read":"0.000000085","input_cache_write":"0.00000053125","prompt":"0.000000425"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-flash\"]":{"classification":"paid","cost":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","input_cache_write":"0.0000002","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","expiration_date":null,"id":"qwen/qwen3.8-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","input_cache_write":"0.0000002","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","expiration_date":null,"id":"qwen/qwen3.8-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","input_cache_write":"0.0000002","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-max-0902\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-max-0902","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","expiration_date":null,"id":"qwen/qwen3.8-max-0902","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max (0902)","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 Max (0902)","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","expiration_date":null,"id":"qwen/qwen3.8-max-0902","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max (0902)","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-max-prime\"]":{"classification":"paid","cost":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000005","prompt":"0.000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-max-prime","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","expiration_date":null,"id":"qwen/qwen3.8-max-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max Prime","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000005","prompt":"0.000004"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 Max Prime","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","expiration_date":null,"id":"qwen/qwen3.8-max-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max Prime","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000005","prompt":"0.000004"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"qwen/qwen3.8-omni-flash\"]":{"classification":"paid","cost":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"qwen/qwen3.8-omni-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","expiration_date":null,"id":"qwen/qwen3.8-omni-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Omni Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Qwen: Qwen3.8 Omni Flash","raw":{"architecture":{"input_modalities":["text","image","audio","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","expiration_date":null,"id":"qwen/qwen3.8-omni-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Omni Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"recursive/flint-v1.0:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"recursive/flint-v1.0:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792622765,"description":"Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...","expiration_date":null,"id":"recursive/flint-v1.0:free","inference_provider_ids":["recursive"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Recursive: Flint (free)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","stop","temperature","tools","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"Recursive: Flint (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792622765,"description":"Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...","expiration_date":null,"id":"recursive/flint-v1.0:free","inference_provider_ids":["recursive"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Recursive: Flint (free)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","stop","temperature","tools","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"reflection/beam-1.0-501b-a23b\"]":{"classification":"paid","cost":{"completion":"0.000001","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"reflection/beam-1.0-501b-a23b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","expiration_date":null,"id":"reflection/beam-1.0-501b-a23b","inference_provider_ids":["baseten","coreweave","digitalocean","nebius","reflection","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reflection: Beam 1.0 501B A23B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Reflection: Beam 1.0 501B A23B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","expiration_date":null,"id":"reflection/beam-1.0-501b-a23b","inference_provider_ids":["baseten","coreweave","digitalocean","nebius","reflection","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reflection: Beam 1.0 501B A23B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"reflection/beam-free\"]":{"classification":"free","cost":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"reflection/beam-free","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"reflection/beam-free","context_length":1048576,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Beam is Reflection's reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference, served through Vercel AI Gateway at no cost. It supports function calling, structured outputs, and streaming, and takes text input only. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"reflection/beam-free","inference_provider_ids":["reflection"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Reflection: Beam 1.0 (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":3,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Reflection: Beam 1.0 (free)","raw":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"reflection/beam-free","context_length":1048576,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Beam is Reflection's reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference, served through Vercel AI Gateway at no cost. It supports function calling, structured outputs, and streaming, and takes text input only. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"reflection/beam-free","inference_provider_ids":["reflection"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Reflection: Beam 1.0 (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":3,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"rekaai/reka-edge\"]":{"classification":"paid","cost":{"completion":"0.0000001","discount":0,"prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"rekaai/reka-edge","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","expiration_date":null,"id":"rekaai/reka-edge","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Edge","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Reka Edge","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","expiration_date":null,"id":"rekaai/reka-edge","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Edge","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"rekaai/reka-flash-3\"]":{"classification":"paid","cost":{"completion":"0.0000002","discount":0,"prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"rekaai/reka-flash-3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","expiration_date":null,"id":"rekaai/reka-flash-3","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Flash 3","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Reka Flash 3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","expiration_date":null,"id":"rekaai/reka-flash-3","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Flash 3","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"relace/relace-apply-3\"]":{"classification":"paid","cost":{"completion":"0.00000125","discount":0,"prompt":"0.00000085"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"relace/relace-apply-3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","expiration_date":null,"id":"relace/relace-apply-3","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Apply 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"prompt":"0.00000085"},"supported_parameters":["max_tokens","seed","stop"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Relace: Relace Apply 3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","expiration_date":null,"id":"relace/relace-apply-3","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Apply 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"prompt":"0.00000085"},"supported_parameters":["max_tokens","seed","stop"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"relace/relace-search\"]":{"classification":"paid","cost":{"completion":"0.000003","discount":0,"prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"relace/relace-search","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","expiration_date":null,"id":"relace/relace-search","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Search","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.000001"},"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Relace: Relace Search","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","expiration_date":null,"id":"relace/relace-search","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Search","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.000001"},"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"ricursiveai/ripple-65b-preview\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-04T19:44:43.499Z","fresh":true,"id":"ricursiveai/ripple-65b-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","expiration_date":null,"id":"ricursiveai/ripple-65b-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ricursiveAI/Ripple-65B-Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000002"},"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ricursiveAI/Ripple-65B-Preview","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","expiration_date":null,"id":"ricursiveai/ripple-65b-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ricursiveAI/Ripple-65B-Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000002"},"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sakana/fugu-max\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sakana/fugu-max","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-max","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Max","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sakana: Fugu Max","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-max","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Max","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sakana/fugu-ultra\"]":{"classification":"paid","cost":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sakana/fugu-ultra","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-ultra","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sakana: Fugu Ultra","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-ultra","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sakana/fugu-ultra-v2\"]":{"classification":"paid","cost":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sakana/fugu-ultra-v2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","expiration_date":null,"id":"sakana/fugu-ultra-v2","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra v2","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sakana: Fugu Ultra v2","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","expiration_date":null,"id":"sakana/fugu-ultra-v2","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra v2","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sakana/sakana-namazu\"]":{"classification":"paid","cost":{"completion":"0.000004","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000095","web_search":"0.007"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sakana/sakana-namazu","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","expiration_date":null,"id":"sakana/sakana-namazu","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Sakana: Sakana Namazu","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000095","web_search":"0.007"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sakana: Sakana Namazu","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","expiration_date":null,"id":"sakana/sakana-namazu","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Sakana: Sakana Namazu","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000095","web_search":"0.007"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sao10k/l3-lunaris-8b\"]":{"classification":"paid","cost":{"completion":"0.00000005","discount":0,"prompt":"0.00000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sao10k/l3-lunaris-8b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":8192,"created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","expiration_date":null,"id":"sao10k/l3-lunaris-8b","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3 8B Lunaris","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":7372}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sao10K: Llama 3 8B Lunaris","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":8192,"created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","expiration_date":null,"id":"sao10k/l3-lunaris-8b","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3 8B Lunaris","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":7372}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"sao10k/l3.1-euryale-70b\"]":{"classification":"paid","cost":{"completion":"0.00000085","discount":0,"prompt":"0.00000085"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"sao10k/l3.1-euryale-70b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","expiration_date":null,"id":"sao10k/l3.1-euryale-70b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000085","discount":0,"prompt":"0.00000085"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","expiration_date":null,"id":"sao10k/l3.1-euryale-70b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000085","discount":0,"prompt":"0.00000085"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"scaledown/extract\"]":{"classification":"paid","cost":{"completion":"0.000000000000","prompt":"0.000000050000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"scaledown/extract","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","expiration_date":null,"id":"scaledown/extract","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Extract","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ScaleDown: Extract","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","expiration_date":null,"id":"scaledown/extract","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Extract","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"scaledown/summarize\"]":{"classification":"paid","cost":{"completion":"0.000000000000","prompt":"0.000000050000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"scaledown/summarize","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","expiration_date":null,"id":"scaledown/summarize","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Summarize","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":4000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ScaleDown: Summarize","raw":{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","expiration_date":null,"id":"scaledown/summarize","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Summarize","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":4000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stealth/claude-opus-4.6\"]":{"classification":"paid","cost":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"stealth/claude-opus-4.6","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.6","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.6 is offered at 20% lower cost than standard Claude Opus 4.6 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.6","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.6 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Stealth: Claude Opus 4.6 (20% off)","raw":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.6","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.6 is offered at 20% lower cost than standard Claude Opus 4.6 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.6","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.6 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stealth/claude-opus-4.7\"]":{"classification":"paid","cost":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"stealth/claude-opus-4.7","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.7","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.7 is offered at 20% lower cost than standard Claude Opus 4.7 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.7","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.7 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Stealth: Claude Opus 4.7 (20% off)","raw":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.7","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.7 is offered at 20% lower cost than standard Claude Opus 4.7 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.7","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.7 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stealth/claude-opus-4.8\"]":{"classification":"paid","cost":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"stealth/claude-opus-4.8","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.8","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.8 is offered at 20% lower cost than standard Claude Opus 4.8 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.8","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.8 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Stealth: Claude Opus 4.8 (20% off)","raw":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-opus-4.8","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.8 is offered at 20% lower cost than standard Claude Opus 4.8 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-opus-4.8","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Opus 4.8 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000020000000","image":"0","input_cache_read":"0.000000400000","input_cache_write":"0.000005000000","internal_reasoning":"0","prompt":"0.000004000000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stealth/claude-sonnet-4.6\"]":{"classification":"paid","cost":{"completion":"0.000012000000","image":"0","input_cache_read":"0.000000240000","input_cache_write":"0.000003000000","internal_reasoning":"0","prompt":"0.000002400000","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"stealth/claude-sonnet-4.6","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-sonnet-4.6","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Sonnet 4.6 is offered at 20% lower cost than standard Claude Sonnet 4.6 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-sonnet-4.6","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Sonnet 4.6 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000012000000","image":"0","input_cache_read":"0.000000240000","input_cache_write":"0.000003000000","internal_reasoning":"0","prompt":"0.000002400000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Stealth: Claude Sonnet 4.6 (20% off)","raw":{"architecture":{"input_modalities":["text","image","pdf"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/claude-sonnet-4.6","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Sonnet 4.6 is offered at 20% lower cost than standard Claude Sonnet 4.6 pricing and is not served by Anthropic or Kilo Code.","hugging_face_id":"","id":"stealth/claude-sonnet-4.6","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Claude Sonnet 4.6 (20% off)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000012000000","image":"0","input_cache_read":"0.000000240000","input_cache_write":"0.000003000000","internal_reasoning":"0","prompt":"0.000002400000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stealth/crouton-alpha\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-03T20:50:35.055Z","fresh":true,"id":"stealth/crouton-alpha","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","file","audio"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793669930,"description":"Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work. Developers...","expiration_date":null,"id":"stealth/crouton-alpha","inference_provider_ids":["stealth"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Crouton Alpha","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Crouton Alpha","raw":{"architecture":{"input_modalities":["text","image","video","file","audio"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793669930,"description":"Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work. Developers...","expiration_date":null,"id":"stealth/crouton-alpha","inference_provider_ids":["stealth"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Crouton Alpha","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"stealth/glyph-cluster\"]":{"classification":"free","cost":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"stealth/glyph-cluster","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/glyph-cluster","context_length":256000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Glyph Cluster is a reasoning model for coding and long-context analysis, served through Vercel AI Gateway during its stealth period at no cost. It supports function calling and streaming, takes text input only, and does not support structured outputs. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"stealth/glyph-cluster","inference_provider_ids":["stealth"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Stealth: Glyph Cluster (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":4,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":256000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Stealth: Glyph Cluster (free)","raw":{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/glyph-cluster","context_length":256000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Glyph Cluster is a reasoning model for coding and long-context analysis, served through Vercel AI Gateway during its stealth period at no cost. It supports function calling and streaming, takes text input only, and does not support structured outputs. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"stealth/glyph-cluster","inference_provider_ids":["stealth"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Stealth: Glyph Cluster (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":4,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":256000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"stealth/qwen3.6-plus\"]":{"classification":"paid","cost":{"completion":"0.000001500000","image":"0","input_cache_read":"0.000000025000","input_cache_write":"0.000000312500","internal_reasoning":"0","prompt":"0.000000250000","request":"0","web_search":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"stealth/qwen3.6-plus","lastListed":"2026-10-28T14:57:44.844Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/qwen3.6-plus","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.","hugging_face_id":"","id":"stealth/qwen3.6-plus","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Qwen3.6 Plus (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001500000","image":"0","input_cache_read":"0.000000025000","input_cache_write":"0.000000312500","internal_reasoning":"0","prompt":"0.000000250000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-10-28T14:57:44.844Z","source":"kilo"},"metadataRetained":true,"name":"Stealth: Qwen3.6 Plus (50% off)","raw":{"architecture":{"input_modalities":["text","image"],"instruct_type":null,"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/qwen3.6-plus","context_length":1000000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.","hugging_face_id":"","id":"stealth/qwen3.6-plus","inference_provider_ids":["stealth"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Stealth: Qwen3.6 Plus (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001500000","image":"0","input_cache_read":"0.000000025000","input_cache_write":"0.000000312500","internal_reasoning":"0","prompt":"0.000000250000","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stepfun/step-3.5-flash\"]":{"classification":"paid","cost":{"completion":"0.0000003","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"stepfun/step-3.5-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","expiration_date":null,"id":"stepfun/step-3.5-flash","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.5 Flash","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"StepFun: Step 3.5 Flash","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","expiration_date":null,"id":"stepfun/step-3.5-flash","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.5 Flash","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stepfun/step-3.7-flash\"]":{"classification":"paid","cost":{"completion":"0.00000115","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000002"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"stepfun/step-3.7-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","expiration_date":null,"id":"stepfun/step-3.7-flash","inference_provider_ids":["novita","stepfun"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000115","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"StepFun: Step 3.7 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","expiration_date":null,"id":"stepfun/step-3.7-flash","inference_provider_ids":["novita","stepfun"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000115","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"stepfun/step-5-preview\"]":{"classification":"paid","cost":{"completion":"0.0000027","discount":0,"input_cache_read":"0.0000001","prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"stepfun/step-5-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","expiration_date":null,"id":"stepfun/step-5-preview","inference_provider_ids":["deepinfra","featherless","gmicloud","stepfun","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 5 Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"input_cache_read":"0.0000001","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"StepFun: Step 5 Preview","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","expiration_date":null,"id":"stepfun/step-5-preview","inference_provider_ids":["deepinfra","featherless","gmicloud","stepfun","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 5 Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"input_cache_read":"0.0000001","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hunyuan-a13b-instruct\"]":{"classification":"paid","cost":{"completion":"0.00000057","discount":0,"prompt":"0.00000014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hunyuan-a13b-instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","enkrypt":{"bias_score":79.33,"cbrn_score":8.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":58.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Hunyuan-A13B-Instruct","nist_score":37,"owasp_score":42,"provider":"openai_compatible","risk_score":37.4464,"robustness_score":null,"safety_score":25.5309,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"tencent/hunyuan-a13b-instruct","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hunyuan A13B Instruct","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000057","discount":0,"prompt":"0.00000014"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hunyuan A13B Instruct","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","enkrypt":{"bias_score":79.33,"cbrn_score":8.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":58.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Hunyuan-A13B-Instruct","nist_score":37,"owasp_score":42,"provider":"openai_compatible","risk_score":37.4464,"robustness_score":null,"safety_score":25.5309,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"tencent/hunyuan-a13b-instruct","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hunyuan A13B Instruct","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000057","discount":0,"prompt":"0.00000014"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy-mt2-1.8b\"]":{"classification":"paid","cost":{"completion":"0.000000177","discount":0,"prompt":"0.000000044"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy-mt2-1.8b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","expiration_date":null,"id":"tencent/hy-mt2-1.8b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-1.8B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000177","discount":0,"prompt":"0.000000044"},"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy-MT2-1.8B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","expiration_date":null,"id":"tencent/hy-mt2-1.8b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-1.8B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000177","discount":0,"prompt":"0.000000044"},"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy-mt2-30b-a3b\"]":{"classification":"paid","cost":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy-mt2-30b-a3b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","expiration_date":null,"id":"tencent/hy-mt2-30b-a3b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-30B-A3B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy-MT2-30B-A3B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","expiration_date":null,"id":"tencent/hy-mt2-30b-a3b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-30B-A3B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy-mt2-7b\"]":{"classification":"paid","cost":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy-mt2-7b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","expiration_date":null,"id":"tencent/hy-mt2-7b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-7B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy-MT2-7B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","expiration_date":null,"id":"tencent/hy-mt2-7b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-7B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy3\"]":{"classification":"paid","cost":{"completion":"0.00000033","discount":0,"input_cache_read":"0.000000020625","prompt":"0.0000000825"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","enkrypt":{"bias_score":56.07,"cbrn_score":0.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":1.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"hy3","nist_score":15,"owasp_score":19,"provider":"novita","risk_score":15.1549,"robustness_score":null,"safety_score":20.6095,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"tencent/hy3","inference_provider_ids":["atlas-cloud","gmicloud","novita","phala","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"input_cache_read":"0.000000020625","prompt":"0.0000000825"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","enkrypt":{"bias_score":56.07,"cbrn_score":0.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":1.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"hy3","nist_score":15,"owasp_score":19,"provider":"novita","risk_score":15.1549,"robustness_score":null,"safety_score":20.6095,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"tencent/hy3","inference_provider_ids":["atlas-cloud","gmicloud","novita","phala","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"input_cache_read":"0.000000020625","prompt":"0.0000000825"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy3-preview\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000018"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy3-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","expiration_date":null,"id":"tencent/hy3-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000018"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy3 preview","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","expiration_date":null,"id":"tencent/hy3-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000018"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy4\"]":{"classification":"paid","cost":{"completion":"0.000002501000","input_cache_read":"0.000000042000","prompt":"0.000000834000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-04T04:59:22.390Z","fresh":true,"id":"tencent/hy4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","expiration_date":null,"id":"tencent/hy4","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002501000","input_cache_read":"0.000000042000","prompt":"0.000000834000"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy4","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","expiration_date":null,"id":"tencent/hy4","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002501000","input_cache_read":"0.000000042000","prompt":"0.000000834000"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"tencent/hy4-preview\"]":{"classification":"paid","cost":{"completion":"0.0000022509","discount":0,"input_cache_read":"0.0000000378","prompt":"0.0000007506"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"tencent/hy4-preview","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","expiration_date":null,"id":"tencent/hy4-preview","inference_provider_ids":["atlas-cloud","cohere","deepinfra","gmicloud","novita","siliconflow","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022509","discount":0,"input_cache_read":"0.0000000378","prompt":"0.0000007506"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":64000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Tencent: Hy4 preview","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","expiration_date":null,"id":"tencent/hy4-preview","inference_provider_ids":["atlas-cloud","cohere","deepinfra","gmicloud","novita","siliconflow","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022509","discount":0,"input_cache_read":"0.0000000378","prompt":"0.0000007506"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":64000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thedrummer/cydonia-24b-v4.1\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"thedrummer/cydonia-24b-v4.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","expiration_date":null,"id":"thedrummer/cydonia-24b-v4.1","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Cydonia 24B V4.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"TheDrummer: Cydonia 24B V4.1","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","expiration_date":null,"id":"thedrummer/cydonia-24b-v4.1","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Cydonia 24B V4.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thedrummer/skyfall-36b-v2\"]":{"classification":"paid","cost":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000025","prompt":"0.00000055"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"thedrummer/skyfall-36b-v2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","expiration_date":null,"id":"thedrummer/skyfall-36b-v2","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Skyfall 36B V2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000025","prompt":"0.00000055"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"TheDrummer: Skyfall 36B V2","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","expiration_date":null,"id":"thedrummer/skyfall-36b-v2","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Skyfall 36B V2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000025","prompt":"0.00000055"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thedrummer/unslopnemo-12b\"]":{"classification":"paid","cost":{"completion":"0.0000004","discount":0,"prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"thedrummer/unslopnemo-12b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1024000,"created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","expiration_date":null,"id":"thedrummer/unslopnemo-12b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: UnslopNemo 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1024000,"is_moderated":false,"max_completion_tokens":819200}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"TheDrummer: UnslopNemo 12B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1024000,"created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","expiration_date":null,"id":"thedrummer/unslopnemo-12b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: UnslopNemo 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1024000,"is_moderated":false,"max_completion_tokens":819200}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thinkingmachines/inkling\"]":{"classification":"paid","cost":{"completion":"0.00000405","discount":0,"input_cache_read":"0.00000017","prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"thinkingmachines/inkling","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","enkrypt":{"bias_score":60.98,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":0.719424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Inkling","nist_score":15,"owasp_score":19,"provider":"together","risk_score":15.2186,"robustness_score":null,"safety_score":24.2983,"source":"ThinkingMachines","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"thinkingmachines/inkling","inference_provider_ids":["modal","thinkingmachines","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000405","discount":0,"input_cache_read":"0.00000017","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":35.689686,"overallScore":0.43595506},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":471859}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Thinking Machines: Inkling","raw":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","enkrypt":{"bias_score":60.98,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":0.719424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Inkling","nist_score":15,"owasp_score":19,"provider":"together","risk_score":15.2186,"robustness_score":null,"safety_score":24.2983,"source":"ThinkingMachines","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"thinkingmachines/inkling","inference_provider_ids":["modal","thinkingmachines","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000405","discount":0,"input_cache_read":"0.00000017","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":35.689686,"overallScore":0.43595506},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":471859}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thinkingmachines/inkling-small\"]":{"classification":"paid","cost":{"completion":"0.0000012","discount":0,"input_cache_read":"0.0000001","prompt":"0.00000045"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"thinkingmachines/inkling-small","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","expiration_date":null,"id":"thinkingmachines/inkling-small","inference_provider_ids":["deepinfra","thinkingmachines"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling Small","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.0000001","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Thinking Machines: Inkling Small","raw":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","expiration_date":null,"id":"thinkingmachines/inkling-small","inference_provider_ids":["deepinfra","thinkingmachines"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling Small","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.0000001","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"thinkingmachines/inkling-small:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-02T23:03:49.693Z","fresh":false,"id":"thinkingmachines/inkling-small:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","expiration_date":"2026-11-04","id":"thinkingmachines/inkling-small:free","inference_provider_ids":["thinkingmachines"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Thinking Machines: Inkling Small (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"Thinking Machines: Inkling Small (free)","raw":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","expiration_date":"2026-11-04","id":"thinkingmachines/inkling-small:free","inference_provider_ids":["thinkingmachines"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Thinking Machines: Inkling Small (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":["2026-11-04"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"thinkingmachines/inkling:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-02T23:03:49.693Z","fresh":false,"id":"thinkingmachines/inkling:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","expiration_date":"2026-11-04","id":"thinkingmachines/inkling:free","inference_provider_ids":["thinkingmachines"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Thinking Machines: Inkling (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"Thinking Machines: Inkling (free)","raw":{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","expiration_date":"2026-11-04","id":"thinkingmachines/inkling:free","inference_provider_ids":["thinkingmachines"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Thinking Machines: Inkling (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","seed","stop","temperature","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},"retirementDates":["2026-11-04"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"typesafe/jev-router\"]":{"classification":"unknown","cost":{"completion":"-1","prompt":"-1"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"typesafe/jev-router","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["audio","file","image","text","video"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790363560,"description":"Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...","expiration_date":null,"id":"typesafe/jev-router","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TypeSafe: Jev Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"TypeSafe: Jev Router","raw":{"architecture":{"input_modalities":["audio","file","image","text","video"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790363560,"description":"Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...","expiration_date":null,"id":"typesafe/jev-router","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TypeSafe: Jev Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"unbiased/pareto-26.10\"]":{"classification":"paid","cost":{"completion":"0.0000032","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"unbiased/pareto-26.10","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.10","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.10","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Pareto 26.10","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.10","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.10","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"unbiased/pareto-26.9\"]":{"classification":"paid","cost":{"completion":"0.0000075","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"unbiased/pareto-26.9","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.9","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.9","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025"},"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Pareto 26.9","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.9","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.9","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025"},"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"undi95/remm-slerp-l2-13b\"]":{"classification":"paid","cost":{"completion":"0.00000065","discount":0,"prompt":"0.00000035"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"undi95/remm-slerp-l2-13b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":6144,"created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","expiration_date":null,"id":"undi95/remm-slerp-l2-13b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ReMM SLERP 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000035"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":6144,"is_moderated":false,"max_completion_tokens":5529}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"ReMM SLERP 13B","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":6144,"created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","expiration_date":null,"id":"undi95/remm-slerp-l2-13b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ReMM SLERP 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000035"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":6144,"is_moderated":false,"max_completion_tokens":5529}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"upstage/solar-mini4\"]":{"classification":"paid","cost":{"completion":"0.000000400000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"upstage/solar-mini4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","expiration_date":null,"id":"upstage/solar-mini4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Mini 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000400000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Upstage: Solar Mini 4","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","expiration_date":null,"id":"upstage/solar-mini4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Mini 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000400000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"upstage/solar-pro-3\"]":{"classification":"paid","cost":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"upstage/solar-pro-3","lastListed":"2026-10-29T16:29:02.750Z","lifecycle":"retired","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1769481200,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...","expiration_date":"2026-10-30","id":"upstage/solar-pro-3","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Pro 3 (retires Oct 30)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-10-29T16:29:02.750Z","source":"kilo"},"metadataRetained":true,"name":"Upstage: Solar Pro 3 (retires Oct 30)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1769481200,"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...","expiration_date":"2026-10-30","id":"upstage/solar-pro-3","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Pro 3 (retires Oct 30)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":["2026-10-30"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"upstage/solar-pro4\"]":{"classification":"paid","cost":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"upstage/solar-pro4","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","expiration_date":null,"id":"upstage/solar-pro4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Pro 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Upstage: Solar Pro 4","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","expiration_date":null,"id":"upstage/solar-pro4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Pro 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"writer/palmyra-x5\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"writer/palmyra-x5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1040000,"created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","expiration_date":null,"id":"writer/palmyra-x5","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Writer: Palmyra X5","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"prompt":"0.0000006"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":1040000,"is_moderated":true,"max_completion_tokens":8192}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Writer: Palmyra X5","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1040000,"created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","expiration_date":null,"id":"writer/palmyra-x5","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Writer: Palmyra X5","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"prompt":"0.0000006"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":1040000,"is_moderated":true,"max_completion_tokens":8192}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.20\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.20","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","expiration_date":null,"id":"x-ai/grok-4.20","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.20","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","expiration_date":null,"id":"x-ai/grok-4.20","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.20-multi-agent\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.20-multi-agent","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","expiration_date":null,"id":"x-ai/grok-4.20-multi-agent","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20 Multi-Agent","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.20 Multi-Agent","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","expiration_date":null,"id":"x-ai/grok-4.20-multi-agent","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20 Multi-Agent","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.3\"]":{"classification":"paid","cost":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":1000000,"created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","enkrypt":{"bias_score":87.08,"cbrn_score":34.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":22.446,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.3","nist_score":31,"owasp_score":36,"provider":"xai","risk_score":31.3584,"robustness_score":null,"safety_score":39.6151,"source":"xai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.55},"expiration_date":null,"id":"x-ai/grok-4.3","inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.3","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":1000000,"created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","enkrypt":{"bias_score":87.08,"cbrn_score":34.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":22.446,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.3","nist_score":31,"owasp_score":36,"provider":"xai","risk_score":31.3584,"robustness_score":null,"safety_score":39.6151,"source":"xai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.55},"expiration_date":null,"id":"x-ai/grok-4.3","inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.5\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000003","prompt":"0.000002","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","enkrypt":{"bias_score":66.41,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":10.3597,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.5","nist_score":20,"owasp_score":22,"provider":"openai_compatible","risk_score":19.5645,"robustness_score":null,"safety_score":29.591,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.64},"expiration_date":null,"id":"x-ai/grok-4.5","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":27.291154,"overallScore":0.70786517},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.5","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","enkrypt":{"bias_score":66.41,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":10.3597,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.5","nist_score":20,"owasp_score":22,"provider":"openai_compatible","risk_score":19.5645,"robustness_score":null,"safety_score":29.591,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.64},"expiration_date":null,"id":"x-ai/grok-4.5","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":27.291154,"overallScore":0.70786517},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.6\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","enkrypt":{"bias_score":35.14,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":7.33813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.6","nist_score":13,"owasp_score":14,"provider":"openai_compatible","risk_score":12.683,"robustness_score":null,"safety_score":19.9679,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"x-ai/grok-4.6","inference_provider_ids":["amazon-bedrock","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.6","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":33.829006,"overallScore":0.73033708},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.6","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","enkrypt":{"bias_score":35.14,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":7.33813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.6","nist_score":13,"owasp_score":14,"provider":"openai_compatible","risk_score":12.683,"robustness_score":null,"safety_score":19.9679,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"x-ai/grok-4.6","inference_provider_ids":["amazon-bedrock","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.6","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":33.829006,"overallScore":0.73033708},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-4.7\"]":{"classification":"paid","cost":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-4.7","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","expiration_date":null,"id":"x-ai/grok-4.7","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.7","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok 4.7","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","expiration_date":null,"id":"x-ai/grok-4.7","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.7","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"x-ai/grok-build-0.1\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001","web_search":"0.005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"x-ai/grok-build-0.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":256000,"created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","enkrypt":{"bias_score":84.75,"cbrn_score":46.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":13.33,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.89,"jailbreak_score":27.7698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-build-0.1","nist_score":34,"owasp_score":37,"provider":"openai_compatible","risk_score":33.9681,"robustness_score":null,"safety_score":42.903,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":12.36},"expiration_date":null,"id":"x-ai/grok-build-0.1","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok Build 0.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":30.701289600000003,"overallScore":0.50561798},"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"SpaceXAI: Grok Build 0.1","raw":{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":256000,"created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","enkrypt":{"bias_score":84.75,"cbrn_score":46.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":13.33,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.89,"jailbreak_score":27.7698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-build-0.1","nist_score":34,"owasp_score":37,"provider":"openai_compatible","risk_score":33.9681,"robustness_score":null,"safety_score":42.903,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":12.36},"expiration_date":null,"id":"x-ai/grok-build-0.1","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok Build 0.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":30.701289600000003,"overallScore":0.50561798},"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xiaomi/mimo-v2.5\"]":{"classification":"paid","cost":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"xiaomi/mimo-v2.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","expiration_date":null,"id":"xiaomi/mimo-v2.5","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Xiaomi: MiMo-V2.5","raw":{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","expiration_date":null,"id":"xiaomi/mimo-v2.5","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xiaomi/mimo-v2.5-pro\"]":{"classification":"paid","cost":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"xiaomi/mimo-v2.5-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","enkrypt":{"bias_score":71.06,"cbrn_score":47,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.33,"jailbreak_score":24.4604,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"mimo-v2.5-pro","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.8866,"robustness_score":null,"safety_score":35.2847,"source":"xiaomi","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":null,"id":"xiaomi/mimo-v2.5-pro","inference_provider_ids":["atlas-cloud","digitalocean","gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":4.9236556,"overallScore":0.47640449},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Xiaomi: MiMo-V2.5-Pro","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","enkrypt":{"bias_score":71.06,"cbrn_score":47,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.33,"jailbreak_score":24.4604,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"mimo-v2.5-pro","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.8866,"robustness_score":null,"safety_score":35.2847,"source":"xiaomi","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":null,"id":"xiaomi/mimo-v2.5-pro","inference_provider_ids":["atlas-cloud","digitalocean","gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":4.9236556,"overallScore":0.47640449},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xiaomi/mimo-v2.6-flash\"]":{"classification":"paid","cost":{"completion":"0.00000028","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"xiaomi/mimo-v2.6-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","expiration_date":null,"id":"xiaomi/mimo-v2.6-flash","inference_provider_ids":["boundless","cohere","darkbloom","deepinfra","gmicloud","inference-net","makora","novita","tencent","venice","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Xiaomi: MiMo-V2.6-Flash","raw":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","expiration_date":null,"id":"xiaomi/mimo-v2.6-flash","inference_provider_ids":["boundless","cohere","darkbloom","deepinfra","gmicloud","inference-net","makora","novita","tencent","venice","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xiaomi/mimo-v2.6-pro\"]":{"classification":"paid","cost":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"xiaomi/mimo-v2.6-pro","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro","inference_provider_ids":["boundless","deepinfra","gmicloud","novita","streamlake","tencent","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Xiaomi: MiMo-V2.6-Pro","raw":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro","inference_provider_ids":["boundless","deepinfra","gmicloud","novita","streamlake","tencent","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xiaomi/mimo-v2.6-pro-ultraspeed\"]":{"classification":"paid","cost":{"completion":"0.0000087","discount":0,"input_cache_read":"0.000000036","prompt":"0.00000435"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"xiaomi/mimo-v2.6-pro-ultraspeed","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro-ultraspeed","inference_provider_ids":["xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000087","discount":0,"input_cache_read":"0.000000036","prompt":"0.00000435"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","raw":{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro-ultraspeed","inference_provider_ids":["xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000087","discount":0,"input_cache_read":"0.000000036","prompt":"0.00000435"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"xingchen-agi/xing4.0-29b-a4b:free\"]":{"classification":"free","cost":{"completion":"0","discount":0,"prompt":"0"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"xingchen-agi/xing4.0-29b-a4b:free","lastListed":"2026-11-03T18:54:08.077Z","lifecycle":"not-listed","listed":false,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792177496,"description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...","expiration_date":null,"id":"xingchen-agi/xing4.0-29b-a4b:free","inference_provider_ids":["phala"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"XingChen: Xing4.0 29B A4B (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"metadataProvenance":{"fetchedAt":"2026-11-03T18:54:08.077Z","source":"kilo"},"metadataRetained":true,"name":"XingChen: Xing4.0 29B A4B (free)","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792177496,"description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...","expiration_date":null,"id":"xingchen-agi/xing4.0-29b-a4b:free","inference_provider_ids":["phala"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"XingChen: Xing4.0 29B A4B (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"kilo\",\"z-ai/glm-4.5\"]":{"classification":"paid","cost":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","enkrypt":{"bias_score":69.51,"cbrn_score":22.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36.89,"jailbreak_score":17.8333,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.5","nist_score":36,"owasp_score":40,"provider":"novita","risk_score":36.1503,"robustness_score":null,"safety_score":36.9792,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.24},"expiration_date":"2026-12-31","id":"z-ai/glm-4.5","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.5","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","enkrypt":{"bias_score":69.51,"cbrn_score":22.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36.89,"jailbreak_score":17.8333,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.5","nist_score":36,"owasp_score":40,"provider":"novita","risk_score":36.1503,"robustness_score":null,"safety_score":36.9792,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.24},"expiration_date":"2026-12-31","id":"z-ai/glm-4.5","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"retirementDates":["2026-12-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.5-air\"]":{"classification":"paid","cost":{"completion":"0.00000085","input_cache_read":"0.000000025","prompt":"0.00000013"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.5-air","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","expiration_date":null,"id":"z-ai/glm-4.5-air","inference_provider_ids":["novita","siliconflow","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5 Air","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000085","input_cache_read":"0.000000025","prompt":"0.00000013"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.5 Air","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","expiration_date":null,"id":"z-ai/glm-4.5-air","inference_provider_ids":["novita","siliconflow","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5 Air","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000085","input_cache_read":"0.000000025","prompt":"0.00000013"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.5v\"]":{"classification":"paid","cost":{"completion":"0.0000018","input_cache_read":"0.00000011","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.5v","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","expiration_date":"2026-12-31","id":"z-ai/glm-4.5v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":16384}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.5V","raw":{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","expiration_date":"2026-12-31","id":"z-ai/glm-4.5v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":16384}},"retirementDates":["2026-12-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.6\"]":{"classification":"paid","cost":{"completion":"0.000002","input_cache_read":"0.0000001","prompt":"0.0000005"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.6","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","enkrypt":{"bias_score":87.34,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.6","nist_score":37,"owasp_score":40,"provider":"novita","risk_score":36.7101,"robustness_score":null,"safety_score":40.0962,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-4.6","inference_provider_ids":["deepinfra","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.0000001","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.6","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","enkrypt":{"bias_score":87.34,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.6","nist_score":37,"owasp_score":40,"provider":"novita","risk_score":36.7101,"robustness_score":null,"safety_score":40.0962,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-4.6","inference_provider_ids":["deepinfra","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.0000001","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.6v\"]":{"classification":"paid","cost":{"completion":"0.0000009","input_cache_read":"0.000000055","prompt":"0.0000003"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.6v","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","expiration_date":null,"id":"z-ai/glm-4.6v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000055","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.6V","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","expiration_date":null,"id":"z-ai/glm-4.6v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000055","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.7\"]":{"classification":"paid","cost":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.7","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","expiration_date":"2026-12-31","id":"z-ai/glm-4.7","inference_provider_ids":["amazon-bedrock","deepinfra","mancer","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.7","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","expiration_date":"2026-12-31","id":"z-ai/glm-4.7","inference_provider_ids":["amazon-bedrock","deepinfra","mancer","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":["2026-12-31"],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-4.7-flash\"]":{"classification":"paid","cost":{"completion":"0.0000004","prompt":"0.0000000605"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-4.7-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","expiration_date":null,"id":"z-ai/glm-4.7-flash","inference_provider_ids":["amazon-bedrock","cloudflare","novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.0000000605"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 4.7 Flash","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","expiration_date":null,"id":"z-ai/glm-4.7-flash","inference_provider_ids":["amazon-bedrock","cloudflare","novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.0000000605"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5\"]":{"classification":"paid","cost":{"completion":"0.0000032","input_cache_read":"0.0000002","prompt":"0.000001"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","expiration_date":null,"id":"z-ai/glm-5","inference_provider_ids":["amazon-bedrock","baidu","gmicloud","novita","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","expiration_date":null,"id":"z-ai/glm-5","inference_provider_ids":["amazon-bedrock","baidu","gmicloud","novita","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5-turbo\"]":{"classification":"paid","cost":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5-turbo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","enkrypt":{"bias_score":88.11,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":11.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":13.6691,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5-turbo","nist_score":28,"owasp_score":32,"provider":"openrouter","risk_score":27.8652,"robustness_score":null,"safety_score":36.9687,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-5-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5 Turbo","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","enkrypt":{"bias_score":88.11,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":11.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":13.6691,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5-turbo","nist_score":28,"owasp_score":32,"provider":"openrouter","risk_score":27.8652,"robustness_score":null,"safety_score":36.9687,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-5-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.1\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.1","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","enkrypt":{"bias_score":76.49,"cbrn_score":21,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.1","nist_score":24,"owasp_score":28,"provider":"novita","risk_score":24.4588,"robustness_score":null,"safety_score":32.7185,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"z-ai/glm-5.1","inference_provider_ids":["alibaba","atlas-cloud","baidu","chutes","friendli","gmicloud","nebius","novita","phala","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":23.9824468,"overallScore":0.49438202},"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.1","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","enkrypt":{"bias_score":76.49,"cbrn_score":21,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.1","nist_score":24,"owasp_score":28,"provider":"novita","risk_score":24.4588,"robustness_score":null,"safety_score":32.7185,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"z-ai/glm-5.1","inference_provider_ids":["alibaba","atlas-cloud","baidu","chutes","friendli","gmicloud","nebius","novita","phala","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":23.9824468,"overallScore":0.49438202},"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.2\"]":{"classification":"paid","cost":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","enkrypt":{"bias_score":86.3,"cbrn_score":50.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":13.78,"jailbreak_score":29.0647,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.2","nist_score":33,"owasp_score":36,"provider":"openai_compatible","risk_score":32.5842,"robustness_score":null,"safety_score":40.016,"source":"z-ai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"z-ai/glm-5.2","inference_provider_ids":["alibaba","ambient","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","digitalocean","friendli","gmicloud","inceptron","mistral","morph","nebius","novita","parasail","relace","runware","siliconflow","streamlake","tencent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.2","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":26.2141134,"overallScore":0.53033708},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.2","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","enkrypt":{"bias_score":86.3,"cbrn_score":50.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":13.78,"jailbreak_score":29.0647,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.2","nist_score":33,"owasp_score":36,"provider":"openai_compatible","risk_score":32.5842,"robustness_score":null,"safety_score":40.016,"source":"z-ai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"z-ai/glm-5.2","inference_provider_ids":["alibaba","ambient","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","digitalocean","friendli","gmicloud","inceptron","mistral","morph","nebius","novita","parasail","relace","runware","siliconflow","streamlake","tencent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.2","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":26.2141134,"overallScore":0.53033708},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.3\"]":{"classification":"paid","cost":{"completion":"0.000004400000","input_cache_read":"0.000000260000","prompt":"0.000001400000"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","expiration_date":null,"id":"z-ai/glm-5.3","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004400000","input_cache_read":"0.000000260000","prompt":"0.000001400000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.3","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","expiration_date":null,"id":"z-ai/glm-5.3","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004400000","input_cache_read":"0.000000260000","prompt":"0.000001400000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.3-flash\"]":{"classification":"paid","cost":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000015"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.3-flash","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","expiration_date":null,"id":"z-ai/glm-5.3-flash","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"preferredIndex":8,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.3 Flash","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","expiration_date":null,"id":"z-ai/glm-5.3-flash","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"preferredIndex":8,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.3-flashx\"]":{"classification":"paid","cost":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.3-flashx","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","expiration_date":null,"id":"z-ai/glm-5.3-flashx","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.3 FlashX","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","expiration_date":null,"id":"z-ai/glm-5.3-flashx","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.3-flashx-legal\"]":{"classification":"paid","cost":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-11-02T13:56:33.393Z","fresh":true,"id":"z-ai/glm-5.3-flashx-legal","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","expiration_date":null,"id":"z-ai/glm-5.3-flashx-legal","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX Legal","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.3 FlashX Legal","raw":{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","expiration_date":null,"id":"z-ai/glm-5.3-flashx-legal","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX Legal","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5.3-prime\"]":{"classification":"paid","cost":{"completion":"0.0000088","input_cache_read":"0.00000056","prompt":"0.0000028"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5.3-prime","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","expiration_date":null,"id":"z-ai/glm-5.3-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Prime","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000088","input_cache_read":"0.00000056","prompt":"0.0000028"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5.3 Prime","raw":{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","expiration_date":null,"id":"z-ai/glm-5.3-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Prime","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000088","input_cache_read":"0.00000056","prompt":"0.0000028"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"z-ai/glm-5v-turbo\"]":{"classification":"paid","cost":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"z-ai/glm-5v-turbo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","expiration_date":null,"id":"z-ai/glm-5v-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5V Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM 5V Turbo","raw":{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","expiration_date":null,"id":"z-ai/glm-5v-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5V Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~anthropic/claude-fable-latest\"]":{"classification":"paid","cost":{"completion":"0.00005","input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~anthropic/claude-fable-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"anthropic/claude-fable-5.1","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","expiration_date":null,"id":"~anthropic/claude-fable-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable Latest ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Fable Latest ($$$$)","raw":{"alias_target":"anthropic/claude-fable-5.1","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","expiration_date":null,"id":"~anthropic/claude-fable-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable Latest ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~anthropic/claude-haiku-latest\"]":{"classification":"paid","cost":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~anthropic/claude-haiku-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"anthropic/claude-haiku-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","expiration_date":null,"id":"~anthropic/claude-haiku-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Haiku Latest","raw":{"alias_target":"anthropic/claude-haiku-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","expiration_date":null,"id":"~anthropic/claude-haiku-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~anthropic/claude-opus-latest\"]":{"classification":"paid","cost":{"completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~anthropic/claude-opus-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"anthropic/claude-opus-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","expiration_date":null,"id":"~anthropic/claude-opus-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Opus Latest","raw":{"alias_target":"anthropic/claude-opus-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","expiration_date":null,"id":"~anthropic/claude-opus-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~anthropic/claude-sonnet-latest\"]":{"classification":"paid","cost":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~anthropic/claude-sonnet-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"anthropic/claude-sonnet-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","expiration_date":null,"id":"~anthropic/claude-sonnet-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Anthropic: Claude Sonnet Latest","raw":{"alias_target":"anthropic/claude-sonnet-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","expiration_date":null,"id":"~anthropic/claude-sonnet-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~deepseek/deepseek-flash-latest\"]":{"classification":"paid","cost":{"completion":"0.0000004","input_cache_read":"0.000000004","prompt":"0.000000022"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~deepseek/deepseek-flash-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"deepseek/deepseek-v4.1-flash-1017","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","expiration_date":null,"id":"~deepseek/deepseek-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.000000004","prompt":"0.000000022"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek Flash Latest","raw":{"alias_target":"deepseek/deepseek-v4.1-flash-1017","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","expiration_date":null,"id":"~deepseek/deepseek-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.000000004","prompt":"0.000000022"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~deepseek/deepseek-pro-latest\"]":{"classification":"paid","cost":{"completion":"0.000008","input_cache_read":"0.0000001","prompt":"0.0000001035"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~deepseek/deepseek-pro-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"deepseek/deepseek-v4-pro-0813","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","expiration_date":null,"id":"~deepseek/deepseek-pro-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","input_cache_read":"0.0000001","prompt":"0.0000001035"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek Pro Latest","raw":{"alias_target":"deepseek/deepseek-v4-pro-0813","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","expiration_date":null,"id":"~deepseek/deepseek-pro-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","input_cache_read":"0.0000001","prompt":"0.0000001035"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~deepseek/deepseek-v4-flash-latest\"]":{"classification":"paid","cost":{"completion":"0.00000013728","input_cache_read":"0.000000001456","prompt":"0.00000004576"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~deepseek/deepseek-v4-flash-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"deepseek/deepseek-v4-flash-0731","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","expiration_date":null,"id":"~deepseek/deepseek-v4-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013728","input_cache_read":"0.000000001456","prompt":"0.00000004576"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"DeepSeek: DeepSeek V4 Flash Latest","raw":{"alias_target":"deepseek/deepseek-v4-flash-0731","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","expiration_date":null,"id":"~deepseek/deepseek-v4-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013728","input_cache_read":"0.000000001456","prompt":"0.00000004576"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~google/gemini-flash-latest\"]":{"classification":"paid","cost":{"completion":"0.00000375","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000375","prompt":"0.00000075","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~google/gemini-flash-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"google/gemini-3.8-flash","architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","expiration_date":null,"id":"~google/gemini-flash-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000375","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000375","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini Flash Latest","raw":{"alias_target":"google/gemini-3.8-flash","architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","expiration_date":null,"id":"~google/gemini-flash-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000375","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000375","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~google/gemini-pro-latest\"]":{"classification":"paid","cost":{"completion":"0.00001","image":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.00001","prompt":"0.000002","web_search":"0.014"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~google/gemini-pro-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"google/gemini-4-argon","architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","expiration_date":null,"id":"~google/gemini-pro-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","image":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.00001","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Google: Gemini Pro Latest","raw":{"alias_target":"google/gemini-4-argon","architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","expiration_date":null,"id":"~google/gemini-pro-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","image":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.00001","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~moonshotai/kimi-latest\"]":{"classification":"paid","cost":{"completion":"0.0000105539","input_cache_read":"0.00000018","prompt":"0.0000001824"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~moonshotai/kimi-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"moonshotai/kimi-k3","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","expiration_date":null,"id":"~moonshotai/kimi-latest","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000105539","input_cache_read":"0.00000018","prompt":"0.0000001824"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"MoonshotAI: Kimi Latest","raw":{"alias_target":"moonshotai/kimi-k3","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","expiration_date":null,"id":"~moonshotai/kimi-latest","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000105539","input_cache_read":"0.00000018","prompt":"0.0000001824"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~openai/gpt-astra-latest\"]":{"classification":"paid","cost":{"completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~openai/gpt-astra-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"openai/gpt-6-astra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","expiration_date":null,"id":"~openai/gpt-astra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Astra Latest ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Astra Latest ($$$$)","raw":{"alias_target":"openai/gpt-6-astra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","expiration_date":null,"id":"~openai/gpt-astra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Astra Latest ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~openai/gpt-luna-latest\"]":{"classification":"paid","cost":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~openai/gpt-luna-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"openai/gpt-6-luna","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","expiration_date":null,"id":"~openai/gpt-luna-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Luna Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Luna Latest","raw":{"alias_target":"openai/gpt-6-luna","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","expiration_date":null,"id":"~openai/gpt-luna-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Luna Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~openai/gpt-mini-latest\"]":{"classification":"paid","cost":{"completion":"0.0000045","input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~openai/gpt-mini-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"openai/gpt-5.4-mini","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":400000,"created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","expiration_date":null,"id":"~openai/gpt-mini-latest","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Mini Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Mini Latest","raw":{"alias_target":"openai/gpt-5.4-mini","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":400000,"created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","expiration_date":null,"id":"~openai/gpt-mini-latest","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Mini Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~openai/gpt-sol-latest\"]":{"classification":"paid","cost":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~openai/gpt-sol-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"openai/gpt-6.1-sol","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","expiration_date":null,"id":"~openai/gpt-sol-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Sol Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Sol Latest","raw":{"alias_target":"openai/gpt-6.1-sol","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","expiration_date":null,"id":"~openai/gpt-sol-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Sol Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~openai/gpt-terra-latest\"]":{"classification":"paid","cost":{"completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~openai/gpt-terra-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"openai/gpt-6.1-terra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","expiration_date":null,"id":"~openai/gpt-terra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Terra Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"OpenAI: GPT Terra Latest","raw":{"alias_target":"openai/gpt-6.1-terra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","expiration_date":null,"id":"~openai/gpt-terra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Terra Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~unbiased/pareto-latest\"]":{"classification":"paid","cost":{"completion":"0.0000032","input_cache_read":"0.00000003","prompt":"0.0000008"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~unbiased/pareto-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"unbiased/pareto-26.10","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","expiration_date":null,"id":"~unbiased/pareto-latest","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto Latest","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Pareto Latest","raw":{"alias_target":"unbiased/pareto-26.10","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","expiration_date":null,"id":"~unbiased/pareto-latest","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto Latest","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~x-ai/grok-latest\"]":{"classification":"paid","cost":{"completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~x-ai/grok-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"x-ai/grok-4.7","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":500000,"created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","expiration_date":null,"id":"~x-ai/grok-latest","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"xAI: Grok Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":true,"max_completion_tokens":450000}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"xAI: Grok Latest","raw":{"alias_target":"x-ai/grok-4.7","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":500000,"created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","expiration_date":null,"id":"~x-ai/grok-latest","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"xAI: Grok Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":true,"max_completion_tokens":450000}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~z-ai/glm-flash-latest\"]":{"classification":"paid","cost":{"completion":"0.0000000923","input_cache_read":"0.0000000285","prompt":"0.0000000285"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~z-ai/glm-flash-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"z-ai/glm-5.3-flash","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","expiration_date":null,"id":"~z-ai/glm-flash-latest","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000000923","input_cache_read":"0.0000000285","prompt":"0.0000000285"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM Flash Latest","raw":{"alias_target":"z-ai/glm-5.3-flash","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","expiration_date":null,"id":"~z-ai/glm-flash-latest","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000000923","input_cache_read":"0.0000000285","prompt":"0.0000000285"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"kilo\",\"~z-ai/glm-latest\"]":{"classification":"paid","cost":{"completion":"0.0000014","input_cache_read":"0.0000000689","prompt":"0.0000000699"},"evidence":"kilo","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"~z-ai/glm-latest","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"alias_target":"z-ai/glm-5.3","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","expiration_date":null,"id":"~z-ai/glm-latest","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","input_cache_read":"0.0000000689","prompt":"0.0000000699"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"kilo"},"metadataRetained":false,"name":"Z.ai: GLM Latest","raw":{"alias_target":"z-ai/glm-5.3","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","expiration_date":null,"id":"~z-ai/glm-latest","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","input_cache_read":"0.0000000689","prompt":"0.0000000699"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},"retirementDates":[],"service":"kilo","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":false},"[\"ovh\",\"Meta-Llama-3_3-70B-Instruct\"]":{"classification":"free","cost":{"completion":"0.00000074","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000074","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Meta-Llama-3_3-70B-Instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"context_length":131072,"created":1743520231,"id":"Meta-Llama-3_3-70B-Instruct","max_completion_tokens":131072,"name":"Meta-Llama-3_3-70B-Instruct","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Large Language Models (LLM)","category_v2":"Text Generation","created_at":"2025-04-01T15:10:31Z","description":"Llama 3.3 is an instruction-tuned generative language model optimized for multilingual dialogue use cases. It was released by Meta AI on December 6, 2024, and utilizes an advanced transformer architecture and is designed to align with human preferences for helpfulness and safety through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). The knowledge cutoff for this 70B model is December 31, 2023.\n","documentation_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Meta-Llama-3_3-70B-Instruct","id":"llama-3-3-70b-instruct","isNew":false,"licence_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["meta-llama/Llama-3.3-70B-Instruct","meta-llama-3_3-70b-instruct"],"api_base_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"Meta-Llama-3_3-70B-Instruct","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":48},{"benchmark_name":"default","benchmark_score":44.85}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":70,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Meta-Llama-3_3-70B-Instruct","publishing_information":{"endpoint_publication_date":"20/02/2025","knowledge_cutoff":"31/12/2023","languages":["*"],"licence_name":"Llama 3.3 Community","licence_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"06/12/2024","publisher":"meta-llama","series":"llama","source":"huggingface","source_link":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.67,"price_unit":"million_input_tokens"},{"price":0.67,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Meta-Llama-3_3-70B-Instruct","new":false,"openapi_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Meta-Llama-3_3-70B-Instruct/openapi.json","tags":[],"version":"v1.0"}},"owned_by":"meta-llama","pricing":{"completion":"0.00000074","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000074","request":"0"},"reasoning":false,"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Meta-Llama-3_3-70B-Instruct","raw":{"context_length":131072,"created":1743520231,"id":"Meta-Llama-3_3-70B-Instruct","max_completion_tokens":131072,"object":"model","owned_by":"meta-llama","pricing":{"completion":"0.00000074","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000074","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Mistral-Nemo-Instruct-2407\"]":{"classification":"unknown","cost":{"completion":"0.00000014","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000014","request":"0"},"evidence":"ovh","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":false,"id":"Mistral-Nemo-Instruct-2407","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"context_length":65536,"created":1732101359,"id":"Mistral-Nemo-Instruct-2407","max_completion_tokens":65536,"object":"model","owned_by":"mistralai","pricing":{"completion":"0.00000014","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000014","request":"0"}},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovh"},"metadataRetained":false,"name":"Mistral-Nemo-Instruct-2407","raw":{"context_length":65536,"created":1732101359,"id":"Mistral-Nemo-Instruct-2407","max_completion_tokens":65536,"object":"model","owned_by":"mistralai","pricing":{"completion":"0.00000014","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000014","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Mistral-Small-3.2-24B-Instruct-2506\"]":{"classification":"free","cost":{"completion":"0.00000031","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.0000001","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Mistral-Small-3.2-24B-Instruct-2506","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"retired","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":131072,"created":1752655627,"id":"Mistral-Small-3.2-24B-Instruct-2506","max_completion_tokens":131072,"name":"Mistral-Small-3.2-24B-Instruct-2506","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":false,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":false,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2025-07-16T08:47:07Z","description":"Building upon Mistral Small 3 (2501), Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.\nWith 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.\nThis model is a minor update of Mistral-Small-3.1-24B-Instruct-2503, which is an instruction-finetuned version of: Mistral-Small-3.1-24B-Base-2503.\n","documentation_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Mistral-Small-3.2-24B-Instruct-2506","id":"mistral-small-3-2-24b-instruct-2506","isNew":false,"licence_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["mistralai/Mistral-Small-3.2-24B-Instruct-2506","mistral-small-3.2-24b-instruct-2506"],"api_base_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"Wildbench v2","benchmark_score":65.33},{"benchmark_name":"Arena Hard v2","benchmark_score":43.1},{"benchmark_name":"IF (Internal; accuracy)","benchmark_score":84.78},{"benchmark_name":"Infinite Generations (Internal; Lower is better)","benchmark_score":1.29},{"benchmark_name":"MMLU","benchmark_score":80.5},{"benchmark_name":"MMLU Pro (5-shot CoT)","benchmark_score":69.06},{"benchmark_name":"MATH","benchmark_score":69.42},{"benchmark_name":"GPQA Main (5-shot CoT)","benchmark_score":44.22},{"benchmark_name":"GPQA Diamond (5-shot CoT )","benchmark_score":46.13},{"benchmark_name":"MBPP Plus - Pass@5","benchmark_score":78.33},{"benchmark_name":"HumanEval Plus - Pass@5","benchmark_score":92.9},{"benchmark_name":"SimpleQA (TotalAcc)","benchmark_score":12.1},{"benchmark_name":"MMMU","benchmark_score":62.5},{"benchmark_name":"Mathvista","benchmark_score":67.09},{"benchmark_name":"ChartQA","benchmark_score":87.4},{"benchmark_name":"DocVQA","benchmark_score":94.86},{"benchmark_name":"AI2D","benchmark_score":92.91}],"context":"128k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","vision"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":128,"max_images_per_prompt":10,"max_output_token_k":128,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":24,"quantization":"bf16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Mistral-Small-3.2-24B-Instruct-2506","publishing_information":{"endpoint_publication_date":"30/06/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"04/11/2026","model_publication_date":"20/06/2025","publisher":"mistralai","series":"mistral","source":"huggingface","source_link":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.09,"price_unit":"million_input_tokens"},{"price":0.28,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Mistral-Small-3.2-24B-Instruct-2506","new":false,"openapi_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Mistral-Small-3.2-24B-Instruct-2506/openapi.json","tags":["Vision"],"version":"v3.1"}},"owned_by":"mistralai","pricing":{"completion":"0.00000031","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.0000001","request":"0"},"reasoning":false,"retirement_date":"2026-11-04","status":"deprecated","tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Mistral-Small-3.2-24B-Instruct-2506","raw":{"context_length":131072,"created":1752655627,"id":"Mistral-Small-3.2-24B-Instruct-2506","max_completion_tokens":131072,"object":"model","owned_by":"mistralai","pricing":{"completion":"0.00000031","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.0000001","request":"0"}},"retirementDates":["2026-11-04"],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen2.5-VL-72B-Instruct\"]":{"classification":"free","cost":{"completion":"0.00000101","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000101","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen2.5-VL-72B-Instruct","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":32768,"created":1743423983,"id":"Qwen2.5-VL-72B-Instruct","max_completion_tokens":32768,"name":"Qwen2.5-VL-72B-Instruct","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2025-03-31T12:26:23Z","description":"Qwen2.5-VL is a powerful vision-language model, designed for advanced image understanding. It can generate detailed image captions, analyze documents, OCR, detect objects, and answer questions based on visuals, making it useful for AI assistants, RAG and Agents.","documentation_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen2.5-VL-72B-Instruct","id":"qwen-2-5-vl-72b-instruct","isNew":false,"licence_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen2.5-VL-72B-Instruct","qwen2.5-vl-72b-instruct"],"api_base_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"AVG OpenVLM","benchmark_score":76.1},{"benchmark_name":"default","benchmark_score":76.1}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text","image"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["multimodal","vision","text_only_compatible"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":32,"max_images_per_prompt":5,"max_output_token_k":32,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":72,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen2.5-VL-72B-Instruct","publishing_information":{"endpoint_publication_date":"26/03/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Qwen","licence_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"27/01/2025","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.91,"price_unit":"million_input_tokens"},{"price":0.91,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Qwen2.5-VL-72B-Instruct","new":false,"openapi_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen2.5-VL-72B-Instruct/openapi.json","tags":["Vision"],"version":"v2.5"}},"owned_by":"Qwen","pricing":{"completion":"0.00000101","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000101","request":"0"},"reasoning":false,"tool_call":false,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen2.5-VL-72B-Instruct","raw":{"context_length":32768,"created":1743423983,"id":"Qwen2.5-VL-72B-Instruct","max_completion_tokens":32768,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000101","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000101","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3-Embedding-8B\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3-Embedding-8B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["embedding_vector"]},"context_length":32768,"created":1774533326,"id":"Qwen3-Embedding-8B","max_completion_tokens":0,"name":"Qwen3-Embedding-8B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Embeddings","category_v2":"Embeddings","created_at":"2026-03-26T13:55:26Z","description":"State-of-the-art text embedding model with 100+ language support and customizable dimensional outputs. Perfect for retrieval, classification, and multilingual applications. The flexible output dimensionality lets you optimize for your specific use case, whether you need compact vectors for fast retrieval or high dimensional representations for complex semantic tasks.\n","documentation_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3-Embedding-8B","id":"qwen3-embedding-8b","isNew":true,"licence_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/qwen3_embedding_8b"],"api_base_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_multilingual_mean_task","benchmark_score":70.58},{"benchmark_name":"mteb_multilingual_mean_task_type","benchmark_score":61.69},{"benchmark_name":"mteb_multilingual_bitext_mining","benchmark_score":80.89},{"benchmark_name":"mteb_multilingual_classification","benchmark_score":74},{"benchmark_name":"mteb_multilingual_clustering","benchmark_score":57.65},{"benchmark_name":"mteb_multilingual_instruction_reranking","benchmark_score":10.06},{"benchmark_name":"mteb_multilingual_multilabel_classification","benchmark_score":28.66},{"benchmark_name":"mteb_multilingual_pair_classification","benchmark_score":86.4},{"benchmark_name":"mteb_multilingual_reranking","benchmark_score":65.63},{"benchmark_name":"mteb_multilingual_retrieval","benchmark_score":70.88},{"benchmark_name":"mteb_multilingual_sts","benchmark_score":81.08}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"supported_sampling_parameters":[],"use_case_tag":["multilingual"],"web_search":false},"model_parameters":{"parameters_type":"embedding","params":{"context_size":32768,"max_batch_size":25,"output_dimension":4096,"output_dimension_max":4096,"output_dimension_min":32}},"nb_of_billion_parameters":7.6,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3-Embedding-8B","publishing_information":{"endpoint_publication_date":"26/03/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"06/06/2025","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/qwen3_embedding_8b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":[""],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.1,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3-Embedding-8B","new":true,"openapi_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3-Embedding-8B/openapi.json","tags":[],"version":"v1.0"}},"owned_by":"Qwen","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"},"reasoning":false,"tool_call":false,"type":"embedding"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3-Embedding-8B","raw":{"context_length":32768,"created":1774533326,"id":"Qwen3-Embedding-8B","max_completion_tokens":0,"object":"model","owned_by":"Qwen","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"}},"retirementDates":[],"service":"ovh","type":"embedding","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3.5-397B-A17B\"]":{"classification":"free","cost":{"completion":"0.00000425","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000071","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3.5-397B-A17B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":262144,"created":1779113482,"id":"Qwen3.5-397B-A17B","max_completion_tokens":262144,"name":"Qwen3.5-397B-A17B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-05-18T14:11:22Z","description":"Qwen3.5-397B-A17B is a highly efficient, reasoning focused MoE (Mixture of Experts) model delivering state-of-the-art performance in language, vision, and multimodal tasks, with strong capabilities in code, reasoning, and real-world adaptability.\n","documentation_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-397B-A17B","id":"qwen-3-5-397b","isNew":true,"licence_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.5-397B-A17B","qwen3.5-397b-a17b","qwen3.5-397b"],"api_base_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":87.8},{"benchmark_name":"IFEval","benchmark_score":92.6},{"benchmark_name":"LiveCodeBench-v6","benchmark_score":83.6},{"benchmark_name":"BFCL-V4","benchmark_score":72.9},{"benchmark_name":"SWE-bench-Verified","benchmark_score":76.4},{"benchmark_name":"MMMU-Pro","benchmark_score":79},{"benchmark_name":"OmniDocBench1.5","benchmark_score":90.8},{"benchmark_name":"OCRBench","benchmark_score":93.1}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["emotion_detection","entity_extraction","multi_language_coding","vision","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":397,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-397B-A17B","publishing_information":{"endpoint_publication_date":"15/05/2026","knowledge_cutoff":"31/09/2025","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/02/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.6,"price_unit":"million_input_tokens"},{"price":3.6,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.5-397B-A17B","new":true,"openapi_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.5-397B-A17B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.5"}},"owned_by":"Qwen","pricing":{"completion":"0.00000425","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000071","request":"0"},"reasoning":true,"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3.5-397B-A17B","raw":{"context_length":262144,"created":1779113482,"id":"Qwen3.5-397B-A17B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000425","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000071","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3.5-9B\"]":{"classification":"free","cost":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3.5-9B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":262144,"created":1776853448,"id":"Qwen3.5-9B","max_completion_tokens":262144,"name":"Qwen3.5-9B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-04-22T10:24:08Z","description":"Qwen3.5 9B is a highly efficient, reasoning focused model delivering state of the art performance in language, vision, and multimodal tasks, with strong capabilities in code, reasoning, and real-world adaptability.\n","documentation_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-9B","id":"qwen-3-5-9b","isNew":true,"licence_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.5-9B","qwen3.5-9b"],"api_base_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":69}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":9.7,"quantization":"bf16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-9B","publishing_information":{"endpoint_publication_date":"15/04/2026","knowledge_cutoff":"31/09/2025","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/02/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.5-9B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.1,"price_unit":"million_input_tokens"},{"price":0.15,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.5-9B","new":true,"openapi_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.5-9B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.5"}},"owned_by":"Qwen","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"},"reasoning":true,"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3.5-9B","raw":{"context_length":262144,"created":1776853448,"id":"Qwen3.5-9B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3.6-27B\"]":{"classification":"free","cost":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3.6-27B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":262144,"created":1780302734,"id":"Qwen3.6-27B","max_completion_tokens":262144,"name":"Qwen3.6-27B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-06-01T08:32:14Z","description":"Qwen3.6-27B is a 27-billion-parameter multimodal causal language model developed by Alibaba's Qwen team, released as an open-weight variant following the February release of the Qwen3.5 series. It is built as an Image-Text-to-Text model.\n","documentation_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.6-27B","id":"qwen-3-6-27b","isNew":true,"licence_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.6-27B","qwen3.6-27b"],"api_base_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":85.2}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":27,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.6-27B","publishing_information":{"endpoint_publication_date":"06/05/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/04/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.6-27B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.4,"price_unit":"million_input_tokens"},{"price":2.7,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.6-27B","new":true,"openapi_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.6-27B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.6"}},"owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"},"reasoning":true,"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3.6-27B","raw":{"context_length":262144,"created":1780302734,"id":"Qwen3.6-27B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3.8-27B\"]":{"classification":"free","cost":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3.8-27B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"context_length":262144,"created":1788356485,"id":"Qwen3.8-27B","max_completion_tokens":262144,"name":"Qwen3.8-27B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-09-02T13:41:25Z","description":"Qwen3.8-27B is a 27-billion-parameter multimodal causal language model developed by Alibaba's Qwen team. It is the most capable generation in the Qwen open-model family, built as a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step agentic tasks through to completion with greater reliability.\n","documentation_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.8-27B","id":"qwen-3-8-27b","isNew":true,"licence_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.8-27B","qwen3.8-27b"],"api_base_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"SWE-bench Pro","benchmark_score":61.7},{"benchmark_name":"LiveCodeBench v6","benchmark_score":90.3},{"benchmark_name":"GPQA Diamond","benchmark_score":89.2},{"benchmark_name":"OSWorld-Verified","benchmark_score":84.3}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["none","low","medium","xhigh"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":27,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.8-27B","publishing_information":{"endpoint_publication_date":"24/08/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/08/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.8-27B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.4,"price_unit":"million_input_tokens"},{"price":2.7,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.8-27B","new":true,"openapi_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.8-27B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.8"}},"owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"},"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3.8-27B","raw":{"context_length":262144,"created":1788356485,"id":"Qwen3.8-27B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3Guard-Gen-0.6B\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3Guard-Gen-0.6B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"context_length":32768,"created":1769078772,"id":"Qwen3Guard-Gen-0.6B","max_completion_tokens":16384,"name":"Qwen3Guard-Gen-0.6B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"LLM Guard","category_v2":"Safety & Moderation","created_at":"2026-01-22T10:46:12Z","description":"Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classification head for real-time safety monitoring during incremental text generation.\n","documentation_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-0.6B","id":"qwen-guard-gen-06b","isNew":false,"licence_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3Guard-Gen-0.6B"],"api_base_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"WildGuardTest","benchmark_score":89.4}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["moderation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":32,"max_output_token_k":16}},"nb_of_billion_parameters":0.6,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-0.6B","publishing_information":{"endpoint_publication_date":"21/01/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"23/09/2025","publisher":"qwen3guard","series":"qwen3guard","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Moderation","Streaming"],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_tokens"},{"price":0,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["beta"]}},"name":"Qwen3Guard-Gen-0.6B","new":false,"openapi_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3Guard-Gen-0.6B/openapi.json","tags":["Moderation"],"version":"v3.1"}},"owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3Guard-Gen-0.6B","raw":{"context_length":32768,"created":1769078772,"id":"Qwen3Guard-Gen-0.6B","max_completion_tokens":16384,"object":"model","owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"Qwen3Guard-Gen-8B\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"Qwen3Guard-Gen-8B","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"context_length":32768,"created":1769078773,"id":"Qwen3Guard-Gen-8B","max_completion_tokens":16384,"name":"Qwen3Guard-Gen-8B","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"LLM Guard","category_v2":"Safety & Moderation","created_at":"2026-01-22T10:46:13Z","description":"Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classification head for real-time safety monitoring during incremental text generation.\n","documentation_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-8B","id":"qwen-guard-gen-8b","isNew":false,"licence_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3Guard-Gen-8B"],"api_base_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"WildGuardTest","benchmark_score":89.4}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["moderation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":32,"max_output_token_k":16}},"nb_of_billion_parameters":8,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-8B","publishing_information":{"endpoint_publication_date":"21/01/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"23/09/2025","publisher":"qwen3guard","series":"qwen3guard","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Moderation","Streaming"],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_tokens"},{"price":0,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["beta"]}},"name":"Qwen3Guard-Gen-8B","new":false,"openapi_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3Guard-Gen-8B/openapi.json","tags":["Moderation"],"version":"v3.1"}},"owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"Qwen3Guard-Gen-8B","raw":{"context_length":32768,"created":1769078773,"id":"Qwen3Guard-Gen-8B","max_completion_tokens":16384,"object":"model","owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"bge-m3\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bge-m3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["embedding_vector"]},"context_length":8192,"created":1731944050,"id":"bge-m3","max_completion_tokens":0,"name":"bge-m3","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Embeddings","category_v2":"Embeddings","created_at":"2024-11-18T15:34:10Z","description":"The BGE-M3 model, developed by the BAAI and released in early 2024, is a powerful multilingual and multigranular embedding model. It supports texts of varying lengths across over 100 languages and produces dense embeddings optimized for semantic search and retrieval applications.\n","documentation_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/bge-m3","id":"bge-m3","isNew":false,"licence_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["BAAI/bge-m3","BGE-M3"],"api_base_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_mean_ask","benchmark_score":59.54},{"benchmark_name":"default","benchmark_score":59.54}],"context_size":8192,"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["multilingual"]},"model_parameters":{"parameters_type":"embedding","params":{"context_size":8192,"max_batch_size":25,"output_dimension":1024}},"nb_of_billion_parameters":0.567,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/bge-m3","publishing_information":{"endpoint_publication_date":"07/11/2024","knowledge_cutoff":"None","languages":["en"],"licence_name":"MIT","licence_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"27/01/2024","publisher":"BAAI","series":"bge","source":"huggingface","source_link":"https://huggingface.co/BAAI/bge-m3"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":[""],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.01,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"bge-m3","new":false,"openapi_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/bge-m3/openapi.json","tags":[],"version":"v1.0"}},"owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"},"reasoning":false,"tool_call":false,"type":"embedding"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"bge-m3","raw":{"context_length":8192,"created":1731944050,"id":"bge-m3","max_completion_tokens":0,"object":"model","owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"}},"retirementDates":[],"service":"ovh","type":"embedding","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"bge-multilingual-gemma2\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"bge-multilingual-gemma2","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"deprecated","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["embedding_vector"]},"context_length":8192,"created":1742826442,"id":"bge-multilingual-gemma2","max_completion_tokens":0,"name":"bge-multilingual-gemma2","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":false,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":false,"category":"Embeddings","category_v2":"Embeddings","created_at":"2025-03-24T14:27:22Z","description":"BGE-Multilingual-Gemma2 is a LLM-based multilingual embedding model. It is trained on a diverse range of languages and tasks. BGE-Multilingual-Gemma2 primarily demonstrates the following advancements:\nDiverse training data: The model's training data spans a broad range of languages, including English, Chinese, Japanese, Korean, French, and more.Additionally, the data covers a variety of task types, such as retrieval, classification, and clustering.\nOutstanding performance: The model exhibits state-of-the-art (SOTA) results on multilingual benchmarks like MIRACL, MTEB-pl, and MTEB-fr. It also achieves excellent performance on other major evaluations, including MTEB, C-MTEB and AIR-Bench.\n","documentation_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/bge-multilingual-gemma2","id":"bge-multilingual-gemma2","isNew":false,"licence_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["BAAI/bge-multilingual-gemma2"],"api_base_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_mean_ask","benchmark_score":59.54},{"benchmark_name":"default","benchmark_score":59.54}],"context_size":8192,"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["multilingual"]},"model_parameters":{"parameters_type":"embedding","params":{"context_size":8192,"max_batch_size":25,"output_dimension":3584}},"nb_of_billion_parameters":0.567,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/bge-multilingual-gemma2","publishing_information":{"endpoint_publication_date":"24/03/2025","knowledge_cutoff":"None","languages":["en"],"licence_name":"Gemma","licence_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"21/01/2027","model_publication_date":"29/06/2024","publisher":"BAAI","series":"bge","source":"huggingface","source_link":"https://huggingface.co/BAAI/bge-multilingual-gemma2"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.01,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"bge-multilingual-gemma2","new":false,"openapi_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/bge-multilingual-gemma2/openapi.json","tags":[],"version":"v1.0"}},"owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"},"reasoning":false,"retirement_date":"2027-01-21","status":"deprecated","tool_call":false,"type":"embedding"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"bge-multilingual-gemma2","raw":{"context_length":8192,"created":1742826442,"id":"bge-multilingual-gemma2","max_completion_tokens":0,"object":"model","owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"}},"retirementDates":["2027-01-21"],"service":"ovh","type":"embedding","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"gpt-oss-120b\"]":{"classification":"free","cost":{"completion":"0.00000047","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000009","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"gpt-oss-120b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"context_length":131072,"created":1756386145,"id":"gpt-oss-120b","max_completion_tokens":131072,"name":"gpt-oss-120b","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Reasoning LLM","category_v2":"Text Generation","created_at":"2025-08-28T13:02:25Z","description":"gpt-oss-120b is a cutting-edge model designed for high-level reasoning, instruction-following, and advanced agent capabilities. It excels in versatile use cases, offering powerful performance for both general-purpose and specialized applications.\n","documentation_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-120b","id":"gpt-oss-120b","isNew":false,"licence_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/gpt-oss-120b"],"api_base_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":80.8},{"benchmark_name":"LiveCodeBench","benchmark_score":63.9}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["low","medium","high"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"]},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":117,"quantization":"fp4"},"playground_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-120b","publishing_information":{"endpoint_publication_date":"12/08/2025","knowledge_cutoff":"31/06/2024","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"05/08/2025","publisher":"OpenAI","series":"gpt-oss","source":"huggingface","source_link":"https://huggingface.co/openai/gpt-oss-120b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.08,"price_unit":"million_input_tokens"},{"price":0.4,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"gpt-oss-120b","new":false,"openapi_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/gpt-oss-120b/openapi.json","tags":["Reasoning"],"version":"v1"}},"owned_by":"OpenAI","pricing":{"completion":"0.00000047","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000009","request":"0"},"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"gpt-oss-120b","raw":{"context_length":131072,"created":1756386145,"id":"gpt-oss-120b","max_completion_tokens":131072,"object":"model","owned_by":"OpenAI","pricing":{"completion":"0.00000047","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000009","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"gpt-oss-20b\"]":{"classification":"free","cost":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000005","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"gpt-oss-20b","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"context_length":131072,"created":1756386145,"id":"gpt-oss-20b","max_completion_tokens":131072,"name":"gpt-oss-20b","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Reasoning LLM","category_v2":"Text Generation","created_at":"2025-08-28T13:02:25Z","description":"gpt-oss-20b delivers strong performance with fast inference and efficient reasoning. Ideal for a wide range of tasks, it offers flexible deployment for developers seeking powerful, customizable AI solutions.\n","documentation_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-20b","id":"gpt-oss-20b","isNew":false,"licence_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/gpt-oss-20b"],"api_base_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":73.6},{"benchmark_name":"LiveCodeBench","benchmark_score":72.1}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["low","medium","high"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"]},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":21,"quantization":"fp4"},"playground_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-20b","publishing_information":{"endpoint_publication_date":"12/08/2025","knowledge_cutoff":"31/06/2024","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"05/08/2025","publisher":"OpenAI","series":"gpt-oss","source":"huggingface","source_link":"https://huggingface.co/openai/gpt-oss-20b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.04,"price_unit":"million_input_tokens"},{"price":0.15,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"gpt-oss-20b","new":false,"openapi_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/gpt-oss-20b/openapi.json","tags":["Reasoning"],"version":"v1"}},"owned_by":"OpenAI","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000005","request":"0"},"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"type":"chat"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"gpt-oss-20b","raw":{"context_length":131072,"created":1756386145,"id":"gpt-oss-20b","max_completion_tokens":131072,"object":"model","owned_by":"OpenAI","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000005","request":"0"}},"retirementDates":[],"service":"ovh","type":"chat","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"nvr-tts-de-de\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvr-tts-de-de","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["sound"]},"context_length":0,"created":1729515876,"id":"nvr-tts-de-de","max_completion_tokens":0,"name":"nvr-tts-de-de","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding German speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-de-de","id":"nvr-tts-de-de","isNew":false,"licence_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["de-de"],"output_languages":["de-de"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-de-de","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["de-de"],"licence_name":"Riva license","licence_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-de-de","new":false,"openapi_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"}},"owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"nvr-tts-de-de","raw":{"context_length":0,"created":1729515876,"id":"nvr-tts-de-de","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"nvr-tts-en-us\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvr-tts-en-us","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["sound"]},"context_length":0,"created":1729515876,"id":"nvr-tts-en-us","max_completion_tokens":0,"name":"nvr-tts-en-us","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding American English speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-en-us","id":"nvr-tts-en-us","isNew":false,"licence_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["en-us"],"output_languages":["en-us"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-en-us","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["en-us"],"licence_name":"Riva license","licence_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-en-us","new":false,"openapi_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"}},"owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"nvr-tts-en-us","raw":{"context_length":0,"created":1729515876,"id":"nvr-tts-en-us","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"nvr-tts-es-es\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvr-tts-es-es","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["sound"]},"context_length":0,"created":1729515876,"id":"nvr-tts-es-es","max_completion_tokens":0,"name":"nvr-tts-es-es","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding European Spanish speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-es-es","id":"nvr-tts-es-es","isNew":false,"licence_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["es-es"],"output_languages":["es-es"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-es-es","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["es-es"],"licence_name":"Riva license","licence_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-es-es","new":false,"openapi_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"}},"owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"nvr-tts-es-es","raw":{"context_length":0,"created":1729515876,"id":"nvr-tts-es-es","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"nvr-tts-it-it\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"nvr-tts-it-it","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["sound"]},"context_length":0,"created":1729515876,"id":"nvr-tts-it-it","max_completion_tokens":0,"name":"nvr-tts-it-it","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding Italian speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-it-it","id":"nvr-tts-it-it","isNew":false,"licence_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["it-it"],"output_languages":["it-it"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-it-it","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["it-it"],"licence_name":"Riva license","licence_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-it-it","new":false,"openapi_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"}},"owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"nvr-tts-it-it","raw":{"context_length":0,"created":1729515876,"id":"nvr-tts-it-it","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"stable-diffusion-xl-base-v10\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"stable-diffusion-xl-base-v10","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["text"],"output_modalities":["image"]},"context_length":0,"created":1730297598,"id":"stable-diffusion-xl-base-v10","max_completion_tokens":0,"name":"stable-diffusion-xl-base-v10","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Image Generation","category_v2":"Image Generation","created_at":"2024-10-30T14:13:18Z","description":"SDXL, developed by Stability AI, is an advanced text-to-image model released in July 2023, offering enhanced image generation capabilities.\n","documentation_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/stable-diffusion-xl-base-v10","id":"stable-diffusion-xl","isNew":false,"licence_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["stabilityai/stable-diffusion-xl-base-1.0"],"api_base_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"Arena-elo","benchmark_score":886},{"benchmark_name":"default","benchmark_score":886}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["image"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["image_generation"]},"model_parameters":{"parameters_type":"image_generation","params":[]},"nb_of_billion_parameters":3.5,"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/stable-diffusion-xl-base-v10","publishing_information":{"endpoint_publication_date":"24/10/2024","knowledge_cutoff":"None","languages":["*"],"licence_name":"OpenRail++","licence_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"25/07/2023","publisher":"stabilityai","series":"stable-diffusion","source":"huggingface","source_link":"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Image Generation"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"per_image"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"stable-diffusion-xl-base-v10","new":false,"openapi_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/stable-diffusion-xl-base-v10/openapi.json","tags":["Image Generation"],"version":"v1.0"}},"owned_by":"stabilityai","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"image"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"stable-diffusion-xl-base-v10","raw":{"context_length":0,"created":1730297598,"id":"stable-diffusion-xl-base-v10","max_completion_tokens":0,"object":"model","owned_by":"stabilityai","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"image","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"whisper-large-v3\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"whisper-large-v3","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["sound"],"output_modalities":["text"]},"context_length":0,"created":1754992184,"id":"whisper-large-v3","max_completion_tokens":0,"name":"whisper-large-v3","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Speech To Text","category_v2":"Speech To Text","created_at":"2025-08-12T09:49:44Z","description":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper \"Robust Speech Recognition via Large-Scale Weak Supervision\" by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.\n","documentation_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3","id":"whisper-large-v3","isNew":false,"licence_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/whisper-large-v3"],"api_base_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"whisper-large-v3","benchmark_results":[{"benchmark_name":"Average WER","benchmark_score":7.44},{"benchmark_name":"AMI","benchmark_score":15.95},{"benchmark_name":"Earnings22","benchmark_score":11.29},{"benchmark_name":"Gigaspeech","benchmark_score":10.02},{"benchmark_name":"LS Clean","benchmark_score":2.01},{"benchmark_name":"LS Other","benchmark_score":3.91},{"benchmark_name":"SPGISpeech","benchmark_score":2.94}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["sound"],"output_modality":["text"],"reasoning":false,"response_format":["json","verbose_json","text"],"streaming":false,"use_case_tag":["speech_to_text","diarisation","translation"]},"model_parameters":{"parameters_type":"asr","params":{"input_languages":["*"],"max_audio_duration":10800,"max_audio_duration_unauthenticated":60,"max_audio_size":2048,"max_audio_size_unauthenticated":10,"output_languages":["*"],"supported_formats":["mp3","mp4","aac","m4a","wav","flac","ogg","opus","webm","mpeg","mpga"]}},"nb_of_billion_parameters":1.54,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3","publishing_information":{"endpoint_publication_date":"15/07/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/11/2023","publisher":"OpenAi","series":"Whisper","source":"huggingface","source_link":"https://huggingface.co/openai/whisper-large-v3"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.00004083,"price_unit":"audio_duration_seconds"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"whisper-large-v3","new":false,"openapi_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/whisper-large-v3/openapi.json","tags":["Automatic Speech Recognition","Diarisation","Translation"],"version":"v1.0"}},"owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"whisper-large-v3","raw":{"context_length":0,"created":1754992184,"id":"whisper-large-v3","max_completion_tokens":0,"object":"model","owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true},"[\"ovh\",\"whisper-large-v3-turbo\"]":{"classification":"free","cost":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"evidence":"ovhmeta","evidenceSources":[],"firstSeen":"2026-10-22T16:14:08.423Z","fresh":true,"id":"whisper-large-v3-turbo","lastListed":"2026-11-04T21:29:27.556Z","lifecycle":"active","listed":true,"listingOrigin":"recorded-listed","metadata":{"architecture":{"input_modalities":["sound"],"output_modalities":["text"]},"context_length":0,"created":1754992184,"id":"whisper-large-v3-turbo","max_completion_tokens":0,"name":"whisper-large-v3-turbo","object":"model","ovh":{"anonymousRateLimit":2,"catalogAvailable":true,"policy":"https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started","richRecord":{"available":true,"category":"Speech To Text","category_v2":"Speech To Text","created_at":"2025-08-12T09:49:44Z","description":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper \"Robust Speech Recognition via Large-Scale Weak Supervision\" by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.\nWhisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.\n","documentation_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3-turbo","id":"whisper-large-v3-turbo","isNew":false,"licence_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/whisper-large-v3-turbo"],"api_base_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"whisper-large-v3-turbo","benchmark_results":[{"benchmark_name":"Average WER","benchmark_score":7.83},{"benchmark_name":"AMI","benchmark_score":16.13},{"benchmark_name":"Earnings22","benchmark_score":11.63},{"benchmark_name":"Gigaspeech","benchmark_score":10.14},{"benchmark_name":"LS Clean","benchmark_score":2.1},{"benchmark_name":"LS Other","benchmark_score":4.24},{"benchmark_name":"SPGISpeech","benchmark_score":2.97}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["sound"],"output_modality":["text"],"reasoning":false,"response_format":["json","verbose_json","text"],"streaming":false,"use_case_tag":["speech_to_text"]},"model_parameters":{"parameters_type":"asr","params":{"input_languages":["*"],"max_audio_duration":10800,"max_audio_duration_unauthenticated":60,"max_audio_size":2048,"max_audio_size_unauthenticated":10,"output_languages":["*"],"supported_formats":["mp3","mp4","aac","m4a","wav","flac","ogg","opus","webm","mpeg","mpga"]}},"nb_of_billion_parameters":0.81,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3-turbo","publishing_information":{"endpoint_publication_date":"15/07/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/09/2024","publisher":"OpenAi","series":"Whisper","source":"huggingface","source_link":"https://huggingface.co/openai/whisper-large-v3-turbo"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.00001278,"price_unit":"audio_duration_seconds"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"whisper-large-v3-turbo","new":false,"openapi_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/whisper-large-v3-turbo/openapi.json","tags":["Automatic Speech Recognition","Diarisation","Translation"],"version":"v1.0"}},"owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"},"reasoning":false,"tool_call":false,"type":"other"},"metadataProvenance":{"fetchedAt":"2026-11-04T21:29:27.556Z","source":"ovhmeta"},"metadataRetained":false,"name":"whisper-large-v3-turbo","raw":{"context_length":0,"created":1754992184,"id":"whisper-large-v3-turbo","max_completion_tokens":0,"object":"model","owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},"retirementDates":[],"service":"ovh","type":"other","updatedAt":"2026-11-04T21:29:27.556Z","wasFree":true}},"history":[{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"kilo-auto/efficient","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"kilo-auto/free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-super-vl:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"reflection/beam-free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/glyph-cluster","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-5.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6.1-sol","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4.1-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.3-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"recursive/flint-v1.0:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m3.1-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4.1-flash-1017","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"elorian/glimpse","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xingchen-agi/xing4.0-29b-a4b:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"reflection/beam-1.0-501b-a23b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inception/mercury-3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moondream/moondream3-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moondream/moondream3.1-9b-a2b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-open","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-super-vl","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"unbiased/pareto-26.10","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~unbiased/pareto-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"unbiased/pareto-26.9","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"liquid/lfm-2.5-24b-a2b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-4-argon","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"scaledown/summarize","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"scaledown/extract","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-wonder","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stepfun/step-5-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-haiku-5.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-nano-banana-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-large-4-0","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inclusionai/ling-3.1-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6.1-sol-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-sonnet-5.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"typesafe/jev-router","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perceptron/perceptron-mk1.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"fireworks/ember-1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.3-prime","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-max-prime","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-3.5-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-3.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"upstage/solar-mini4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/command-a-plus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-luna-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-luna","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-sol-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-sol","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/switchyard","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xiaomi/mimo-v2.6-pro-ultraspeed","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xiaomi/mimo-v2.6-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xiaomi/mimo-v2.6-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.7","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-omni-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"prism-ml/ternary-bonsai-2-27b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.3-flashx","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~deepseek/deepseek-pro-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~deepseek/deepseek-flash-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inference-net/schematron-v2-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inference-net/schematron-v2-small","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~openai/gpt-astra-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~openai/gpt-sol-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~openai/gpt-terra-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~openai/gpt-luna-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sakana/fugu-ultra-v2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sakana/fugu-max","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inclusionai/ling-3.0-flash-vl","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inception/mercury-2.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nex-agi/nex-n2.5-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nex-agi/nex-n2.5-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-astra","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-6-astra-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-max-0902","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-1.3-contributor","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-1.3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.8-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-fable-5.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"ibm-granite/granite-4.2-8b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy4-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~z-ai/glm-flash-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-1.2-contributor","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4-flash-vision-exp","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy-mt2-1.8b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy-mt2-30b-a3b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~z-ai/glm-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy-mt2-7b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-27b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"dots-studio/dots-3-note-preview:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.7-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-2-1-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.8-2.4t-a95b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-2.0-code","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4-pro-0813","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"liquid/lfm-2.5-2.6b:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-lightning","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-lightning:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sakana/sakana-namazu","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"upstage/solar-pro4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-glimmer-30b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-1.2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~deepseek/deepseek-v4-flash-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4-flash-0731","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"thinkingmachines/inkling-small","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.7-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inclusionai/ling-3.0-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"poolside/laguna-s-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"poolside/laguna-s-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.6-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.5-flash-lite","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meituan/longcat-2.0","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"thinkingmachines/inkling","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/auto-beta","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta/muse-spark-1.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-luna-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-luna","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-terra-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-terra","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-sol-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.6-sol","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~x-ai/grok-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-3.0-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-3.0","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"poolside/laguna-xs-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"poolside/laguna-xs-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-sonnet-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-flash-lite-image","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sakana/fugu-ultra","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-flash-image","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3-pro-image","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/north-mini-code:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/fusion","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2.7-code","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~anthropic/claude-fable-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-fable-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-content-safety","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3.5-content-safety:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.7-plus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stepfun/step-3.7-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-4.8","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.7-max","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-build-0.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.5-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perceptron/perceptron-mk1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-flash-lite","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-chat-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-medium-3-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~anthropic/claude-haiku-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~openai/gpt-mini-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~google/gemini-pro-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~moonshotai/kimi-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~google/gemini-flash-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~anthropic/claude-sonnet-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-plus-20260420","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.6-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.6-35b-a3b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.6-27b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.5-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v4-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hy3-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xiaomi/mimo-v2.5-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"xiaomi/mimo-v2.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.4-image-2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"~anthropic/claude-opus-latest","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/pareto-code","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-4.7","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-4-26b-a4b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-4-31b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.6-plus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5v-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"arcee-ai/trinity-large-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.20-multi-agent","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"x-ai/grok-4.20","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/lyria-3-pro-preview","service":"kilo","to":{"classification":"conflict","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/lyria-3-clip-preview","service":"kilo","to":{"classification":"conflict","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"rekaai/reka-edge","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m2.7","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.4-nano","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.4-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-small-2603","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-super-120b-a12b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-super-120b-a12b:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-2.0-lite","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-9b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.4-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"inception/mercury-2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-flash-lite-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-2.0-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-flash-image-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-35b-a3b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-27b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-122b-a10b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-flash-02-23","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-pro-preview-customtools","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.3-codex","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-2.0","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3.1-pro-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-sonnet-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-plus-02-15","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3.5-397b-a17b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m2.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-coder-next","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stepfun/step-3.5-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"upstage/solar-pro-3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m2-her","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"writer/palmyra-x5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-audio","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-audio-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.7-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.2-codex","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-1.6-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance-seed/seed-1.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m2.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.7","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3-flash-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvidia/nemotron-3-nano-30b-a3b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.2-chat","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.2-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/devstral-2512","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"relace/relace-search","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.6v","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/bodybuilder","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.1-codex-max","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"amazon/nova-2-lite-v1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/ministral-14b-2512","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/ministral-8b-2512","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/ministral-3b-2512","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-large-2512","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v3.2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-4.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-3-pro-image-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.1-codex","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5.1-codex-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"amazon/nova-premier-v1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perplexity/sonar-pro-search","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/voxtral-small-24b-2507","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-oss-safeguard-20b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"ibm-granite/granite-4.0-h-micro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5-image-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-haiku-4.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-vl-8b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5-image","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-2.5-flash-image","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-sonnet-4.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v3.2-exp","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"thedrummer/cydonia-24b-v4.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"relace/relace-apply-3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-v3.1-terminus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-coder-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-next-80b-a3b-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-next-80b-a3b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2-0905","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nousresearch/hermes-4-405b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-chat-v3.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-medium-3.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.5v","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-5-nano","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-oss-120b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-oss-20b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthropic/claude-opus-4.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/codestral-2508","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.5","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"z-ai/glm-4.5-air","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-coder","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bytedance/ui-tars-1.5-7b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-2.5-flash-lite","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-235b-a22b-2507","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"moonshotai/kimi-k2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"tencent/hunyuan-a13b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"morph/morph-v3-large","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"morph/morph-v3-fast","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-small-3.2-24b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-m1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-2.5-flash","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-2.5-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o3-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemini-2.5-pro-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-r1-0528","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-medium-3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-guard-4-12b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-30b-a3b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-14b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen3-32b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o4-mini-high","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o4-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4.1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4.1-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4.1-nano","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-4-maverick","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-4-scout","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-chat-v3-0324","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o1-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-small-3.1-24b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-3-4b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-3-12b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/command-a","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"rekaai/reka-flash-3","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-3-27b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"thedrummer/skyfall-36b-v2","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perplexity/sonar-reasoning-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perplexity/sonar-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perplexity/sonar-deep-research","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-saba","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o3-mini-high","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"aion-labs/aion-rp-llama-3.1-8b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen2.5-vl-72b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen-plus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o3-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-small-24b-instruct-2501","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"perplexity/sonar","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"minimax/minimax-01","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"microsoft/phi-4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"deepseek/deepseek-chat","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/o1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/command-r7b-12-2024","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-3.3-70b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"amazon/nova-lite-v1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"amazon/nova-micro-v1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"amazon/nova-pro-v1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o-2024-11-20","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-large-2407","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen-2.5-coder-32b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"thedrummer/unslopnemo-12b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"anthracite-org/magnum-v4-72b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen-2.5-7b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-3.2-1b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-3.2-3b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"qwen/qwen-2.5-72b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/command-r-08-2024","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"cohere/command-r-plus-08-2024","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sao10k/l3.1-euryale-70b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nousresearch/hermes-3-llama-3.1-70b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nousresearch/hermes-3-llama-3.1-405b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"sao10k/l3-lunaris-8b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o-2024-08-06","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-3.1-70b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"meta-llama/llama-3.1-8b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-nemo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o-mini","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o-mini-2024-07-18","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"google/gemma-2-27b-it","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4o-2024-05-13","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mixtral-8x22b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mistralai/mistral-large","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-3.5-turbo-0613","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openrouter/auto","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-3.5-turbo-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-3.5-turbo-16k","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"mancer/weaver","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"undi95/remm-slerp-l2-13b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"gryphe/mythomax-l2-13b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-3.5-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"openai/gpt-4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/qwen3.6-plus","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/claude-opus-4.8","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/claude-opus-4.7","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/claude-sonnet-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stealth/claude-opus-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"kilo-auto/frontier","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"kilo-auto/balanced","service":"kilo","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"kilo-auto/small","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"stable-diffusion-xl-base-v10","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3-Embedding-8B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bge-m3","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"bge-multilingual-gemma2","service":"ovh","to":{"classification":"free","lifecycle":"deprecated","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvr-tts-es-es","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvr-tts-it-it","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvr-tts-en-us","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"nvr-tts-de-de","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"whisper-large-v3","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"whisper-large-v3-turbo","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen2.5-VL-72B-Instruct","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3.5-9B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3Guard-Gen-8B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3.8-27B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3Guard-Gen-0.6B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"gpt-oss-20b","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Meta-Llama-3_3-70B-Instruct","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3.5-397B-A17B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"gpt-oss-120b","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Qwen3.6-27B","service":"ovh","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Mistral-Small-3.2-24B-Instruct-2506","service":"ovh","to":{"classification":"free","lifecycle":"deprecated","listed":true}},{"at":"2026-10-22T16:14:08.423Z","from":null,"id":"Mistral-Nemo-Instruct-2407","service":"ovh","to":{"classification":"free","lifecycle":"deprecated","listed":true}},{"at":"2026-10-23T18:22:11.920Z","from":null,"id":"moonshotai/kimi-k3.1-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-24T18:03:08.683Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/gpt-3.5-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-24T18:03:08.683Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/gpt-3.5-turbo-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-24T22:31:11.700Z","from":null,"id":"liquid/lfm-2.5-2.6b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-26T00:57:23.824Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"arcee-ai/trinity-large-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-10-26T14:12:11.834Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"arcee-ai/trinity-large-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-10-26T19:11:32.182Z","from":null,"id":"openai/gpt-6.1-terra","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-26T23:16:49.259Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"ibm-granite/granite-4.0-h-micro","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-27T01:15:53.771Z","from":null,"id":"openai/gpt-6.1-terra-pro","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-27T10:03:04.103Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"nvidia/nemotron-3-super-120b-a12b:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-10-27T19:57:53.011Z","from":null,"id":"prism-ml/ternary-bonsai-2-9b","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/gpt-4-turbo","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o1","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o1-pro","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o3-mini","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o3-mini-high","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o4-mini","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/o4-mini-high","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"qwen/qwen3-next-80b-a3b-thinking","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"stealth/claude-opus-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"stealth/claude-opus-4.7","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"stealth/claude-opus-4.8","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"stealth/claude-sonnet-4.6","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T15:55:26.462Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"stealth/qwen3.6-plus","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-28T20:19:03.403Z","from":null,"id":"particle-ai/particle-1","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-10-28T20:19:03.403Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"openai/gpt-5.2-chat","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-29T17:26:57.917Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"upstage/solar-pro-3","service":"kilo","to":{"classification":"paid","lifecycle":"not-listed","listed":false}},{"at":"2026-10-30T00:58:07.528Z","from":{"classification":"paid","lifecycle":"not-listed","listed":false},"id":"upstage/solar-pro-3","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-10-30T14:22:44.671Z","from":null,"id":"inclusionai/ling-3.1-flash-1019-free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-10-31T00:22:17.033Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"poolside/laguna-s-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-10-31T00:22:17.033Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"poolside/laguna-s-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":true}},{"at":"2026-10-31T00:22:17.033Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"poolside/laguna-xs-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-10-31T00:22:17.033Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"poolside/laguna-xs-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":true}},{"at":"2026-10-31T13:35:24.515Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"poolside/laguna-s-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-10-31T13:35:24.515Z","from":{"classification":"free","lifecycle":"retired","listed":true},"id":"poolside/laguna-s-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":false}},{"at":"2026-10-31T13:35:24.515Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"poolside/laguna-xs-2.1","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-10-31T13:35:24.515Z","from":{"classification":"free","lifecycle":"retired","listed":true},"id":"poolside/laguna-xs-2.1:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":false}},{"at":"2026-11-02T01:04:06.781Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"nousresearch/hermes-3-llama-3.1-70b","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-11-02T01:04:06.781Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"nousresearch/hermes-3-llama-3.1-405b","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-11-02T13:56:33.393Z","from":null,"id":"z-ai/glm-5.3-flashx-legal","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-11-02T13:56:33.393Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"nousresearch/hermes-3-llama-3.1-405b","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-11-02T13:56:33.393Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"nousresearch/hermes-3-llama-3.1-70b","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":false}},{"at":"2026-11-02T23:03:49.693Z","from":null,"id":"thinkingmachines/inkling-small:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-11-02T23:03:49.693Z","from":null,"id":"thinkingmachines/inkling:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-11-02T23:03:49.693Z","from":null,"id":"google/gemma-4-31b-it:free","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-11-03T00:23:51.078Z","from":{"classification":"paid","lifecycle":"active","listed":true},"id":"meta-llama/llama-3.1-70b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"retired","listed":true}},{"at":"2026-11-03T10:42:03.150Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"inclusionai/ling-3.1-flash-1019-free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T11:38:16.150Z","from":{"classification":"paid","lifecycle":"retired","listed":true},"id":"meta-llama/llama-3.1-70b-instruct","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"google/gemma-4-31b-it:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"liquid/lfm-2.5-2.6b:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"nvidia/nemotron-3.5-content-safety:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"recursive/flint-v1.0:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"thinkingmachines/inkling-small:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"thinkingmachines/inkling:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T19:55:39.383Z","from":{"classification":"free","lifecycle":"active","listed":true},"id":"xingchen-agi/xing4.0-29b-a4b:free","service":"kilo","to":{"classification":"free","lifecycle":"not-listed","listed":false}},{"at":"2026-11-03T20:50:35.055Z","from":null,"id":"stealth/crouton-alpha","service":"kilo","to":{"classification":"free","lifecycle":"active","listed":true}},{"at":"2026-11-04T01:02:52.584Z","from":{"classification":"free","lifecycle":"not-listed","listed":false},"id":"thinkingmachines/inkling-small:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":false}},{"at":"2026-11-04T01:02:52.584Z","from":{"classification":"free","lifecycle":"not-listed","listed":false},"id":"thinkingmachines/inkling:free","service":"kilo","to":{"classification":"free","lifecycle":"retired","listed":false}},{"at":"2026-11-04T01:02:52.584Z","from":{"classification":"free","lifecycle":"deprecated","listed":true},"id":"Mistral-Small-3.2-24B-Instruct-2506","service":"ovh","to":{"classification":"free","lifecycle":"retired","listed":true}},{"at":"2026-11-04T01:02:52.584Z","from":{"classification":"free","lifecycle":"deprecated","listed":true},"id":"Mistral-Nemo-Instruct-2407","service":"ovh","to":{"classification":"free","lifecycle":"retired","listed":true}},{"at":"2026-11-04T04:59:22.390Z","from":null,"id":"tencent/hy4","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}},{"at":"2026-11-04T13:51:00.283Z","from":{"classification":"free","lifecycle":"retired","listed":true},"id":"Mistral-Nemo-Instruct-2407","service":"ovh","to":{"classification":"unknown","lifecycle":"active","listed":true}},{"at":"2026-11-04T19:44:43.499Z","from":null,"id":"ricursiveai/ripple-65b-preview","service":"kilo","to":{"classification":"paid","lifecycle":"active","listed":true}}]},"generatedAt":"2026-11-04T21:29:27.556Z","integrity":{"algorithm":"sha256","payloadHash":"62e1194ae1cb02eeaddc5a3485b106a9001d290a69eaf36c9df738022969fc13"},"producer":{"commit":"7060479484fabdbbfbef85bccbb5bee6d7284939","repository":"aminmzadev/pi-free-catalog","runId":"41916445624","workflow":"catalog.yml"},"quality":{"freshSources":3,"largeChanges":[],"largeChangesApproved":false,"retainedSources":0,"status":"fresh"},"rulesHash":"04b27859860298ded60a16297a66ed839cfb25d4b5949cfc95c8deaa54310f20","schemaVersion":2,"sources":{"kilo":{"attemptedAt":"2026-11-04T21:29:27.556Z","bodySha256":"af7426f4d2021efa7bceb9a2d19fbfe0ea79bd8f3190a26dfc662b6f63d10f28","consecutiveFailures":0,"data":{"data":[{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","id":"kilo-auto/efficient","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Efficient","opencode":{},"preferredIndex":0,"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["dots-studio/dots-3-note-preview:free","nvidia/nemotron-3.5-super-vl:free","reflection/beam-free","stealth/glyph-cluster"]},"context_length":256000,"created":0,"description":"Rotates through available free models. Limited capability and no credits required. [Learn more](https://kilo.ai/docs/code-with-ai/agents/auto-model)\n\n**Warning** Prompts may be logged by the upstream provider and used to improve their services. Not suitable for production or sensitive data workloads.","id":"kilo-auto/free","inference_provider_ids":[],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Auto Free","opencode":{},"preferredIndex":1,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Super VL (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"preferredIndex":2,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"reflection/beam-free","context_length":1048576,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Beam is Reflection's reasoning model for coding and agentic workflows, combining strong coding capabilities with fast, low-latency inference, served through Vercel AI Gateway at no cost. It supports function calling, structured outputs, and streaming, and takes text input only. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"reflection/beam-free","inference_provider_ids":["reflection"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Reflection: Beam 1.0 (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":3,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"instruct_type":null,"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"canonical_slug":"stealth/glyph-cluster","context_length":256000,"created":1756238927,"default_parameters":{},"description":"Your prompts and completions may be retained and used to train or improve the provider's services. Glyph Cluster is a reasoning model for coding and long-context analysis, served through Vercel AI Gateway during its stealth period at no cost. It supports function calling and streaming, takes text input only, and does not support structured outputs. Zero Data Retention is not available for this model.","hugging_face_id":"","id":"stealth/glyph-cluster","inference_provider_ids":["stealth"],"isCustomLlm":true,"isFree":true,"mayTrainOnYourPrompts":true,"name":"Stealth: Glyph Cluster (free)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":4,"pricing":{"completion":"0","image":"0","input_cache_read":"0","input_cache_write":"0","internal_reasoning":"0","prompt":"0","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":256000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","expiration_date":null,"id":"anthropic/claude-opus-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"preferredIndex":5,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","expiration_date":null,"id":"openai/gpt-6.1-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"preferredIndex":6,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash-1017","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash 1017","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"preferredIndex":7,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","expiration_date":null,"id":"z-ai/glm-5.3-flash","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"preferredIndex":8,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","expiration_date":null,"id":"ricursiveai/ripple-65b-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ricursiveAI/Ripple-65B-Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000002"},"supported_parameters":["logprobs","max_tokens","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","expiration_date":null,"id":"tencent/hy4","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002501000","input_cache_read":"0.000000042000","prompt":"0.000000834000"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793669930,"description":"Crouton Alpha is a lightweight model built for scalable coding, agentic, and multimodal workflows. It's ideal for executing agentic sub-tasks, tool use, and document analysis in high-volume, repeated work. Developers...","expiration_date":null,"id":"stealth/crouton-alpha","inference_provider_ids":["stealth"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Crouton Alpha","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","expiration_date":null,"id":"z-ai/glm-5.3-flashx-legal","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX Legal","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","expiration_date":null,"id":"particle-ai/particle-1","inference_provider_ids":["particle-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Particle AI: Particle-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.000000003","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","expiration_date":null,"id":"openai/gpt-6.1-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","expiration_date":null,"id":"moonshotai/kimi-k3.1-pro","inference_provider_ids":["alibaba","baseten","fireworks","inference-net","modal","moonshotai","morph","nebius","parasail","phala","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3.1 Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","expiration_date":null,"id":"minimax/minimax-m3.1-flash","inference_provider_ids":["digitalocean","fireworks","gmicloud","inference-net","minimax","modelrun","nebius","novita","parasail","sambanova","streamlake","tenstorrent","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":524288}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","expiration_date":null,"id":"elorian/glimpse","inference_provider_ids":["elorian","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Elorian: Glimpse","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":256000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","expiration_date":null,"id":"reflection/beam-1.0-501b-a23b","inference_provider_ids":["baseten","coreweave","digitalocean","nebius","reflection","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reflection: Beam 1.0 501B A23B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1792158337,"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","expiration_date":"2026-11-08","id":"inception/mercury-3","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 3 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000700000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-9b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","expiration_date":null,"id":"moondream/moondream3-preview","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3 Preview","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32000,"created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","expiration_date":null,"id":"moondream/moondream3.1-9b-a2b","inference_provider_ids":["primeintellect"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Moondream: Moondream 3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","temperature","top_p"],"top_provider":{"context_length":32000,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","expiration_date":null,"id":"meta/muse-spark-open","inference_provider_ids":["baseten","fireworks","makora","modal","nebius","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark Open","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","expiration_date":null,"id":"nvidia/nemotron-3.5-super-vl","inference_provider_ids":["baseten","coreweave","crusoe","darkbloom","deepinfra","io-net","nebius","primeintellect","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Super VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000035","discount":0,"input_cache_read":"0.00000001","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.10","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.10","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"alias_target":"unbiased/pareto-26.10","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","expiration_date":null,"id":"~unbiased/pareto-latest","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto Latest","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.00000003","prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","expiration_date":null,"id":"unbiased/pareto-26.9","inference_provider_ids":["unbiased"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Pareto 26.9","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025"},"supported_parameters":["max_tokens","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","expiration_date":null,"id":"liquid/lfm-2.5-24b-a2b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-24B-A2B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000007","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","expiration_date":null,"id":"google/gemini-4-argon","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 4 Argon (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000010000000","image":"0.000002000000","input_cache_read":"0.000000100000","input_cache_write":"0.000000187500","internal_reasoning":"0.000010000000","prompt":"0.000002000000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","expiration_date":null,"id":"scaledown/summarize","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Summarize","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":4000}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","expiration_date":null,"id":"scaledown/extract","inference_provider_ids":["scaledown"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ScaleDown: Extract","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000000000","prompt":"0.000000050000"},"supported_parameters":["max_tokens"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","expiration_date":null,"id":"meta/muse-wonder","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Wonder","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000004","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","expiration_date":null,"id":"stepfun/step-5-preview","inference_provider_ids":["deepinfra","featherless","gmicloud","stepfun","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 5 Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"input_cache_read":"0.0000001","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","expiration_date":null,"id":"anthropic/claude-haiku-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","expiration_date":null,"id":"google/gemini-nano-banana-2.1","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2.1","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1048576,"created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","expiration_date":null,"id":"mistralai/mistral-large-4-0","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000021","discount":0,"input_cache_read":"0.00000007","prompt":"0.0000007"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","expiration_date":null,"id":"inclusionai/ling-3.1-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.1 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000900000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6.1-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6.1 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","expiration_date":null,"id":"anthropic/claude-sonnet-5.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":36864,"created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","expiration_date":null,"id":"perceptron/perceptron-mk1.5","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":36864,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","expiration_date":null,"id":"fireworks/ember-1","inference_provider_ids":["fireworks"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Fireworks: Ember-1","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","expiration_date":null,"id":"z-ai/glm-5.3-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 Prime","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000088","input_cache_read":"0.00000056","prompt":"0.0000028"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","expiration_date":null,"id":"qwen/qwen3.8-max-prime","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max Prime","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000005","prompt":"0.000004"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","expiration_date":null,"id":"aion-labs/aion-3.5-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5 Mini","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.5","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","expiration_date":null,"id":"upstage/solar-mini4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Mini 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000400000","input_cache_read":"0.000000010000","prompt":"0.000000100000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":192000,"created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","expiration_date":null,"id":"cohere/command-a-plus","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A+","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tools","top_k","top_p"],"top_provider":{"context_length":192000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","expiration_date":null,"id":"openai/gpt-6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","expiration_date":null,"id":"openai/gpt-6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro-ultraspeed","inference_provider_ids":["xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000087","discount":0,"input_cache_read":"0.000000036","prompt":"0.00000435"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","expiration_date":null,"id":"xiaomi/mimo-v2.6-flash","inference_provider_ids":["boundless","cohere","darkbloom","deepinfra","gmicloud","inference-net","makora","novita","tencent","venice","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video","audio"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","expiration_date":null,"id":"xiaomi/mimo-v2.6-pro","inference_provider_ids":["boundless","deepinfra","gmicloud","novita","streamlake","tencent","xiaomi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.6-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","expiration_date":null,"id":"x-ai/grok-4.7","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.7","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},{"architecture":{"input_modalities":["text","image","audio","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","expiration_date":null,"id":"qwen/qwen3.8-omni-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Omni Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","expiration_date":null,"id":"prism-ml/ternary-bonsai-2-27b","inference_provider_ids":["darkbloom"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"PrismML: Ternary Bonsai 2 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","xhigh"]}],"variants":{"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","expiration_date":null,"id":"z-ai/glm-5.3-flashx","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3 FlashX","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","input_cache_read":"0.000000075","prompt":"0.00000037"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"alias_target":"deepseek/deepseek-v4-pro-0813","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","expiration_date":null,"id":"~deepseek/deepseek-pro-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","input_cache_read":"0.0000001","prompt":"0.0000001035"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},{"alias_target":"deepseek/deepseek-v4.1-flash-1017","architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","expiration_date":null,"id":"~deepseek/deepseek-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cloudflare","cohere","coreweave","crusoe","decart","deepinfra","deepseek","dekallm","digitalocean","fireworks","gmicloud","inference-net","ionstream","makora","mistral","modal","modelrun","morph","near-ai","nebius","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","stepfun","streamlake","subconscious","telnyx","tenstorrent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.000000004","prompt":"0.000000022"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","expiration_date":null,"id":"inference-net/schematron-v2-turbo","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Turbo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.00000003","prompt":"0.00000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","expiration_date":null,"id":"inference-net/schematron-v2-small","inference_provider_ids":["inference-net"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inference.net: Schematron V2 Small","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000023","discount":0,"input_cache_read":"0.00000005","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},{"alias_target":"openai/gpt-6-astra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","expiration_date":null,"id":"~openai/gpt-astra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Astra Latest ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"alias_target":"openai/gpt-6.1-sol","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","expiration_date":null,"id":"~openai/gpt-sol-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Sol Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"alias_target":"openai/gpt-6.1-terra","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","expiration_date":null,"id":"~openai/gpt-terra-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Terra Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"alias_target":"openai/gpt-6-luna","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1050000,"created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","expiration_date":null,"id":"~openai/gpt-luna-latest","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Luna Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","expiration_date":null,"id":"sakana/fugu-ultra-v2","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra v2","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-max","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Max","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","expiration_date":null,"id":"inclusionai/ling-3.0-flash-vl","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash VL","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000018","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","expiration_date":null,"id":"deepseek/deepseek-v4.1-flash","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","cohere","coreweave","crusoe","deepinfra","deepseek","digitalocean","fireworks","gmicloud","google-vertex","inference-net","makora","mancer","modal","morph","nebius","novita","open-inference","parasail","pareto","particle","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4.1 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000006000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":2.5831196000000003,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":260000,"created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2.5","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2.5 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000000750000","input_cache_read":"0.000000020000","prompt":"0.000000200000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":260000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-mini","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.0000000025","prompt":"0.000000025"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","expiration_date":null,"id":"nex-agi/nex-n2.5-pro","inference_provider_ids":["nex-agi"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nex AGI: Nex-N2.5-Pro","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","discount":0,"input_cache_read":"0.000000015","prompt":"0.000000075"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","expiration_date":null,"id":"openai/gpt-6-astra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":107.293192,"overallScore":0.79325843},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-6-astra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-6 Astra Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","expiration_date":null,"id":"qwen/qwen3.8-max-0902","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Max (0902)","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","expiration_date":null,"id":"meta/muse-spark-1.3-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.3 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","expiration_date":null,"id":"meta/muse-spark-1.3","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","expiration_date":null,"id":"google/gemini-3.8-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.8 Flash (50% off)","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":112.2663174,"overallScore":0.75280899},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","expiration_date":null,"id":"anthropic/claude-fable-5.1","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":91.4074256,"overallScore":0.76179775},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","expiration_date":null,"id":"ibm-granite/granite-4.2-8b","inference_provider_ids":["coreweave","deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"IBM: Granite 4.2 8B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","expiration_date":null,"id":"tencent/hy4-preview","inference_provider_ids":["atlas-cloud","cohere","deepinfra","gmicloud","novita","siliconflow","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy4 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022509","discount":0,"input_cache_read":"0.0000000378","prompt":"0.0000007506"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":64000}},{"alias_target":"z-ai/glm-5.3-flash","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","expiration_date":null,"id":"~z-ai/glm-flash-latest","inference_provider_ids":["atlas-cloud","baseten","boundless","cohere","coreweave","crusoe","darkbloom","deepinfra","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","morph","near-ai","nebius","nextbit","novita","open-inference","parasail","pareto","particle","particle-ai","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000000923","input_cache_read":"0.0000000285","prompt":"0.0000000285"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","expiration_date":null,"id":"qwen/qwen3.8-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000047","discount":0,"input_cache_read":"0.000000016","input_cache_write":"0.0000002","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","expiration_date":null,"id":"meta/muse-spark-1.2-contributor","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Meta: Muse Spark 1.2 Contributor","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.000000002","prompt":"0.0000001","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","expiration_date":null,"id":"deepseek/deepseek-v4-flash-vision-exp","inference_provider_ids":["deepinfra","gmicloud","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Vision Exp","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006468","input_cache_read":"0.00000000686","prompt":"0.0000002156"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","expiration_date":null,"id":"tencent/hy-mt2-1.8b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-1.8B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000177","discount":0,"prompt":"0.000000044"},"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","expiration_date":null,"id":"tencent/hy-mt2-30b-a3b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-30B-A3B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},{"alias_target":"z-ai/glm-5.3","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","expiration_date":null,"id":"~z-ai/glm-latest","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","input_cache_read":"0.0000000689","prompt":"0.0000000699"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":8192,"created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","expiration_date":null,"id":"tencent/hy-mt2-7b","inference_provider_ids":["tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy-MT2-7B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000295","discount":0,"prompt":"0.000000074"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","expiration_date":null,"id":"z-ai/glm-5.3","inference_provider_ids":["akashml","alibaba","amazon-bedrock","atlas-cloud","baidu","baseten","boundless","cloudflare","coreweave","crusoe","decart","deepinfra","dekallm","digitalocean","fireworks","friendli","gmicloud","inceptron","inference-net","makora","mistral","modal","modelrun","morph","nebius","novita","parasail","phala","primeintellect","reka","relace","runinfra","runware","sail-research","siliconflow","streamlake","subconscious","telnyx","tencent","tenstorrent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.3","opencode":{"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004400000","input_cache_read":"0.000000260000","prompt":"0.000001400000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1024000,"created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","expiration_date":null,"id":"qwen/qwen3.8-27b","inference_provider_ids":["akashml","alibaba","cerebras","chutes","cloudflare","coreweave","darkbloom","deepinfra","dekallm","ionstream","mancer","modal","modelrun","near-ai","nebius","novita","parasail","phala","primeintellect","reka","runinfra","streamlake","tenstorrent","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 27B","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000255","discount":0,"input_cache_read":"0.000000085","input_cache_write":"0.00000053125","prompt":"0.000000425"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":512000,"created":1786680361,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","expiration_date":"2026-12-31","id":"dots-studio/dots-3-note-preview:free","inference_provider_ids":["atlas-cloud"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Dots Studio: Dots3-Note Preview (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":512000,"is_moderated":false,"max_completion_tokens":460800}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","expiration_date":null,"id":"google/gemini-3.7-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003750000","image":"0.000000750000","input_cache_read":"0.000000075000","input_cache_write":"0.000000041667","internal_reasoning":"0.000003750000","prompt":"0.000000750000","web_search":"0.028000000000"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","expiration_date":null,"id":"bytedance-seed/seed-2-1-turbo","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 2.1 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1048576,"created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","expiration_date":null,"id":"qwen/qwen3.8-2.4t-a95b","inference_provider_ids":["alibaba","deepinfra","fireworks","gmicloud","modal","novita","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.8 2.4T A95B","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000025","input_cache_write":"0.0000025","prompt":"0.000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-2.0-code","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Code (retires Nov 11)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","expiration_date":null,"id":"deepseek/deepseek-v4-pro-0813","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","deepseek","digitalocean","gmicloud","ionstream","nebius","novita","parasail","phala","relace","sail-research","siliconflow","streamlake","tencent","together","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0813","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003960000","input_cache_read":"0.000000044000","prompt":"0.000001320000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","enkrypt":{"bias_score":35.14,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":7.33813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.6","nist_score":13,"owasp_score":14,"provider":"openai_compatible","risk_score":12.683,"robustness_score":null,"safety_score":19.9679,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"x-ai/grok-4.6","inference_provider_ids":["amazon-bedrock","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.6","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":33.829006,"overallScore":0.73033708},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","expiration_date":null,"id":"liquid/lfm-2.5-2.6b","inference_provider_ids":["liquid"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"LiquidAI: LFM2.5-2.6B","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000004","prompt":"0.00000035"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning","inference_provider_ids":["coreweave","darkbloom","deepinfra","fireworks","io-net","runinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Lightning","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"input_cache_read":"0.0000000125","prompt":"0.000000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3.5-lightning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3.5 Lightning (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","expiration_date":null,"id":"sakana/sakana-namazu","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":true,"name":"Sakana: Sakana Namazu","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000095","web_search":"0.007"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","expiration_date":null,"id":"upstage/solar-pro4","inference_provider_ids":["upstage"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Upstage: Solar Pro 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","expiration_date":null,"id":"meta/muse-glimmer-30b","inference_provider_ids":["deepinfra","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Glimmer 30B","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","expiration_date":null,"id":"meta/muse-spark-1.2","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":44.68511,"overallScore":0.51460674},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"alias_target":"deepseek/deepseek-v4-flash-0731","architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","expiration_date":null,"id":"~deepseek/deepseek-v4-flash-latest","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013728","input_cache_read":"0.000000001456","prompt":"0.00000004576"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","expiration_date":null,"id":"deepseek/deepseek-v4-flash-0731","inference_provider_ids":["alibaba","atlas-cloud","baidu","baseten","boundless","chutes","cloudflare","cohere","coreweave","deepinfra","digitalocean","gmicloud","inceptron","mancer","morph","novita","parasail","phala","primeintellect","reka","relace","runware","sail-research","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0731","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000001320000","input_cache_read":"0.000000028000","prompt":"0.000000440000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","expiration_date":null,"id":"thinkingmachines/inkling-small","inference_provider_ids":["deepinfra","thinkingmachines"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling Small","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.0000001","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","expiration_date":null,"id":"qwen/qwen3.7-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000013","discount":0,"input_cache_read":"0.000000006","input_cache_write":"0.000000038","prompt":"0.00000003"},"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","enkrypt":{"bias_score":40.83,"cbrn_score":25.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-5","nist_score":14,"owasp_score":15,"provider":"openai_compatible","risk_score":13.8351,"robustness_score":null,"safety_score":19.4868,"source":"Anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.18},"expiration_date":null,"id":"anthropic/claude-opus-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":113.5366288,"overallScore":0.71460674},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","expiration_date":null,"id":"inclusionai/ling-3.0-flash","inference_provider_ids":["deepinfra","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"inclusionAI: Ling 3.0 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000180000","input_cache_read":"0.000000012000","prompt":"0.000000060000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","enkrypt":{"bias_score":83.72,"cbrn_score":52.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":27.56,"jailbreak_score":28.4892,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.6-flash","nist_score":36,"owasp_score":40,"provider":"openai_compatible","risk_score":35.5088,"robustness_score":null,"safety_score":43.7851,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"google/gemini-3.6-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.6 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001875","discount":0,"image":"0.000000375","input_cache_read":"0.0000000375","input_cache_write":"0.0000000208333333333333","internal_reasoning":"0.000001875","prompt":"0.000000375","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":80.3143008,"overallScore":0.47865169},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","expiration_date":null,"id":"google/gemini-3.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048756,"created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","expiration_date":null,"id":"meituan/longcat-2.0","inference_provider_ids":["atlas-cloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meituan: LongCat 2.0","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003000000","input_cache_read":"0.000000015000","prompt":"0.000000750000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1048756,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text","image","audio"],"modality":"text+image+audio->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":524288,"created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","enkrypt":{"bias_score":60.98,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":0.719424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Inkling","nist_score":15,"owasp_score":19,"provider":"together","risk_score":15.2186,"robustness_score":null,"safety_score":24.2983,"source":"ThinkingMachines","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"thinkingmachines/inkling","inference_provider_ids":["modal","thinkingmachines","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Thinking Machines: Inkling","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000405","discount":0,"input_cache_read":"0.00000017","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":35.689686,"overallScore":0.43595506},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":471859}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","expiration_date":null,"id":"moonshotai/kimi-k3","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":48.378817,"overallScore":0.72808989},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image","video","file","pdf"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","enkrypt":{"bias_score":50.13,"cbrn_score":6.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.11,"jailbreak_score":1.43885,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"muse-spark-1.1","nist_score":16,"owasp_score":20,"provider":"openai_compatible","risk_score":15.9875,"robustness_score":null,"safety_score":23.1756,"source":"Meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"meta/muse-spark-1.1","inference_provider_ids":["meta"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Muse Spark 1.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000425","discount":0,"input_cache_read":"0.00000015","prompt":"0.00000125","web_search":"0.0025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":30.153412199999998,"overallScore":0.59775281},"top_provider":{"context_length":1048576,"is_moderated":true,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-luna-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","enkrypt":{"bias_score":78.04,"cbrn_score":22.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":9.64029,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-luna","nist_score":23,"owasp_score":27,"provider":"openai","risk_score":22.8769,"robustness_score":null,"safety_score":33.6808,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"openai/gpt-5.6-luna","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Luna","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000002","input_cache_write":"0.00000025","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-terra-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","enkrypt":{"bias_score":60.72,"cbrn_score":20,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4.44,"jailbreak_score":8.48921,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-terra","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.0053,"robustness_score":null,"safety_score":28.2277,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.64},"expiration_date":null,"id":"openai/gpt-5.6-terra","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Terra","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","expiration_date":null,"id":"openai/gpt-5.6-sol-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol Pro","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","enkrypt":{"bias_score":72.09,"cbrn_score":19.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.6-sol","nist_score":22,"owasp_score":25,"provider":"openai","risk_score":21.5671,"robustness_score":null,"safety_score":31.7562,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.91},"expiration_date":null,"id":"openai/gpt-5.6-sol","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.6 Sol","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00002","discount":0,"input_cache_read":"0.0000004","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.40998859999999,"overallScore":0.76179775},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":500000,"created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","enkrypt":{"bias_score":66.41,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":0.44,"jailbreak_score":10.3597,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.5","nist_score":20,"owasp_score":22,"provider":"openai_compatible","risk_score":19.5645,"robustness_score":null,"safety_score":29.591,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.64},"expiration_date":null,"id":"x-ai/grok-4.5","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":27.291154,"overallScore":0.70786517},"top_provider":{"context_length":500000,"is_moderated":false,"max_completion_tokens":450000}},{"alias_target":"x-ai/grok-4.7","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":500000,"created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","expiration_date":null,"id":"~x-ai/grok-latest","inference_provider_ids":["amazon-bedrock","google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"xAI: Grok Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","input_cache_read":"0.0000005","input_cache_write":"0","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":500000,"is_moderated":true,"max_completion_tokens":450000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","expiration_date":null,"id":"aion-labs/aion-3.0-mini","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0-Mini","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000014","discount":0,"input_cache_read":"0.00000018","prompt":"0.0000007"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","expiration_date":null,"id":"aion-labs/aion-3.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-3.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.00000075","prompt":"0.000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","enkrypt":{"bias_score":56.07,"cbrn_score":0.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":1.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"hy3","nist_score":15,"owasp_score":19,"provider":"novita","risk_score":15.1549,"robustness_score":null,"safety_score":20.6095,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"tencent/hy3","inference_provider_ids":["atlas-cloud","gmicloud","novita","phala","tencent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"input_cache_read":"0.000000020625","prompt":"0.0000000825"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","enkrypt":{"bias_score":29.46,"cbrn_score":7.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8.89,"jailbreak_score":2.01439,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-5","nist_score":9,"owasp_score":11,"provider":"anthropic","risk_score":9.20561,"robustness_score":null,"safety_score":13.3119,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.18},"expiration_date":null,"id":"anthropic/claude-sonnet-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.0000002","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":36.186279799999994,"overallScore":0.59550562},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","expiration_date":null,"id":"sakana/fugu-ultra","inference_provider_ids":["sakana"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sakana: Fugu Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","expiration_date":null,"id":"google/gemini-3.1-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":131072,"created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":256000,"created":1781723748,"description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","expiration_date":null,"id":"cohere/north-mini-code:free","inference_provider_ids":["cohere"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"Cohere: North Mini Code (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","enkrypt":{"bias_score":86.3,"cbrn_score":50.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":13.78,"jailbreak_score":29.0647,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.2","nist_score":33,"owasp_score":36,"provider":"openai_compatible","risk_score":32.5842,"robustness_score":null,"safety_score":40.016,"source":"z-ai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"z-ai/glm-5.2","inference_provider_ids":["alibaba","ambient","atlas-cloud","baidu","baseten","cloudflare","coreweave","deepinfra","digitalocean","friendli","gmicloud","inceptron","mistral","morph","nebius","novita","parasail","relace","runware","siliconflow","streamlake","tencent","together","venice","wafer","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.2","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":26.2141134,"overallScore":0.53033708},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","enkrypt":{"bias_score":84.24,"cbrn_score":42,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":7.56,"jailbreak_score":21.5827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.7-code","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.6738,"robustness_score":null,"safety_score":37.2093,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2.7-code","inference_provider_ids":["alibaba","cloudflare","coreweave","gmicloud","inceptron","moonshotai","novita","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.7 Code","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":32.940153,"overallScore":0.60674157},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"alias_target":"anthropic/claude-fable-5.1","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","expiration_date":null,"id":"~anthropic/claude-fable-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable Latest ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","input_cache_read":"0.00000025","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","enkrypt":{"bias_score":0,"cbrn_score":0,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":0,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-fable-5","nist_score":0,"owasp_score":0,"provider":"anthropic","risk_score":0,"robustness_score":null,"safety_score":0,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"anthropic/claude-fable-5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Fable 5 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00005","discount":0,"input_cache_read":"0.000001","input_cache_write":"0.0000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":87.5169082,"overallScore":0.71011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","expiration_date":null,"id":"nvidia/nemotron-3.5-content-safety","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3.5 Content Safety","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","enkrypt":{"bias_score":87.34,"cbrn_score":52.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":6.22,"jailbreak_score":27.1942,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"nemotron-3-ultra-550b-a55b","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.0435,"robustness_score":null,"safety_score":41.7803,"source":"nvidia","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","inference_provider_ids":["baseten","deepinfra","fireworks","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Ultra","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000176","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"terminalBench":{"avgAttemptCostUsd":101.8186902,"overallScore":0.19101124},"top_provider":{"context_length":202800,"is_moderated":false,"max_completion_tokens":182520}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Ultra (free)","opencode":{"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","expiration_date":null,"id":"qwen/qwen3.7-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000128","discount":0,"input_cache_read":"0.000000064","input_cache_write":"0.0000004","prompt":"0.00000032"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","enkrypt":{"bias_score":79.59,"cbrn_score":49.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":20,"jailbreak_score":26.3309,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m3","nist_score":31,"owasp_score":35,"provider":"openai_compatible","risk_score":31.3345,"robustness_score":null,"safety_score":39.1339,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.36},"expiration_date":null,"id":"minimax/minimax-m3","inference_provider_ids":["atlas-cloud","coreweave","deepinfra","fireworks","gmicloud","mara","minimax","modelrun","nebius","novita","parasail","streamlake","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M3","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000006","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":10.350343800000001,"overallScore":0.47640449},"top_provider":{"context_length":524288,"is_moderated":false,"max_completion_tokens":512000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","expiration_date":null,"id":"stepfun/step-3.7-flash","inference_provider_ids":["novita","stepfun"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.7 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000115","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","enkrypt":{"bias_score":48.06,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":24.89,"jailbreak_score":3.02158,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-8","nist_score":16,"owasp_score":21,"provider":"anthropic","risk_score":16.4467,"robustness_score":null,"safety_score":21.9727,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.73},"expiration_date":null,"id":"anthropic/claude-opus-4.8","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.8","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":85.194714,"overallScore":0.67640449},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","enkrypt":{"bias_score":74.42,"cbrn_score":49.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":8.89,"jailbreak_score":26.9065,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.7-max","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2787,"robustness_score":null,"safety_score":36.8885,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"qwen/qwen3.7-max","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.7 Max","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004425","discount":0,"input_cache_read":"0.000000295","input_cache_write":"0.00000184375","prompt":"0.000001475"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":20.6499772,"overallScore":0.54606742},"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":256000,"created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","enkrypt":{"bias_score":84.75,"cbrn_score":46.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":13.33,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.89,"jailbreak_score":27.7698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-build-0.1","nist_score":34,"owasp_score":37,"provider":"openai_compatible","risk_score":33.9681,"robustness_score":null,"safety_score":42.903,"source":"xAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":12.36},"expiration_date":null,"id":"x-ai/grok-build-0.1","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok Build 0.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":30.701289600000003,"overallScore":0.50561798},"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":230400}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","enkrypt":{"bias_score":80.36,"cbrn_score":52,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":11.56,"jailbreak_score":30.6475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-3.5-flash","nist_score":32,"owasp_score":35,"provider":"openai_compatible","risk_score":32.3289,"robustness_score":null,"safety_score":38.332,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.73},"expiration_date":null,"id":"google/gemini-3.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.5 Flash","opencode":{"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000045","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"terminalBench":{"avgAttemptCostUsd":104.4912192,"overallScore":0.64719101},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","expiration_date":null,"id":"perceptron/perceptron-mk1","inference_provider_ids":["perceptron"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perceptron: Perceptron Mk1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","expiration_date":null,"id":"google/gemini-3.1-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","expiration_date":null,"id":"openai/gpt-chat-latest","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Chat Latest","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":1000000,"created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","enkrypt":{"bias_score":87.08,"cbrn_score":34.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":22.446,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"grok-4.3","nist_score":31,"owasp_score":36,"provider":"xai","risk_score":31.3584,"robustness_score":null,"safety_score":39.6151,"source":"xai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.55},"expiration_date":null,"id":"x-ai/grok-4.3","inference_provider_ids":["google-vertex","xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":900000}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","expiration_date":null,"id":"mistralai/mistral-medium-3-5","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.5","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000075","discount":0,"prompt":"0.0000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1777393095,"description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...\n\n**Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","expiration_date":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","inference_provider_ids":["nvidia"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":65536}},{"alias_target":"anthropic/claude-haiku-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","expiration_date":null,"id":"~anthropic/claude-haiku-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.000000125","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"alias_target":"openai/gpt-5.4-mini","architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":400000,"created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","expiration_date":null,"id":"~openai/gpt-mini-latest","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Mini Latest","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"alias_target":"google/gemini-4-argon","architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","expiration_date":null,"id":"~google/gemini-pro-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Pro Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","image":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.00001","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"alias_target":"moonshotai/kimi-k3","architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","expiration_date":null,"id":"~moonshotai/kimi-latest","inference_provider_ids":["alibaba","amazon-bedrock","baseten","boundless","chutes","decart","deepinfra","digitalocean","fireworks","inference-net","io-net","makora","modal","moonshotai","morph","nebius","parasail","pareto-alpha","phala","relace","runware","sail-research","together","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi Latest","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"max":{"reasoning":{"effort":"max","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000105539","input_cache_read":"0.00000018","prompt":"0.0000001824"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":943718}},{"alias_target":"google/gemini-3.8-flash","architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1048576,"created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","expiration_date":null,"id":"~google/gemini-flash-latest","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini Flash Latest","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000375","image":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000375","prompt":"0.00000075","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"alias_target":"anthropic/claude-sonnet-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","expiration_date":null,"id":"~anthropic/claude-sonnet-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.0000001","input_cache_write":"0.0000025","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","expiration_date":null,"id":"qwen/qwen3.5-plus-20260420","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-04-20","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","discount":0,"input_cache_write":"0.000000375","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","expiration_date":null,"id":"qwen/qwen3.6-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001125","discount":0,"input_cache_write":"0.000000234375","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","expiration_date":null,"id":"qwen/qwen3.6-35b-a3b","inference_provider_ids":["akashml","atlas-cloud","coreweave","darkbloom","deepinfra","dekallm","parasail","phala","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 35B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000025","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","expiration_date":null,"id":"qwen/qwen3.6-27b","inference_provider_ids":["alibaba","chutes","deepinfra","phala","reka","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000027","discount":0,"prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","enkrypt":{"bias_score":61.5,"cbrn_score":20.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.33,"jailbreak_score":9.20863,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.5","nist_score":19,"owasp_score":22,"provider":"openai","risk_score":19.2109,"robustness_score":null,"safety_score":28.4683,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8},"expiration_date":null,"id":"openai/gpt-5.5","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.5","opencode":{"ai_sdk_provider":"openai","prompt":"gpt55","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00003","discount":0,"input_cache_read":"0.0000005","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":72.62918640000001,"overallScore":0.74157303},"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","enkrypt":{"bias_score":85.27,"cbrn_score":17.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":22.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":33.78,"jailbreak_score":9.06475,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-pro","nist_score":33,"owasp_score":39,"provider":"novita","risk_score":33.2118,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":7.45},"expiration_date":null,"id":"deepseek/deepseek-v4-pro","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","deepseek","digitalocean","gmicloud","nebius","novita","relace","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Pro 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"input_cache_read":"0.000000135","prompt":"0.0000016"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":15.908566,"overallScore":0.44044944},"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":393216}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":1048576,"created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","enkrypt":{"bias_score":85.27,"cbrn_score":29.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":23.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":21.0072,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v4-flash","nist_score":36,"owasp_score":41,"provider":"novita","risk_score":36.2603,"robustness_score":null,"safety_score":42.3416,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.36},"expiration_date":null,"id":"deepseek/deepseek-v4-flash","inference_provider_ids":["alibaba","atlas-cloud","azure","baidu","baseten","deepinfra","digitalocean","fireworks","gmicloud","mancer","novita","parasail","relace","siliconflow","streamlake","venice","wafer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V4 Flash 0423","opencode":{"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000182","input_cache_read":"0.0000000182","prompt":"0.000000091"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048575,"is_moderated":false,"max_completion_tokens":943717}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","expiration_date":null,"id":"tencent/hy3-preview","inference_provider_ids":["gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hy3 preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000006","prompt":"0.00000018"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1050000,"created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","enkrypt":{"bias_score":71.06,"cbrn_score":47,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.33,"jailbreak_score":24.4604,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"mimo-v2.5-pro","nist_score":28,"owasp_score":31,"provider":"openai_compatible","risk_score":27.8866,"robustness_score":null,"safety_score":35.2847,"source":"xiaomi","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":null,"id":"xiaomi/mimo-v2.5-pro","inference_provider_ids":["atlas-cloud","digitalocean","gmicloud"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5-Pro","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000870000","input_cache_read":"0.000000004000","prompt":"0.000000435000"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":4.9236556,"overallScore":0.47640449},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","audio","image","video"],"modality":"text+image+audio+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","expiration_date":null,"id":"xiaomi/mimo-v2.5","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Xiaomi: MiMo-V2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000008","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":272000,"created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","expiration_date":null,"id":"openai/gpt-5.4-image-2","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Image 2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.000002","prompt":"0.000008","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","top_logprobs","verbosity"],"top_provider":{"context_length":272000,"is_moderated":true,"max_completion_tokens":128000}},{"alias_target":"anthropic/claude-opus-5.5","architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","expiration_date":null,"id":"~anthropic/claude-opus-latest","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus Latest","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.00002","input_cache_read":"0.0000002","input_cache_write":"0.000005","prompt":"0.000004","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","enkrypt":{"bias_score":71.32,"cbrn_score":48.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":9.44,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":12.44,"jailbreak_score":27.0504,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.6","nist_score":29,"owasp_score":32,"provider":"openai_compatible","risk_score":29.2868,"robustness_score":null,"safety_score":36.0866,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.73},"expiration_date":null,"id":"moonshotai/kimi-k2.6","inference_provider_ids":["atlas-cloud","baidu","chutes","cloudflare","coreweave","crusoe","deepinfra","digitalocean","gmicloud","inceptron","moonshotai","novita","parasail","phala","siliconflow","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000341","input_cache_read":"0.00000015","prompt":"0.00000065"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":24.844050600000003,"overallScore":0.54382022},"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","enkrypt":{"bias_score":76.49,"cbrn_score":3.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":17.78,"jailbreak_score":1.72662,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-opus-4-7","nist_score":20,"owasp_score":26,"provider":"anthropic","risk_score":19.9881,"robustness_score":null,"safety_score":28.4683,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"anthropic/claude-opus-4.7","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.7","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true},"verbosity":"xhigh"}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"terminalBench":{"avgAttemptCostUsd":100.5076156,"overallScore":0.7011236},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","enkrypt":{"bias_score":76.49,"cbrn_score":21,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":11.5108,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5.1","nist_score":24,"owasp_score":28,"provider":"novita","risk_score":24.4588,"robustness_score":null,"safety_score":32.7185,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"z-ai/glm-5.1","inference_provider_ids":["alibaba","atlas-cloud","baidu","chutes","friendli","gmicloud","nebius","novita","phala","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000044","discount":0,"input_cache_read":"0.00000026","prompt":"0.0000014"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"terminalBench":{"avgAttemptCostUsd":23.9824468,"overallScore":0.49438202},"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","enkrypt":{"bias_score":87.08,"cbrn_score":37,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":21.8705,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-26B-A4B-it","nist_score":29,"owasp_score":33,"provider":"openai_compatible","risk_score":28.5312,"robustness_score":null,"safety_score":36.5678,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"google/gemma-4-26b-a4b-it","inference_provider_ids":["akashml","cloudflare","coreweave","darkbloom","deepinfra","dekallm","gmicloud","google-vertex","io-net","makora","nextbit","novita","parasail","primeintellect","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 26B A4B ","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000108","discount":0,"input_cache_read":"0.000000018","prompt":"0.000000036"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Gemma"},"context_length":262144,"created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","enkrypt":{"bias_score":91.47,"cbrn_score":33.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12,"jailbreak_score":19.4245,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-4-31B-it","nist_score":29,"owasp_score":34,"provider":"openai_compatible","risk_score":29.4562,"robustness_score":null,"safety_score":38.5726,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"google/gemma-4-31b-it","inference_provider_ids":["chutes","coreweave","crusoe","deepinfra","friendli","gmicloud","io-net","modal","modelrun","nextbit","novita","parasail","primeintellect","sambanova","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 4 31B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000166","discount":0,"input_cache_read":"0.00000005","prompt":"0.000000099"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","expiration_date":null,"id":"qwen/qwen3.6-plus","inference_provider_ids":["alibaba","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.6 Plus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000195","discount":0,"input_cache_write":"0.00000040625","prompt":"0.000000325"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","expiration_date":null,"id":"z-ai/glm-5v-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5V Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","expiration_date":null,"id":"x-ai/grok-4.20-multi-agent","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20 Multi-Agent","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Grok"},"context_length":2000000,"created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","expiration_date":null,"id":"x-ai/grok-4.20","inference_provider_ids":["xai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"SpaceXAI: Grok 4.20","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"input_cache_read":"0.0000002","prompt":"0.00000125","web_search":"0.005"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":2000000,"is_moderated":false,"max_completion_tokens":1800000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907286,"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","expiration_date":null,"id":"google/lyria-3-pro-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Pro Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text+audio","output_modalities":["text","audio"],"tokenizer":"Other"},"context_length":1048576,"created":1774907255,"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","expiration_date":null,"id":"google/lyria-3-clip-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Lyria 3 Clip Preview","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","discount":0,"prompt":"0"},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","expiration_date":null,"id":"rekaai/reka-edge","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Edge","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","enkrypt":{"bias_score":45.48,"cbrn_score":15,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0.89,"jailbreak_score":2.15827,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2.7","nist_score":13,"owasp_score":15,"provider":"novita","risk_score":13.0815,"robustness_score":null,"safety_score":21.4114,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.82},"expiration_date":"2026-11-05","id":"minimax/minimax-m2.7","inference_provider_ids":["atlas-cloud","gmicloud","groq","minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.7 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001200000","input_cache_read":"0.000000060000","prompt":"0.000000300000"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","expiration_date":null,"id":"openai/gpt-5.4-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","expiration_date":null,"id":"openai/gpt-5.4-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000045","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000075","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","expiration_date":null,"id":"mistralai/mistral-small-2603","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 4","opencode":{"reasoning_options":[{"type":"effort","values":["none","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":202752,"created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","enkrypt":{"bias_score":88.11,"cbrn_score":24,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":11.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":13.6691,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-5-turbo","nist_score":28,"owasp_score":32,"provider":"openrouter","risk_score":27.8652,"robustness_score":null,"safety_score":36.9687,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-5-turbo","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5 Turbo","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000004","input_cache_read":"0.00000024","prompt":"0.0000012"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1048576,"created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","expiration_date":null,"id":"nvidia/nemotron-3-super-120b-a12b","inference_provider_ids":["amazon-bedrock","crusoe","deepinfra","dekallm"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Super","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"variants":{"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":262144}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","expiration_date":null,"id":"bytedance-seed/seed-2.0-lite","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Lite","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","expiration_date":null,"id":"qwen/qwen3.5-9b","inference_provider_ids":["darkbloom","deepinfra","parasail","primeintellect","siliconflow","together"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-9B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000025","prompt":"0.00000017"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","expiration_date":null,"id":"openai/gpt-5.4-pro","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00018","discount":0,"prompt":"0.00003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1050000,"created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","expiration_date":null,"id":"openai/gpt-5.4","inference_provider_ids":["amazon-bedrock","azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.4","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":1050000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","expiration_date":"2026-11-08","id":"inception/mercury-2","inference_provider_ids":["inception"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Inception: Mercury 2 (retires Nov 8)","opencode":{"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":50000}},{"architecture":{"input_modalities":["text","image","video","file","audio","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","expiration_date":null,"id":"google/gemini-3.1-flash-lite-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Flash Lite Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"image":"0.000000125","input_cache_read":"0.0000000125","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000075","prompt":"0.000000125","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","expiration_date":null,"id":"bytedance-seed/seed-2.0-mini","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed-2.0-Mini","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","expiration_date":null,"id":"google/gemini-3.1-flash-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","enkrypt":{"bias_score":73.39,"cbrn_score":26.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":8,"jailbreak_score":13.3813,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-35b-a3b","nist_score":22,"owasp_score":26,"provider":"novita","risk_score":22.3043,"robustness_score":null,"safety_score":30.6335,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.64},"expiration_date":null,"id":"qwen/qwen3.5-35b-a3b","inference_provider_ids":["alibaba","atlas-cloud","darkbloom","deepinfra","parasail","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-35B-A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000013","discount":0,"prompt":"0.0000001625"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","enkrypt":{"bias_score":60.47,"cbrn_score":28.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":1.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":6.22,"jailbreak_score":13.9568,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-27b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.0536,"robustness_score":null,"safety_score":27.7466,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-27b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","novita","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-27B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.000000195"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":81920}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","enkrypt":{"bias_score":59.69,"cbrn_score":29.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":14.1007,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-122b-a10b","nist_score":20,"owasp_score":23,"provider":"novita","risk_score":20.4986,"robustness_score":null,"safety_score":28.2277,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"qwen/qwen3.5-122b-a10b","inference_provider_ids":["alibaba","atlas-cloud","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-122B-A10B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000208","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","expiration_date":null,"id":"qwen/qwen3.5-flash-02-23","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5-Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000026","discount":0,"prompt":"0.000000065"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","audio","image","video","file","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","expiration_date":null,"id":"google/gemini-3.1-pro-preview-customtools","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000012","discount":0,"image":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","expiration_date":null,"id":"openai/gpt-5.3-codex","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.3-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","expiration_date":null,"id":"aion-labs/aion-2.0","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-2.0","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000002","prompt":"0.0000008"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["audio","file","image","text","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","expiration_date":null,"id":"google/gemini-3.1-pro-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3.1 Pro Preview","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","enkrypt":{"bias_score":81.14,"cbrn_score":15.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":0.56,"ingestedAt":"2026-09-29T04:00:25.155Z","insecure_code_score":32.89,"jailbreak_score":null,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"claude-sonnet-4-6","nist_score":32,"owasp_score":39,"provider":"anthropic","risk_score":32.4787,"robustness_score":null,"safety_score":null,"source":"anthropic","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":null},"expiration_date":null,"id":"anthropic/claude-sonnet-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"terminalBench":{"avgAttemptCostUsd":53.374126600000004,"overallScore":0.5505618},"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","expiration_date":null,"id":"qwen/qwen3.5-plus-02-15","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 Plus 2026-02-15","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000156","discount":0,"prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","enkrypt":{"bias_score":49.61,"cbrn_score":24.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":2.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":11.6547,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3.5-397b-a17b","nist_score":17,"owasp_score":19,"provider":"novita","risk_score":17.0427,"robustness_score":null,"safety_score":23.2558,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.55},"expiration_date":null,"id":"qwen/qwen3.5-397b-a17b","inference_provider_ids":["alibaba","atlas-cloud","deepinfra","digitalocean","gmicloud","novita","parasail","phala","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3.5 397B A17B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000234","discount":0,"prompt":"0.00000039"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","expiration_date":null,"id":"minimax/minimax-m2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","digitalocean","gmicloud","minimax","novita","streamlake","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.5","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":198000,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","expiration_date":null,"id":"z-ai/glm-5","inference_provider_ids":["amazon-bedrock","baidu","gmicloud","novita","siliconflow","streamlake","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000032","input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","expiration_date":null,"id":"anthropic/claude-opus-4.6","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.6","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true},"verbosity":"high"},"low":{"reasoning":{"effort":"low","enabled":true},"verbosity":"low"},"max":{"reasoning":{"effort":"max","enabled":true},"verbosity":"max"},"medium":{"reasoning":{"effort":"medium","enabled":true},"verbosity":"medium"},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":262144,"created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","expiration_date":null,"id":"qwen/qwen3-coder-next","inference_provider_ids":["amazon-bedrock","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Next","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000007","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","expiration_date":null,"id":"stepfun/step-3.5-flash","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"StepFun: Step 3.5 Flash","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","enkrypt":{"bias_score":83.72,"cbrn_score":33.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":5.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":5.78,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2.5","nist_score":26,"owasp_score":30,"provider":"novita","risk_score":26.3715,"robustness_score":null,"safety_score":33.8412,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.64},"expiration_date":null,"id":"moonshotai/kimi-k2.5","inference_provider_ids":["amazon-bedrock","atlas-cloud","novita","siliconflow","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","expiration_date":"2026-11-05","id":"minimax/minimax-m2-her","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2-her (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":2048}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1040000,"created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","expiration_date":null,"id":"writer/palmyra-x5","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Writer: Palmyra X5","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"prompt":"0.0000006"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":1040000,"is_moderated":true,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","expiration_date":null,"id":"openai/gpt-audio","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","audio","pdf"],"modality":"text+audio->text+audio","output_modalities":["text","audio"],"tokenizer":"GPT"},"context_length":128000,"created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","expiration_date":null,"id":"openai/gpt-audio-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT Audio Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000024","discount":0,"prompt":"0.0000006"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","expiration_date":null,"id":"z-ai/glm-4.7-flash","inference_provider_ids":["amazon-bedrock","cloudflare","novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.0000000605"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.2-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6-flash","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"prompt":"0.000000075"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","expiration_date":"2026-11-11","id":"bytedance-seed/seed-1.6","inference_provider_ids":["seed"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance Seed: Seed 1.6 (retires Nov 11)","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","expiration_date":"2026-11-05","id":"minimax/minimax-m2.1","inference_provider_ids":["amazon-bedrock","minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2.1 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000012","input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","expiration_date":"2026-12-31","id":"z-ai/glm-4.7","inference_provider_ids":["amazon-bedrock","deepinfra","mancer","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.7","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","expiration_date":null,"id":"google/gemini-3-flash-preview","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 3 Flash Preview","opencode":{"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"image":"0.00000025","input_cache_read":"0.000000025","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000015","prompt":"0.00000025","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","expiration_date":null,"id":"nvidia/nemotron-3-nano-30b-a3b","inference_provider_ids":["deepinfra","nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"input_cache_read":"0.000000012","prompt":"0.00000006"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","expiration_date":null,"id":"openai/gpt-5.2-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000168","discount":0,"prompt":"0.000021","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","enkrypt":{"bias_score":58.4,"cbrn_score":10.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":0,"jailbreak_score":4.02878,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.2","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":16.0341,"robustness_score":null,"safety_score":23.4162,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.27},"expiration_date":null,"id":"openai/gpt-5.2","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.2","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000014","discount":0,"input_cache_read":"0.000000175","prompt":"0.00000175","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","expiration_date":null,"id":"mistralai/devstral-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Devstral 2 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","expiration_date":null,"id":"relace/relace-search","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Search","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"prompt":"0.000001"},"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","video"],"modality":"text+image+video->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","expiration_date":null,"id":"z-ai/glm-4.6v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000009","input_cache_read":"0.000000055","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","expiration_date":null,"id":"openai/gpt-5.1-codex-max","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Max","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"xhigh":{"reasoning":{"effort":"xhigh","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","video","file"],"modality":"text+image+file+video->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","expiration_date":null,"id":"amazon/nova-2-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova 2 Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"prompt":"0.0000003"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","expiration_date":null,"id":"mistralai/ministral-14b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 14B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-8b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 8B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","expiration_date":null,"id":"mistralai/ministral-3b-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Ministral 3 3B 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000001","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":262144,"created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","expiration_date":null,"id":"mistralai/mistral-large-2512","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Large 3 2512","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000015","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":209715}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","expiration_date":null,"id":"deepseek/deepseek-v3.2","inference_provider_ids":["amazon-bedrock","atlas-cloud","baidu","deepinfra","digitalocean","gmicloud","phala","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000038","input_cache_read":"0.00000013","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","expiration_date":null,"id":"anthropic/claude-opus-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000025","discount":0,"input_cache_read":"0.0000005","input_cache_write":"0.00000625","prompt":"0.000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":65536,"created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","expiration_date":null,"id":"google/gemini-3-pro-image-preview","inference_provider_ids":["google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"image":"0.000001","input_cache_read":"0.0000001","input_cache_write":"0.0000001875","internal_reasoning":"0.000006","prompt":"0.000001","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","enkrypt":{"bias_score":56.33,"cbrn_score":6.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":16.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":4,"jailbreak_score":7.19424,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5.1","nist_score":17,"owasp_score":20,"provider":"openai","risk_score":17.4611,"robustness_score":null,"safety_score":21.5718,"source":"","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.36},"expiration_date":null,"id":"openai/gpt-5.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"none":{"reasoning":{"effort":"none","enabled":false}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","expiration_date":null,"id":"openai/gpt-5.1-codex","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","input_cache_read":"0.00000013","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","expiration_date":null,"id":"openai/gpt-5.1-codex-mini","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5.1-Codex-Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.00000003","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","enkrypt":{"bias_score":67.44,"cbrn_score":24.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":19.56,"jailbreak_score":11.6456,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"kimi-k2-thinking","nist_score":28,"owasp_score":31,"provider":"novita","risk_score":28.0702,"robustness_score":null,"safety_score":31.676,"source":"moonshotai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"moonshotai/kimi-k2-thinking","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000025","input_cache_read":"0.00000015","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":1000000,"created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","expiration_date":null,"id":"amazon/nova-premier-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Premier 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000125","discount":0,"input_cache_read":"0.000000625","prompt":"0.0000025"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","expiration_date":null,"id":"perplexity/sonar-pro-search","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro Search","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.018"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},{"architecture":{"input_modalities":["text","audio","file"],"modality":"text+file+audio->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","expiration_date":null,"id":"mistralai/voxtral-small-24b-2507","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Voxtral Small 24B 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","enkrypt":{"bias_score":74.42,"cbrn_score":18,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":17.1223,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-safeguard-20b","nist_score":26,"owasp_score":29,"provider":"groq","risk_score":25.7241,"robustness_score":null,"safety_score":28.6287,"source":"openai","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-oss-safeguard-20b","inference_provider_ids":["amazon-bedrock","groq"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-safeguard-20b","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.0000000375","prompt":"0.000000075"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","enkrypt":{"bias_score":48.06,"cbrn_score":14,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":10.56,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":5.89928,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"minimax-m2","nist_score":18,"owasp_score":21,"provider":"novita","risk_score":17.6387,"robustness_score":null,"safety_score":22.935,"source":"minimax","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.91},"expiration_date":"2026-11-05","id":"minimax/minimax-m2","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M2 (retires Nov 5)","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000102","prompt":"0.000000255"},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":204800,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["file","image","text","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","expiration_date":null,"id":"openai/gpt-5-image-mini","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000025","prompt":"0.0000025","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","expiration_date":null,"id":"anthropic/claude-haiku-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Haiku 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"input_cache_read":"0.0000001","input_cache_write":"0.00000125","prompt":"0.000001","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","expiration_date":null,"id":"qwen/qwen3-vl-8b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","input_cache_read":"0.00000012","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text+image","output_modalities":["image","text"],"tokenizer":"GPT"},"context_length":400000,"created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","expiration_date":null,"id":"openai/gpt-5-image","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Image ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.00001","web_search":"0.01"},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["image","text","pdf"],"modality":"text+image->text+image","output_modalities":["image","text"],"tokenizer":"Gemini"},"context_length":32768,"created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","expiration_date":null,"id":"google/gemini-2.5-flash-image","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","discount":0,"image":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833333333333333","internal_reasoning":"0.0000025","prompt":"0.0000003","web_search":"0.014"},"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Thinking","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","expiration_date":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","inference_provider_ids":["deepinfra","novita","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","expiration_date":null,"id":"openai/gpt-5-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00012","discount":0,"prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":204800,"created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","enkrypt":{"bias_score":87.34,"cbrn_score":25.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":21.33,"jailbreak_score":20.7194,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.6","nist_score":37,"owasp_score":40,"provider":"novita","risk_score":36.7101,"robustness_score":null,"safety_score":40.0962,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.55},"expiration_date":null,"id":"z-ai/glm-4.6","inference_provider_ids":["deepinfra","novita","venice","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.6","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","input_cache_read":"0.0000001","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":202752,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":1000000,"created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","expiration_date":null,"id":"anthropic/claude-sonnet-4.5","inference_provider_ids":["amazon-bedrock","anthropic","azure","claude-on-aws","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Sonnet 4.5","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"input_cache_read":"0.0000003","input_cache_write":"0.00000375","prompt":"0.000003","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":true,"max_completion_tokens":64000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","enkrypt":{"bias_score":77,"cbrn_score":18.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":53.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.22,"jailbreak_score":23.8849,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-v3.2-exp","nist_score":34,"owasp_score":37,"provider":"novita","risk_score":34.5025,"robustness_score":null,"safety_score":32.8789,"source":"deepseek","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"deepseek/deepseek-v3.2-exp","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.2 Exp","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000041","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","expiration_date":null,"id":"thedrummer/cydonia-24b-v4.1","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Cydonia 24B V4.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000005","discount":0,"input_cache_read":"0.00000015","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","expiration_date":null,"id":"relace/relace-apply-3","inference_provider_ids":["relace"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Relace: Relace Apply 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"prompt":"0.00000085"},"supported_parameters":["max_tokens","seed","stop"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","enkrypt":{"bias_score":72.61,"cbrn_score":17.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":29.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":9.78,"jailbreak_score":18.1295,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-vl-235b-a22b-instruct","nist_score":27,"owasp_score":30,"provider":"novita","risk_score":26.9573,"robustness_score":null,"safety_score":29.2702,"source":"qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","inference_provider_ids":["deepinfra","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 VL 235B A22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","input_cache_read":"0.0000001","prompt":"0.00000021"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","expiration_date":null,"id":"deepseek/deepseek-v3.1-terminus","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1 Terminus","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000027"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":1000000,"created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","expiration_date":null,"id":"qwen/qwen3-coder-flash","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder Flash","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000975","discount":0,"input_cache_read":"0.000000039","input_cache_write":"0.00000024375","prompt":"0.000000195"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","expiration_date":null,"id":"qwen/qwen3-next-80b-a3b-instruct","inference_provider_ids":["deepinfra","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Next 80B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","input_cache_read":"0.00000007","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","expiration_date":null,"id":"moonshotai/kimi-k2-0905","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0905","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000025","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":98304}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","expiration_date":null,"id":"nousresearch/hermes-4-405b","inference_provider_ids":["nebius"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Nous: Hermes 4 405B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000003","discount":0,"input_cache_read":"0.0000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","expiration_date":null,"id":"deepseek/deepseek-chat-v3.1","inference_provider_ids":["coreweave","deepinfra","sambanova","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3.1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000095","input_cache_read":"0.00000013","prompt":"0.00000025"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":147456}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","expiration_date":null,"id":"mistralai/mistral-medium-3.1","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3.1","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","expiration_date":"2026-12-31","id":"z-ai/glm-4.5v","inference_provider_ids":["novita","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5V","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000018","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","enkrypt":{"bias_score":40.05,"cbrn_score":7.11,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":2.22,"jailbreak_score":2.07317,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5","nist_score":12,"owasp_score":14,"provider":"openai","risk_score":11.7922,"robustness_score":null,"safety_score":14.389,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.91},"expiration_date":null,"id":"openai/gpt-5","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.000000125","prompt":"0.00000125","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","enkrypt":{"bias_score":58.91,"cbrn_score":3.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.11,"jailbreak_score":2.57576,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-mini","nist_score":16,"owasp_score":19,"provider":"openai","risk_score":15.7763,"robustness_score":null,"safety_score":16.0232,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.8},"expiration_date":null,"id":"openai/gpt-5-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Mini","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.000000025","prompt":"0.00000025","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":400000,"created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","enkrypt":{"bias_score":60.98,"cbrn_score":2,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":7.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":1.85567,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-5-nano","nist_score":15,"owasp_score":18,"provider":"openai","risk_score":14.9257,"robustness_score":null,"safety_score":14.334,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.09},"expiration_date":null,"id":"openai/gpt-5-nano","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-5 Nano","opencode":{"ai_sdk_provider":"openai","reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}},"minimal":{"reasoning":{"effort":"minimal","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"input_cache_read":"0.000000005","prompt":"0.00000005","web_search":"0.01"},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools","verbosity"],"top_provider":{"context_length":400000,"is_moderated":true,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","enkrypt":{"bias_score":60.21,"cbrn_score":13.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":14.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":1.33,"jailbreak_score":18.8679,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-120b","nist_score":20,"owasp_score":22,"provider":"fireworks","risk_score":20.1454,"robustness_score":null,"safety_score":24.8614,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.91},"expiration_date":null,"id":"openai/gpt-oss-120b","inference_provider_ids":["akashml","amazon-bedrock","baseten","cerebras","coreweave","crusoe","deepinfra","dekallm","digitalocean","fireworks","google-vertex","groq","mancer","mara","near-ai","nebius","parasail","phala","primeintellect","sail-research","sambanova","siliconflow","together","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-120b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000000089","discount":0,"input_cache_read":"0.000000022","prompt":"0.000000024"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":131072,"created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","enkrypt":{"bias_score":72.35,"cbrn_score":19,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.56,"jailbreak_score":27.1698,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-oss-20b","nist_score":28,"owasp_score":30,"provider":"fireworks","risk_score":27.6703,"robustness_score":null,"safety_score":31.9778,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":20},"expiration_date":null,"id":"openai/gpt-oss-20b","inference_provider_ids":["akashml","amazon-bedrock","coreweave","darkbloom","deepinfra","dekallm","groq","parasail","primeintellect","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: gpt-oss-20b","opencode":{"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"variants":{"high":{"reasoning":{"effort":"high","enabled":true}},"low":{"reasoning":{"effort":"low","enabled":true}},"medium":{"reasoning":{"effort":"medium","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000009","discount":0,"input_cache_read":"0.000000009","prompt":"0.000000018"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Claude"},"context_length":200000,"created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","expiration_date":null,"id":"anthropic/claude-opus-4.1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Anthropic: Claude Opus 4.1 ($$$$)","opencode":{"ai_sdk_provider":"anthropic","reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000075","input_cache_read":"0.0000015","input_cache_write":"0.00001875","prompt":"0.000015","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":32000}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","expiration_date":null,"id":"mistralai/codestral-2508","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Codestral 2508","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","discount":0,"input_cache_read":"0.00000003","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":256000,"is_moderated":false,"max_completion_tokens":204800}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","expiration_date":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","inference_provider_ids":["amazon-bedrock","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":true,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","expiration_date":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","inference_provider_ids":["dekallm","nebius","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":235929}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","enkrypt":{"bias_score":69.51,"cbrn_score":22.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36.89,"jailbreak_score":17.8333,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"glm-4.5","nist_score":36,"owasp_score":40,"provider":"novita","risk_score":36.1503,"robustness_score":null,"safety_score":36.9792,"source":"zai-org","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.24},"expiration_date":"2026-12-31","id":"z-ai/glm-4.5","inference_provider_ids":["z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","input_cache_read":"0.00000011","prompt":"0.0000006"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","expiration_date":null,"id":"z-ai/glm-4.5-air","inference_provider_ids":["novita","siliconflow","z-ai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Z.ai: GLM 4.5 Air","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000085","input_cache_read":"0.000000025","prompt":"0.00000013"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":128000,"created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Thinking 2507","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000035","prompt":"0.00000045"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","expiration_date":null,"id":"qwen/qwen3-coder","inference_provider_ids":["deepinfra","google-vertex","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 Coder 480B A35B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000001","prompt":"0.0000003"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","expiration_date":null,"id":"bytedance/ui-tars-1.5-7b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ByteDance: UI-TARS 7B ","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":2048}},{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","expiration_date":null,"id":"google/gemini-2.5-flash-lite","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash Lite","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"image":"0.00000005","input_cache_read":"0.000000005","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.0000002","prompt":"0.00000005","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":262144,"created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","expiration_date":null,"id":"qwen/qwen3-235b-a22b-2507","inference_provider_ids":["deepinfra","gmicloud","google-vertex","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 235B A22B Instruct 2507","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","input_cache_read":"0.00000005","prompt":"0.00000014"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","expiration_date":null,"id":"moonshotai/kimi-k2","inference_provider_ids":["novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MoonshotAI: Kimi K2 0711","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000023","prompt":"0.00000057"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":98304}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","expiration_date":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","inference_provider_ids":["venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Venice: Uncensored","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000009","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":131072,"created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","enkrypt":{"bias_score":79.33,"cbrn_score":8.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":58.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":34.67,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Hunyuan-A13B-Instruct","nist_score":37,"owasp_score":42,"provider":"openai_compatible","risk_score":37.4464,"robustness_score":null,"safety_score":25.5309,"source":"tencent","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.18},"expiration_date":null,"id":"tencent/hunyuan-a13b-instruct","inference_provider_ids":["siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Tencent: Hunyuan A13B Instruct","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000057","discount":0,"prompt":"0.00000014"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","expiration_date":null,"id":"morph/morph-v3-large","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000019","discount":0,"prompt":"0.0000009"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":262144,"created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","expiration_date":null,"id":"morph/morph-v3-fast","inference_provider_ids":["morph"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Morph: Morph V3 Fast","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000012","discount":0,"prompt":"0.0000008"},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":131072}},{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":256000,"created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","expiration_date":null,"id":"mistralai/mistral-small-3.2-24b-instruct","inference_provider_ids":["deepinfra","mistral","parasail","venice"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.2 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000003","discount":0,"input_cache_read":"0.00000001","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000000,"created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","expiration_date":null,"id":"minimax/minimax-m1","inference_provider_ids":["minimax","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax M1","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000022","discount":0,"prompt":"0.00000055"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":40000}},{"architecture":{"input_modalities":["file","image","text","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","enkrypt":{"bias_score":75.16,"cbrn_score":15.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":45.37,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.38,"jailbreak_score":27.1429,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-flash","nist_score":32,"owasp_score":35,"provider":"gemini","risk_score":32.0541,"robustness_score":null,"safety_score":32.1138,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":8.52},"expiration_date":null,"id":"google/gemini-2.5-flash","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Flash","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000125","discount":0,"image":"0.00000015","input_cache_read":"0.000000015","input_cache_write":"0.0000000416666666666667","internal_reasoning":"0.00000125","prompt":"0.00000015","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65535}},{"architecture":{"input_modalities":["text","image","file","audio","video","pdf"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","enkrypt":{"bias_score":61.15,"cbrn_score":20.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.63,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":38.46,"jailbreak_score":31.0714,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemini-2.5-pro","nist_score":36,"owasp_score":39,"provider":"gemini","risk_score":35.8097,"robustness_score":null,"safety_score":32.5203,"source":"Google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.98},"expiration_date":null,"id":"google/gemini-2.5-pro","inference_provider_ids":["google-vertex","google-ai-studio"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","file","image","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","expiration_date":null,"id":"openai/o3-pro","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3 Pro ($$$$)","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00008","discount":0,"prompt":"0.00002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},{"architecture":{"input_modalities":["file","image","text","audio","pdf"],"modality":"text+image+file+audio->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":1048576,"created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","expiration_date":null,"id":"google/gemini-2.5-pro-preview","inference_provider_ids":["google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemini 2.5 Pro Preview 06-05","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"image":"0.000000625","input_cache_read":"0.0000000625","input_cache_write":"0.0000001875","internal_reasoning":"0.000005","prompt":"0.000000625","web_search":"0.014"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1048576,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","enkrypt":{"bias_score":74.94,"cbrn_score":53.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":57.78,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":73.78,"jailbreak_score":27.1711,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-r1-0528","nist_score":52,"owasp_score":57,"provider":"fireworks","risk_score":52.4164,"robustness_score":null,"safety_score":24.8069,"source":"accounts","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"deepseek/deepseek-r1-0528","inference_provider_ids":["deepinfra","siliconflow","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: R1 0528","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000215","input_cache_read":"0.00000035","prompt":"0.0000005"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text","image","file"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","expiration_date":null,"id":"mistralai/mistral-medium-3","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Medium 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000002","discount":0,"input_cache_read":"0.00000004","prompt":"0.0000004"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},{"architecture":{"input_modalities":["image","text"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":163840,"created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","expiration_date":null,"id":"meta-llama/llama-guard-4-12b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama Guard 4 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000144","discount":0,"prompt":"0.000000144"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":163840,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","enkrypt":{"bias_score":91.47,"cbrn_score":55.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":61.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":37.33,"jailbreak_score":27.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"qwen3-30b-a3b","nist_score":50,"owasp_score":53,"provider":"fireworks","risk_score":49.6461,"robustness_score":null,"safety_score":24.9517,"source":"Qwen","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.09},"expiration_date":null,"id":"qwen/qwen3-30b-a3b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 30B A3B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000005","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":40960,"created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-14b","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 14B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000024","prompt":"0.00000012"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen3"},"context_length":131072,"created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","expiration_date":null,"id":"qwen/qwen3-32b","inference_provider_ids":["amazon-bedrock","deepinfra","siliconflow","tenstorrent"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen3 32B","opencode":{"reasoning_options":[{"type":"toggle"}],"variants":{"instant":{"reasoning":{"effort":"none","enabled":false}},"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.00000028","prompt":"0.00000008"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":40960,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":200000,"created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","enkrypt":{"bias_score":77,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":6.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":7.11,"jailbreak_score":2.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"o3","nist_score":21,"owasp_score":25,"provider":"openai","risk_score":20.9692,"robustness_score":null,"safety_score":22.249,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"openai/o3","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: o3","opencode":{"ai_sdk_provider":"openai","reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"top_provider":{"context_length":200000,"is_moderated":true,"max_completion_tokens":100000}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","enkrypt":{"bias_score":82.17,"cbrn_score":10,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":25,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.11,"jailbreak_score":7.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1","nist_score":27,"owasp_score":31,"provider":"openai","risk_score":26.7472,"robustness_score":null,"safety_score":22.1525,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":5.45},"expiration_date":null,"id":"openai/gpt-4.1","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"input_cache_read":"0.0000005","prompt":"0.000002","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","enkrypt":{"bias_score":84.5,"cbrn_score":11.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":14.67,"jailbreak_score":10.7895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-mini","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":31.3871,"robustness_score":null,"safety_score":21.4286,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.77},"expiration_date":null,"id":"openai/gpt-4.1-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"input_cache_read":"0.0000001","prompt":"0.0000004","web_search":"0.01"},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":true,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["image","text","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":1047576,"created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","enkrypt":{"bias_score":87.08,"cbrn_score":10.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":40,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":12.44,"jailbreak_score":9.67105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4.1-nano","nist_score":31,"owasp_score":35,"provider":"openai","risk_score":30.7776,"robustness_score":null,"safety_score":21.139,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.86},"expiration_date":null,"id":"openai/gpt-4.1-nano","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4.1 Nano","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000004","input_cache_read":"0.00000003","prompt":"0.0000001","web_search":"0.01"},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":1047576,"is_moderated":false,"max_completion_tokens":942818}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":524288,"created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","expiration_date":null,"id":"meta-llama/llama-4-maverick","inference_provider_ids":["amazon-bedrock","digitalocean","google-vertex","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Maverick","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006525","discount":0,"input_cache_read":"0.00000005","prompt":"0.0000001875"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Llama4"},"context_length":1310720,"created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","expiration_date":null,"id":"meta-llama/llama-4-scout","inference_provider_ids":["amazon-bedrock","deepinfra","google-vertex"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 4 Scout","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":327680,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","expiration_date":null,"id":"deepseek/deepseek-chat-v3-0324","inference_provider_ids":["gmicloud","siliconflow"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3 0324","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000114","input_cache_read":"0.00000011","prompt":"0.00000029"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","expiration_date":null,"id":"mistralai/mistral-small-3.1-24b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3.1 24B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000555","prompt":"0.000000351"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":83.98,"cbrn_score":11.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":51.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":44,"jailbreak_score":10.8553,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-4b-it","nist_score":39,"owasp_score":45,"provider":"openai_compatible","risk_score":39.109,"robustness_score":null,"safety_score":25.5309,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.95},"expiration_date":null,"id":"google/gemma-3-4b-it","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 4B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"input_cache_read":"0.00000002","prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":86.82,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":47.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":31.56,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-12b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.3775,"robustness_score":null,"safety_score":22.6834,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.95},"expiration_date":null,"id":"google/gemma-3-12b-it","inference_provider_ids":["deepinfra","nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000012","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":256000,"created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","expiration_date":null,"id":"cohere/command-a","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command A","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":256000,"is_moderated":true,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":65536,"created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","expiration_date":null,"id":"rekaai/reka-flash-3","inference_provider_ids":["reka"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Reka Flash 3","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.0000002","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":58982}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":131072,"created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","enkrypt":{"bias_score":82.95,"cbrn_score":9.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":43.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":36,"jailbreak_score":7.03947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-3-27b-it","nist_score":35,"owasp_score":40,"provider":"openai_compatible","risk_score":35.0275,"robustness_score":null,"safety_score":23.6486,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2.64},"expiration_date":null,"id":"google/gemma-3-27b-it","inference_provider_ids":["deepinfra","nebius","nextbit","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 3 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000016","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","expiration_date":null,"id":"thedrummer/skyfall-36b-v2","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: Skyfall 36B V2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000008","discount":0,"input_cache_read":"0.00000025","prompt":"0.00000055"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","expiration_date":null,"id":"perplexity/sonar-reasoning-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Reasoning Pro","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":200000,"created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","expiration_date":null,"id":"perplexity/sonar-pro","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Pro","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000015","discount":0,"prompt":"0.000003","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":200000,"is_moderated":false,"max_completion_tokens":8000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":128000,"created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","expiration_date":null,"id":"perplexity/sonar-deep-research","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar Deep Research","opencode":{"reasoning_options":[],"variants":{"thinking":{"reasoning":{"effort":"high","enabled":true}}}},"per_request_limits":null,"pricing":{"completion":"0.000008","discount":0,"internal_reasoning":"0.000003","prompt":"0.000002","web_search":"0.005"},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","expiration_date":null,"id":"mistralai/mistral-saba","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Saba","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.00000002","prompt":"0.0000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":26214}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":32768,"created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","expiration_date":null,"id":"aion-labs/aion-rp-llama-3.1-8b","inference_provider_ids":["aion-labs"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"AionLabs: Aion-RP 1.0 (8B)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000016","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":128000,"created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","expiration_date":null,"id":"qwen/qwen2.5-vl-72b-instruct","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 VL 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","input_cache_read":"0.0000004","prompt":"0.0000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":115200}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":1000000,"created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","expiration_date":null,"id":"qwen/qwen-plus","inference_provider_ids":["alibaba"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen-Plus","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000078","discount":0,"input_cache_read":"0.000000052","input_cache_write":"0.000000325","prompt":"0.00000026"},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":32768}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":32768,"created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","enkrypt":{"bias_score":84.75,"cbrn_score":9.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":54.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":45.78,"jailbreak_score":9.60526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Mistral-Small-24B-Instruct-2501","nist_score":40,"owasp_score":45,"provider":"Together","risk_score":39.5529,"robustness_score":null,"safety_score":24.8552,"source":"Mistral","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":3.45},"expiration_date":null,"id":"mistralai/mistral-small-24b-instruct-2501","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Small 3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000008","prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":127072,"created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","expiration_date":null,"id":"perplexity/sonar","inference_provider_ids":["perplexity"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Perplexity: Sonar","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","discount":0,"prompt":"0.000001","web_search":"0.005"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"top_provider":{"context_length":127072,"is_moderated":false,"max_completion_tokens":114364}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":1000192,"created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","expiration_date":"2026-11-05","id":"minimax/minimax-01","inference_provider_ids":["minimax"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MiniMax: MiniMax-01 (retires Nov 5)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000011","prompt":"0.0000002"},"supported_parameters":["max_tokens","temperature","top_p"],"top_provider":{"context_length":1000192,"is_moderated":false,"max_completion_tokens":900172}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Other"},"context_length":16384,"created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","enkrypt":{"bias_score":83.2,"cbrn_score":5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":3.33,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16,"jailbreak_score":2.17105,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"phi-4","nist_score":22,"owasp_score":28,"provider":"HuggingFace","risk_score":21.6711,"robustness_score":null,"safety_score":18.2915,"source":"Microsoft","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0.82},"expiration_date":null,"id":"microsoft/phi-4","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Microsoft: Phi 4","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000112","discount":0,"prompt":"0.000000056"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":16384,"is_moderated":false,"max_completion_tokens":14745}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"DeepSeek"},"context_length":163840,"created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","enkrypt":{"bias_score":85.27,"cbrn_score":8.83,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":41.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":26.67,"jailbreak_score":9.07895,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"deepseek-chat","nist_score":34,"owasp_score":38,"provider":"deepseek","risk_score":33.7785,"robustness_score":null,"safety_score":25.1931,"source":"deepseek-chat","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.45},"expiration_date":null,"id":"deepseek/deepseek-chat","inference_provider_ids":["deepinfra","streamlake"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"DeepSeek: DeepSeek V3","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000010287","prompt":"0.0000002574"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":16000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","enkrypt":{"bias_score":99.48,"cbrn_score":28.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":55,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":15.56,"jailbreak_score":12.1053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r7b-12-2024","nist_score":41,"owasp_score":44,"provider":"cohere","risk_score":40.632,"robustness_score":null,"safety_score":29.1988,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.45},"expiration_date":null,"id":"cohere/command-r7b-12-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R7B (12-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"prompt":"0.0000000375"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","expiration_date":null,"id":"meta-llama/llama-3.3-70b-instruct","inference_provider_ids":["akashml","amazon-bedrock","cloudflare","coreweave","deepinfra","google-vertex","groq","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.3 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000032","discount":0,"prompt":"0.0000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","expiration_date":null,"id":"amazon/nova-lite-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Lite 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000024","discount":0,"prompt":"0.00000006"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":128000,"created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","expiration_date":null,"id":"amazon/nova-micro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Micro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000014","discount":0,"prompt":"0.000000035"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":5120}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Nova"},"context_length":300000,"created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","expiration_date":null,"id":"amazon/nova-pro-v1","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Amazon: Nova Pro 1.0","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000032","discount":0,"prompt":"0.0000008"},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"top_provider":{"context_length":300000,"is_moderated":true,"max_completion_tokens":5120}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","expiration_date":null,"id":"openai/gpt-4o-2024-11-20","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-11-20)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large-2407","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large 2407","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":104857}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","expiration_date":null,"id":"qwen/qwen-2.5-coder-32b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 Coder 32B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000001","prompt":"0.00000066"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":1024000,"created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","expiration_date":null,"id":"thedrummer/unslopnemo-12b","inference_provider_ids":["parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TheDrummer: UnslopNemo 12B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":1024000,"is_moderated":false,"max_completion_tokens":819200}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","expiration_date":null,"id":"anthracite-org/magnum-v4-72b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Magnum v4 72B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000005","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-7b-instruct","inference_provider_ids":["phala"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen: Qwen2.5 7B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000002","prompt":"0.0000001"},"supported_parameters":["frequency_penalty","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":29491}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":60000,"created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","enkrypt":{"bias_score":95.87,"cbrn_score":11.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":8.89,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":69.78,"jailbreak_score":3.22368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-1B-Instruct","nist_score":37,"owasp_score":48,"provider":"Hugging Face","risk_score":37.4762,"robustness_score":null,"safety_score":28.5232,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.18},"expiration_date":null,"id":"meta-llama/llama-3.2-1b-instruct","inference_provider_ids":["cloudflare"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 1B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000000201","discount":0,"prompt":"0.000000027"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"top_provider":{"context_length":60000,"is_moderated":false,"max_completion_tokens":54000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","enkrypt":{"bias_score":88.89,"cbrn_score":14.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":15,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":68.89,"jailbreak_score":7.96053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.2-3B-Instruct","nist_score":38,"owasp_score":48,"provider":"Hugging Face","risk_score":38.3222,"robustness_score":null,"safety_score":28.4749,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":4.5},"expiration_date":null,"id":"meta-llama/llama-3.2-3b-instruct","inference_provider_ids":["cloudflare","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.2 3B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000033","discount":0,"prompt":"0.00000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":80000,"is_moderated":false,"max_completion_tokens":72000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Qwen"},"context_length":32768,"created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","expiration_date":null,"id":"qwen/qwen-2.5-72b-instruct","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Qwen2.5 72B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000004","prompt":"0.00000036"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":32768,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","expiration_date":null,"id":"cohere/command-r-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"prompt":"0.00000015"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Cohere"},"context_length":128000,"created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","enkrypt":{"bias_score":98.71,"cbrn_score":9.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":60,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":86.67,"jailbreak_score":6.71053,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"command-r-plus-08-2024","nist_score":53,"owasp_score":62,"provider":"cohere","risk_score":52.9355,"robustness_score":null,"safety_score":41.5541,"source":"Cohere","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":10.14},"expiration_date":null,"id":"cohere/command-r-plus-08-2024","inference_provider_ids":["cohere"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Cohere: Command R+ (08-2024)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"prompt":"0.0000025"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":4000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","expiration_date":null,"id":"sao10k/l3.1-euryale-70b","inference_provider_ids":["deepinfra"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000085","discount":0,"prompt":"0.00000085"},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":8192,"created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","expiration_date":null,"id":"sao10k/l3-lunaris-8b","inference_provider_ids":["deepinfra","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Sao10K: Llama 3 8B Lunaris","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000005","discount":0,"prompt":"0.00000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":7372}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","enkrypt":{"bias_score":79.33,"cbrn_score":6.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":32.22,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":10.67,"jailbreak_score":5.19737,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-2024-08-06","nist_score":26,"owasp_score":30,"provider":"openai","risk_score":25.9949,"robustness_score":null,"safety_score":18.4363,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.59},"expiration_date":null,"id":"openai/gpt-4o-2024-08-06","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-08-06)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","expiration_date":null,"id":"meta-llama/llama-3.1-70b-instruct","inference_provider_ids":["amazon-bedrock"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 70B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000072","discount":0,"prompt":"0.00000072"},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"top_provider":{"context_length":131072,"is_moderated":true,"max_completion_tokens":8192}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama3"},"context_length":131072,"created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","enkrypt":{"bias_score":81.65,"cbrn_score":16.17,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":50.67,"jailbreak_score":25.3947,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"Llama-3.1-8B-Instruct","nist_score":38,"owasp_score":44,"provider":"openai_compatible","risk_score":38.2035,"robustness_score":null,"safety_score":25.9653,"source":"meta","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":15.86},"expiration_date":null,"id":"meta-llama/llama-3.1-8b-instruct","inference_provider_ids":["amazon-bedrock","cloudflare","coreweave","deepinfra","groq","novita"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Meta: Llama 3.1 8B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000004","discount":0,"prompt":"0.00000002"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":117964}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":131072,"created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","expiration_date":null,"id":"mistralai/mistral-nemo","inference_provider_ids":["deepinfra","dekallm","io-net","mistral","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mistral Nemo","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000015","discount":0,"input_cache_read":"0.000000015","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":131072,"is_moderated":false,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","enkrypt":{"bias_score":86.3,"cbrn_score":8,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":39.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":18.67,"jailbreak_score":5.85526,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o-mini","nist_score":31,"owasp_score":35,"provider":"OpenAI","risk_score":30.8832,"robustness_score":null,"safety_score":21.7181,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":2},"expiration_date":null,"id":"openai/gpt-4o-mini","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","expiration_date":null,"id":"openai/gpt-4o-mini-2024-07-18","inference_provider_ids":["openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o-mini (2024-07-18)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.0000006","discount":0,"input_cache_read":"0.000000075","prompt":"0.00000015"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Gemini"},"context_length":8192,"created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","enkrypt":{"bias_score":68.22,"cbrn_score":10.33,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.11,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":3.56,"jailbreak_score":6.11842,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gemma-2-27b-it","nist_score":22,"owasp_score":24,"provider":"together","risk_score":21.6434,"robustness_score":null,"safety_score":24.1611,"source":"google","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":0},"expiration_date":null,"id":"google/gemma-2-27b-it","inference_provider_ids":["nextbit"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Google: Gemma 2 27B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000065"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"top_provider":{"context_length":8192,"is_moderated":false,"max_completion_tokens":2048}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","enkrypt":{"bias_score":83.46,"cbrn_score":5.5,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":26.67,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":11.56,"jailbreak_score":3.68421,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4o","nist_score":26,"owasp_score":30,"provider":"OpenAI","risk_score":25.7279,"robustness_score":null,"safety_score":19.5946,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":1.45},"expiration_date":null,"id":"openai/gpt-4o","inference_provider_ids":["azure","openai"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00001","discount":0,"input_cache_read":"0.00000125","prompt":"0.0000025"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":true,"max_completion_tokens":16384}},{"architecture":{"input_modalities":["text","image","file","pdf"],"modality":"text+image+file->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":128000,"created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","expiration_date":null,"id":"openai/gpt-4o-2024-05-13","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4o (2024-05-13)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000015","prompt":"0.000005"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":65536,"created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","expiration_date":null,"id":"mistralai/mixtral-8x22b-instruct","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral: Mixtral 8x22B Instruct","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":65536,"is_moderated":false,"max_completion_tokens":52428}},{"architecture":{"input_modalities":["text","file"],"modality":"text+file->text","output_modalities":["text"],"tokenizer":"Mistral"},"context_length":128000,"created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","expiration_date":null,"id":"mistralai/mistral-large","inference_provider_ids":["mistral"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mistral Large","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.000006","discount":0,"input_cache_read":"0.0000002","prompt":"0.000002"},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"top_provider":{"context_length":128000,"is_moderated":false,"max_completion_tokens":102400}},{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":4095,"created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","expiration_date":null,"id":"openai/gpt-3.5-turbo-0613","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000002","prompt":"0.000001"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":4095,"is_moderated":false,"max_completion_tokens":3685}},{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":16385,"created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","expiration_date":null,"id":"openai/gpt-3.5-turbo-16k","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-3.5 Turbo 16k","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.000004","prompt":"0.000003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":16385,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8000,"created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","expiration_date":null,"id":"mancer/weaver","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Mancer: Weaver (alpha)","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000075","discount":0,"prompt":"0.0000004"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":8000,"is_moderated":false,"max_completion_tokens":6000}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":6144,"created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","expiration_date":null,"id":"undi95/remm-slerp-l2-13b","inference_provider_ids":["mancer"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"ReMM SLERP 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000065","discount":0,"prompt":"0.00000035"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":6144,"is_moderated":false,"max_completion_tokens":5529}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Llama2"},"context_length":8192,"created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","expiration_date":null,"id":"gryphe/mythomax-l2-13b","inference_provider_ids":["mancer","parasail"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"MythoMax 13B","opencode":{},"per_request_limits":null,"pricing":{"completion":"0.00000011","discount":0,"prompt":"0.00000008"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_a","top_k","top_logprobs","top_p"],"top_provider":{"context_length":4096,"is_moderated":false,"max_completion_tokens":3686}},{"architecture":{"input_modalities":["text","pdf"],"modality":"text->text","output_modalities":["text"],"tokenizer":"GPT"},"context_length":8191,"created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","enkrypt":{"bias_score":84.75,"cbrn_score":8.67,"evaluatedAt":null,"evasion_score":null,"freshness":"fresh","harmful_score":19.44,"ingestedAt":"2026-09-04T04:01:19.650Z","insecure_code_score":16.89,"jailbreak_score":4.47368,"lastCheckedAt":"2026-11-04T04:00:23.865Z","model_name":"gpt-4","nist_score":27,"owasp_score":32,"provider":"OpenAI","risk_score":27.3327,"robustness_score":null,"safety_score":25.917,"source":"OpenAI","staleAfter":"2026-11-05T06:00:23.865Z","toxicity_score":6.91},"expiration_date":null,"id":"openai/gpt-4","inference_provider_ids":["azure"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenAI: GPT-4 ($$$$)","opencode":{"ai_sdk_provider":"openai"},"per_request_limits":null,"pricing":{"completion":"0.00006","prompt":"0.00003"},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"top_provider":{"context_length":8191,"is_moderated":false,"max_completion_tokens":4096}},{"architecture":{"input_modalities":["audio","file","image","text","video"],"modality":"text+image+file+audio+video->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790363560,"description":"Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...","expiration_date":null,"id":"typesafe/jev-router","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"TypeSafe: Jev Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1790025947,"description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","expiration_date":null,"id":"nvidia/switchyard","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"NVIDIA: Switchyard","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1784311165,"description":"The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...","expiration_date":null,"id":"openrouter/auto-beta","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router (Beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":1000000,"created":1781371647,"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","expiration_date":null,"id":"openrouter/fusion","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter: Fusion","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":2000000,"created":1776747900,"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...","expiration_date":null,"id":"openrouter/pareto-code","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Pareto Code Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","verbosity"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image"],"modality":"text+image->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":200000,"created":1769917427,"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","expiration_date":null,"id":"openrouter/free","inference_provider_ids":["virtual"],"isFree":true,"mayTrainOnYourPrompts":true,"name":"OpenRouter Free Models Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"0","prompt":"0"},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text"],"modality":"text->text","output_modalities":["text"],"tokenizer":"Router"},"context_length":128000,"created":1764903653,"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","expiration_date":null,"id":"openrouter/bodybuilder","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Body Builder (beta)","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":[],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","audio","file","video"],"modality":"text+image+file+audio+video->text+image","output_modalities":["text","image"],"tokenizer":"Router"},"context_length":2000000,"created":1699401600,"description":"The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...","expiration_date":null,"id":"openrouter/auto","inference_provider_ids":["virtual"],"isFree":false,"mayTrainOnYourPrompts":false,"name":"OpenRouter Auto Router","opencode":{},"per_request_limits":null,"pricing":{"completion":"-1","prompt":"-1"},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","prediction","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p","web_search_options"],"top_provider":{"context_length":null,"is_moderated":false,"max_completion_tokens":null}},{"architecture":{"input_modalities":["text","image","pdf"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-fable-5.1","anthropic/claude-opus-5.5","anthropic/claude-sonnet-5.5","google/gemini-4-argon","meta/muse-wonder","moonshotai/kimi-k3","moonshotai/kimi-k3.1-pro","openai/gpt-6-astra","openai/gpt-6.1-sol","openai/gpt-6.1-terra","x-ai/grok-4.7"]},"context_length":1000000,"created":0,"description":"Highest performance and capability for any task.","id":"kilo-auto/frontier","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Frontier","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":128000}},{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["anthropic/claude-haiku-5.5","deepseek/deepseek-v4.1-flash-1017","mistralai/mistral-large-4-0","moonshotai/kimi-k3","openai/gpt-6-luna","qwen/qwen3.8-flash","qwen/qwen3.8-max-0902","stepfun/step-5-preview","x-ai/grok-4.7","xiaomi/mimo-v2.6-pro","z-ai/glm-5.3","z-ai/glm-5.3-flash"]},"context_length":1000000,"created":0,"description":"Great balance of price and capability.","id":"kilo-auto/balanced","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Balanced","opencode":{},"pricing":{"completion":"-1","image":"0","internal_reasoning":"0","prompt":"-1","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":1000000,"is_moderated":false,"max_completion_tokens":65536}},{"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other"},"autoRouting":{"models":["google/gemma-4-26b-a4b-it"]},"context_length":262144,"created":0,"description":"Automatically routes your request to a small model.","id":"kilo-auto/small","inference_provider_ids":[],"isFree":false,"mayTrainOnYourPrompts":false,"name":"Auto Small","opencode":{},"pricing":{"completion":"0.0000004","image":"0","input_cache_read":"0.000000005","internal_reasoning":"0","prompt":"0.00000005","request":"0","web_search":"0"},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"top_provider":{"context_length":262144,"is_moderated":false,"max_completion_tokens":32768}}]},"dataSha256":"404a077f48df9f0b2e78186190508dbb9f5fdfdab4e7e01ed0d4b8c39c2aa286","failure":null,"fetchedAt":"2026-11-04T21:29:27.556Z","firstFailureAt":null,"fresh":true,"rowCount":381,"status":"fresh","url":"https://api.kilo.ai/api/gateway/models"},"ovh":{"attemptedAt":"2026-11-04T21:29:27.556Z","bodySha256":"df966895c3f9ca1e9ae9f9d7ff6c951eb8ce06f261162702b4fdd27dafa69a10","consecutiveFailures":0,"data":{"data":[{"context_length":262144,"created":1780302734,"id":"Qwen3.6-27B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"}},{"context_length":262144,"created":1779113482,"id":"Qwen3.5-397B-A17B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000425","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000071","request":"0"}},{"context_length":32768,"created":1769078773,"id":"Qwen3Guard-Gen-8B","max_completion_tokens":16384,"object":"model","owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":262144,"created":1776853448,"id":"Qwen3.5-9B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"}},{"context_length":262144,"created":1788356485,"id":"Qwen3.8-27B","max_completion_tokens":262144,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000319","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000047","request":"0"}},{"context_length":32768,"created":1769078772,"id":"Qwen3Guard-Gen-0.6B","max_completion_tokens":16384,"object":"model","owned_by":"qwen3guard","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":131072,"created":1756386145,"id":"gpt-oss-120b","max_completion_tokens":131072,"object":"model","owned_by":"OpenAI","pricing":{"completion":"0.00000047","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000009","request":"0"}},{"context_length":131072,"created":1756386145,"id":"gpt-oss-20b","max_completion_tokens":131072,"object":"model","owned_by":"OpenAI","pricing":{"completion":"0.00000018","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000005","request":"0"}},{"context_length":131072,"created":1743520231,"id":"Meta-Llama-3_3-70B-Instruct","max_completion_tokens":131072,"object":"model","owned_by":"meta-llama","pricing":{"completion":"0.00000074","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000074","request":"0"}},{"context_length":65536,"created":1732101359,"id":"Mistral-Nemo-Instruct-2407","max_completion_tokens":65536,"object":"model","owned_by":"mistralai","pricing":{"completion":"0.00000014","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000014","request":"0"}},{"context_length":32768,"created":1743423983,"id":"Qwen2.5-VL-72B-Instruct","max_completion_tokens":32768,"object":"model","owned_by":"Qwen","pricing":{"completion":"0.00000101","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000101","request":"0"}},{"context_length":131072,"created":1752655627,"id":"Mistral-Small-3.2-24B-Instruct-2506","max_completion_tokens":131072,"object":"model","owned_by":"mistralai","pricing":{"completion":"0.00000031","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.0000001","request":"0"}},{"context_length":8192,"created":1742826442,"id":"bge-multilingual-gemma2","max_completion_tokens":0,"object":"model","owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"}},{"context_length":32768,"created":1774533326,"id":"Qwen3-Embedding-8B","max_completion_tokens":0,"object":"model","owned_by":"Qwen","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000012","request":"0"}},{"context_length":8192,"created":1731944050,"id":"bge-m3","max_completion_tokens":0,"object":"model","owned_by":"BAAI","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0.00000001","request":"0"}},{"context_length":0,"created":1730297598,"id":"stable-diffusion-xl-base-v10","max_completion_tokens":0,"object":"model","owned_by":"stabilityai","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1729515876,"id":"nvr-tts-es-es","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1729515876,"id":"nvr-tts-it-it","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1729515876,"id":"nvr-tts-de-de","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1729515876,"id":"nvr-tts-en-us","max_completion_tokens":0,"object":"model","owned_by":"NVIDIA Riva","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1754992184,"id":"whisper-large-v3-turbo","max_completion_tokens":0,"object":"model","owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}},{"context_length":0,"created":1754992184,"id":"whisper-large-v3","max_completion_tokens":0,"object":"model","owned_by":"OpenAi","pricing":{"completion":"0","currency_unit":"USD","image":"0","input_cache_reads":"0","input_cache_writes":"0","prompt":"0","request":"0"}}],"object":"list"},"dataSha256":"c4818bcdc7428118289ac184e1dc5a2507e81ba5dd526b0fd818ebb6a12d3856","failure":null,"fetchedAt":"2026-11-04T21:29:27.556Z","firstFailureAt":null,"fresh":true,"rowCount":22,"status":"fresh","url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models"},"ovhmeta":{"attemptedAt":"2026-11-04T21:29:27.556Z","bodySha256":"d1c3f6c57986843936dd53712630f3acec0dfe3d614d9397667060b041de9e69","consecutiveFailures":0,"data":[{"available":false,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2025-07-16T08:47:07Z","description":"Building upon Mistral Small 3 (2501), Mistral Small 3.2 (2506) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.\nWith 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.\nThis model is a minor update of Mistral-Small-3.1-24B-Instruct-2503, which is an instruction-finetuned version of: Mistral-Small-3.1-24B-Base-2503.\n","documentation_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Mistral-Small-3.2-24B-Instruct-2506","id":"mistral-small-3-2-24b-instruct-2506","isNew":false,"licence_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["mistralai/Mistral-Small-3.2-24B-Instruct-2506","mistral-small-3.2-24b-instruct-2506"],"api_base_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"Wildbench v2","benchmark_score":65.33},{"benchmark_name":"Arena Hard v2","benchmark_score":43.1},{"benchmark_name":"IF (Internal; accuracy)","benchmark_score":84.78},{"benchmark_name":"Infinite Generations (Internal; Lower is better)","benchmark_score":1.29},{"benchmark_name":"MMLU","benchmark_score":80.5},{"benchmark_name":"MMLU Pro (5-shot CoT)","benchmark_score":69.06},{"benchmark_name":"MATH","benchmark_score":69.42},{"benchmark_name":"GPQA Main (5-shot CoT)","benchmark_score":44.22},{"benchmark_name":"GPQA Diamond (5-shot CoT )","benchmark_score":46.13},{"benchmark_name":"MBPP Plus - Pass@5","benchmark_score":78.33},{"benchmark_name":"HumanEval Plus - Pass@5","benchmark_score":92.9},{"benchmark_name":"SimpleQA (TotalAcc)","benchmark_score":12.1},{"benchmark_name":"MMMU","benchmark_score":62.5},{"benchmark_name":"Mathvista","benchmark_score":67.09},{"benchmark_name":"ChartQA","benchmark_score":87.4},{"benchmark_name":"DocVQA","benchmark_score":94.86},{"benchmark_name":"AI2D","benchmark_score":92.91}],"context":"128k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","vision"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":128,"max_images_per_prompt":10,"max_output_token_k":128,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":24,"quantization":"bf16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Mistral-Small-3.2-24B-Instruct-2506","publishing_information":{"endpoint_publication_date":"30/06/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"04/11/2026","model_publication_date":"20/06/2025","publisher":"mistralai","series":"mistral","source":"huggingface","source_link":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.09,"price_unit":"million_input_tokens"},{"price":0.28,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Mistral-Small-3.2-24B-Instruct-2506","new":false,"openapi_url":"https://mistral-small-3-2-24b-instruct-2506.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Mistral-Small-3.2-24B-Instruct-2506/openapi.json","tags":["Vision"],"version":"v3.1"},{"available":true,"category":"Embeddings","category_v2":"Embeddings","created_at":"2024-11-18T15:34:10Z","description":"The BGE-M3 model, developed by the BAAI and released in early 2024, is a powerful multilingual and multigranular embedding model. It supports texts of varying lengths across over 100 languages and produces dense embeddings optimized for semantic search and retrieval applications.\n","documentation_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/bge-m3","id":"bge-m3","isNew":false,"licence_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["BAAI/bge-m3","BGE-M3"],"api_base_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_mean_ask","benchmark_score":59.54},{"benchmark_name":"default","benchmark_score":59.54}],"context_size":8192,"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["multilingual"]},"model_parameters":{"parameters_type":"embedding","params":{"context_size":8192,"max_batch_size":25,"output_dimension":1024}},"nb_of_billion_parameters":0.567,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/bge-m3","publishing_information":{"endpoint_publication_date":"07/11/2024","knowledge_cutoff":"None","languages":["en"],"licence_name":"MIT","licence_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"27/01/2024","publisher":"BAAI","series":"bge","source":"huggingface","source_link":"https://huggingface.co/BAAI/bge-m3"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":[""],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.01,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"bge-m3","new":false,"openapi_url":"https://bge-m3.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/bge-m3/openapi.json","tags":[],"version":"v1.0"},{"available":true,"category":"Large Language Models (LLM)","category_v2":"Text Generation","created_at":"2025-04-01T15:10:31Z","description":"Llama 3.3 is an instruction-tuned generative language model optimized for multilingual dialogue use cases. It was released by Meta AI on December 6, 2024, and utilizes an advanced transformer architecture and is designed to align with human preferences for helpfulness and safety through supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). The knowledge cutoff for this 70B model is December 31, 2023.\n","documentation_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Meta-Llama-3_3-70B-Instruct","id":"llama-3-3-70b-instruct","isNew":false,"licence_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["meta-llama/Llama-3.3-70B-Instruct","meta-llama-3_3-70b-instruct"],"api_base_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"Meta-Llama-3_3-70B-Instruct","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":48},{"benchmark_name":"default","benchmark_score":44.85}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":70,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Meta-Llama-3_3-70B-Instruct","publishing_information":{"endpoint_publication_date":"20/02/2025","knowledge_cutoff":"31/12/2023","languages":["*"],"licence_name":"Llama 3.3 Community","licence_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"06/12/2024","publisher":"meta-llama","series":"llama","source":"huggingface","source_link":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.67,"price_unit":"million_input_tokens"},{"price":0.67,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Meta-Llama-3_3-70B-Instruct","new":false,"openapi_url":"https://llama-3-3-70b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Meta-Llama-3_3-70B-Instruct/openapi.json","tags":[],"version":"v1.0"},{"available":false,"category":"Embeddings","category_v2":"Embeddings","created_at":"2025-03-24T14:27:22Z","description":"BGE-Multilingual-Gemma2 is a LLM-based multilingual embedding model. It is trained on a diverse range of languages and tasks. BGE-Multilingual-Gemma2 primarily demonstrates the following advancements:\nDiverse training data: The model's training data spans a broad range of languages, including English, Chinese, Japanese, Korean, French, and more.Additionally, the data covers a variety of task types, such as retrieval, classification, and clustering.\nOutstanding performance: The model exhibits state-of-the-art (SOTA) results on multilingual benchmarks like MIRACL, MTEB-pl, and MTEB-fr. It also achieves excellent performance on other major evaluations, including MTEB, C-MTEB and AIR-Bench.\n","documentation_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/bge-multilingual-gemma2","id":"bge-multilingual-gemma2","isNew":false,"licence_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["BAAI/bge-multilingual-gemma2"],"api_base_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_mean_ask","benchmark_score":59.54},{"benchmark_name":"default","benchmark_score":59.54}],"context_size":8192,"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["multilingual"]},"model_parameters":{"parameters_type":"embedding","params":{"context_size":8192,"max_batch_size":25,"output_dimension":3584}},"nb_of_billion_parameters":0.567,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/bge-multilingual-gemma2","publishing_information":{"endpoint_publication_date":"24/03/2025","knowledge_cutoff":"None","languages":["en"],"licence_name":"Gemma","licence_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"21/01/2027","model_publication_date":"29/06/2024","publisher":"BAAI","series":"bge","source":"huggingface","source_link":"https://huggingface.co/BAAI/bge-multilingual-gemma2"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.01,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"bge-multilingual-gemma2","new":false,"openapi_url":"https://bge-multilingual-gemma2.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/bge-multilingual-gemma2/openapi.json","tags":[],"version":"v1.0"},{"available":true,"category":"Reasoning LLM","category_v2":"Text Generation","created_at":"2025-08-28T13:02:25Z","description":"gpt-oss-120b is a cutting-edge model designed for high-level reasoning, instruction-following, and advanced agent capabilities. It excels in versatile use cases, offering powerful performance for both general-purpose and specialized applications.\n","documentation_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-120b","id":"gpt-oss-120b","isNew":false,"licence_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/gpt-oss-120b"],"api_base_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":80.8},{"benchmark_name":"LiveCodeBench","benchmark_score":63.9}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["low","medium","high"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"]},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":117,"quantization":"fp4"},"playground_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-120b","publishing_information":{"endpoint_publication_date":"12/08/2025","knowledge_cutoff":"31/06/2024","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"05/08/2025","publisher":"OpenAI","series":"gpt-oss","source":"huggingface","source_link":"https://huggingface.co/openai/gpt-oss-120b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.08,"price_unit":"million_input_tokens"},{"price":0.4,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"gpt-oss-120b","new":false,"openapi_url":"https://gpt-oss-120b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/gpt-oss-120b/openapi.json","tags":["Reasoning"],"version":"v1"},{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding German speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-de-de","id":"nvr-tts-de-de","isNew":false,"licence_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["de-de"],"output_languages":["de-de"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-de-de","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["de-de"],"licence_name":"Riva license","licence_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-de-de","new":false,"openapi_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-de-de.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"},{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2025-03-31T12:26:23Z","description":"Qwen2.5-VL is a powerful vision-language model, designed for advanced image understanding. It can generate detailed image captions, analyze documents, OCR, detect objects, and answer questions based on visuals, making it useful for AI assistants, RAG and Agents.","documentation_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen2.5-VL-72B-Instruct","id":"qwen-2-5-vl-72b-instruct","isNew":false,"licence_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen2.5-VL-72B-Instruct","qwen2.5-vl-72b-instruct"],"api_base_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"AVG OpenVLM","benchmark_score":76.1},{"benchmark_name":"default","benchmark_score":76.1}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text","image"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["multimodal","vision","text_only_compatible"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":32,"max_images_per_prompt":5,"max_output_token_k":32,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":72,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen2.5-VL-72B-Instruct","publishing_information":{"endpoint_publication_date":"26/03/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Qwen","licence_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"27/01/2025","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.91,"price_unit":"million_input_tokens"},{"price":0.91,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"Qwen2.5-VL-72B-Instruct","new":false,"openapi_url":"https://qwen-2-5-vl-72b-instruct.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen2.5-VL-72B-Instruct/openapi.json","tags":["Vision"],"version":"v2.5"},{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-06-01T08:32:14Z","description":"Qwen3.6-27B is a 27-billion-parameter multimodal causal language model developed by Alibaba's Qwen team, released as an open-weight variant following the February release of the Qwen3.5 series. It is built as an Image-Text-to-Text model.\n","documentation_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.6-27B","id":"qwen-3-6-27b","isNew":true,"licence_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.6-27B","qwen3.6-27b"],"api_base_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":85.2}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":27,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.6-27B","publishing_information":{"endpoint_publication_date":"06/05/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/04/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.6-27B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.4,"price_unit":"million_input_tokens"},{"price":2.7,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.6-27B","new":true,"openapi_url":"https://qwen-3-6-27b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.6-27B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.6"},{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-05-18T14:11:22Z","description":"Qwen3.5-397B-A17B is a highly efficient, reasoning focused MoE (Mixture of Experts) model delivering state-of-the-art performance in language, vision, and multimodal tasks, with strong capabilities in code, reasoning, and real-world adaptability.\n","documentation_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-397B-A17B","id":"qwen-3-5-397b","isNew":true,"licence_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.5-397B-A17B","qwen3.5-397b-a17b","qwen3.5-397b"],"api_base_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":87.8},{"benchmark_name":"IFEval","benchmark_score":92.6},{"benchmark_name":"LiveCodeBench-v6","benchmark_score":83.6},{"benchmark_name":"BFCL-V4","benchmark_score":72.9},{"benchmark_name":"SWE-bench-Verified","benchmark_score":76.4},{"benchmark_name":"MMMU-Pro","benchmark_score":79},{"benchmark_name":"OmniDocBench1.5","benchmark_score":90.8},{"benchmark_name":"OCRBench","benchmark_score":93.1}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["emotion_detection","entity_extraction","multi_language_coding","vision","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":397,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-397B-A17B","publishing_information":{"endpoint_publication_date":"15/05/2026","knowledge_cutoff":"31/09/2025","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/02/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.6,"price_unit":"million_input_tokens"},{"price":3.6,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.5-397B-A17B","new":true,"openapi_url":"https://qwen-3-5-397b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.5-397B-A17B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.5"},{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-04-22T10:24:08Z","description":"Qwen3.5 9B is a highly efficient, reasoning focused model delivering state of the art performance in language, vision, and multimodal tasks, with strong capabilities in code, reasoning, and real-world adaptability.\n","documentation_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-9B","id":"qwen-3-5-9b","isNew":true,"licence_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.5-9B","qwen3.5-9b"],"api_base_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":69}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":9.7,"quantization":"bf16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.5-9B","publishing_information":{"endpoint_publication_date":"15/04/2026","knowledge_cutoff":"31/09/2025","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"15/02/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.5-9B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.1,"price_unit":"million_input_tokens"},{"price":0.15,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.5-9B","new":true,"openapi_url":"https://qwen-3-5-9b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.5-9B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.5"},{"available":true,"category":"LLM Guard","category_v2":"Safety & Moderation","created_at":"2026-01-22T10:46:12Z","description":"Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classification head for real-time safety monitoring during incremental text generation.\n","documentation_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-0.6B","id":"qwen-guard-gen-06b","isNew":false,"licence_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3Guard-Gen-0.6B"],"api_base_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"WildGuardTest","benchmark_score":89.4}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["moderation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":32,"max_output_token_k":16}},"nb_of_billion_parameters":0.6,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-0.6B","publishing_information":{"endpoint_publication_date":"21/01/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"23/09/2025","publisher":"qwen3guard","series":"qwen3guard","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-0.6B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Moderation","Streaming"],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_tokens"},{"price":0,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["beta"]}},"name":"Qwen3Guard-Gen-0.6B","new":false,"openapi_url":"https://qwen-guard-gen-06b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3Guard-Gen-0.6B/openapi.json","tags":["Moderation"],"version":"v3.1"},{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding European Spanish speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-es-es","id":"nvr-tts-es-es","isNew":false,"licence_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["es-es"],"output_languages":["es-es"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-es-es","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["es-es"],"licence_name":"Riva license","licence_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-es-es","new":false,"openapi_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-es-es.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"},{"available":true,"category":"Visual LLM","category_v2":"Text Generation","created_at":"2026-09-02T13:41:25Z","description":"Qwen3.8-27B is a 27-billion-parameter multimodal causal language model developed by Alibaba's Qwen team. It is the most capable generation in the Qwen open-model family, built as a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step agentic tasks through to completion with greater reliability.\n","documentation_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3.8-27B","id":"qwen-3-8-27b","isNew":true,"licence_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3.8-27B","qwen3.8-27b"],"api_base_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"SWE-bench Pro","benchmark_score":61.7},{"benchmark_name":"LiveCodeBench v6","benchmark_score":90.3},{"benchmark_name":"GPQA Diamond","benchmark_score":89.2},{"benchmark_name":"OSWorld-Verified","benchmark_score":84.3}],"context":"262k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text","image"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["none","low","medium","xhigh"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["vision","code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation","multimodal"],"web_search":false},"model_parameters":{"parameters_type":"vlm","params":{"context_size_k":262,"max_images_per_prompt":5,"max_output_token_k":262,"supported_aspect_ratios":["*"]}},"nb_of_billion_parameters":27,"quantization":"fp8"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3.8-27B","publishing_information":{"endpoint_publication_date":"24/08/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/08/2026","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3.8-27B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Vision","Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.4,"price_unit":"million_input_tokens"},{"price":2.7,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3.8-27B","new":true,"openapi_url":"https://qwen-3-8-27b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3.8-27B/openapi.json","tags":["Vision","Reasoning"],"version":"v3.8"},{"available":true,"category":"Embeddings","category_v2":"Embeddings","created_at":"2026-03-26T13:55:26Z","description":"State-of-the-art text embedding model with 100+ language support and customizable dimensional outputs. Perfect for retrieval, classification, and multilingual applications. The flexible output dimensionality lets you optimize for your specific use case, whether you need compact vectors for fast retrieval or high dimensional representations for complex semantic tasks.\n","documentation_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3-Embedding-8B","id":"qwen3-embedding-8b","isNew":true,"licence_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/qwen3_embedding_8b"],"api_base_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"mteb_multilingual_mean_task","benchmark_score":70.58},{"benchmark_name":"mteb_multilingual_mean_task_type","benchmark_score":61.69},{"benchmark_name":"mteb_multilingual_bitext_mining","benchmark_score":80.89},{"benchmark_name":"mteb_multilingual_classification","benchmark_score":74},{"benchmark_name":"mteb_multilingual_clustering","benchmark_score":57.65},{"benchmark_name":"mteb_multilingual_instruction_reranking","benchmark_score":10.06},{"benchmark_name":"mteb_multilingual_multilabel_classification","benchmark_score":28.66},{"benchmark_name":"mteb_multilingual_pair_classification","benchmark_score":86.4},{"benchmark_name":"mteb_multilingual_reranking","benchmark_score":65.63},{"benchmark_name":"mteb_multilingual_retrieval","benchmark_score":70.88},{"benchmark_name":"mteb_multilingual_sts","benchmark_score":81.08}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["embedding_vector"],"reasoning":false,"response_format":[],"streaming":false,"supported_sampling_parameters":[],"use_case_tag":["multilingual"],"web_search":false},"model_parameters":{"parameters_type":"embedding","params":{"context_size":32768,"max_batch_size":25,"output_dimension":4096,"output_dimension_max":4096,"output_dimension_min":32}},"nb_of_billion_parameters":7.6,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3-Embedding-8B","publishing_information":{"endpoint_publication_date":"26/03/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"06/06/2025","publisher":"Qwen","series":"qwen","source":"huggingface","source_link":"https://huggingface.co/Qwen/qwen3_embedding_8b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":[""],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.1,"price_unit":"million_input_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"statuses":["live"]}},"name":"Qwen3-Embedding-8B","new":true,"openapi_url":"https://qwen3-embedding-8b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3-Embedding-8B/openapi.json","tags":[],"version":"v1.0"},{"available":true,"category":"LLM Guard","category_v2":"Safety & Moderation","created_at":"2026-01-22T10:46:13Z","description":"Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety. The series includes models of three sizes (0.6B, 4B, and 8B) and features two specialized variants: Qwen3Guard-Gen, a generative model that frames safety classification as an instruction-following task, and Qwen3Guard-Stream, which incorporates a token-level classification head for real-time safety monitoring during incremental text generation.\n","documentation_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-8B","id":"qwen-guard-gen-8b","isNew":false,"licence_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["Qwen/Qwen3Guard-Gen-8B"],"api_base_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"WildGuardTest","benchmark_score":89.4}],"context":"32k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["text"],"reasoning":false,"response_format":["raw_text"],"streaming":true,"supported_sampling_parameters":["temperature","stop","top_p","seed"],"use_case_tag":["moderation"],"web_search":false},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":32,"max_output_token_k":16}},"nb_of_billion_parameters":8,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/Qwen3Guard-Gen-8B","publishing_information":{"endpoint_publication_date":"21/01/2026","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"23/09/2025","publisher":"qwen3guard","series":"qwen3guard","source":"huggingface","source_link":"https://huggingface.co/Qwen/Qwen3Guard-Gen-8B"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Moderation","Streaming"],"usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_tokens"},{"price":0,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["beta"]}},"name":"Qwen3Guard-Gen-8B","new":false,"openapi_url":"https://qwen-guard-gen-8b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/Qwen3Guard-Gen-8B/openapi.json","tags":["Moderation"],"version":"v3.1"},{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding Italian speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-it-it","id":"nvr-tts-it-it","isNew":false,"licence_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["it-it"],"output_languages":["it-it"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-it-it","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["it-it"],"licence_name":"Riva license","licence_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-it-it","new":false,"openapi_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-it-it.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"},{"available":true,"category":"Image Generation","category_v2":"Image Generation","created_at":"2024-10-30T14:13:18Z","description":"SDXL, developed by Stability AI, is an advanced text-to-image model released in July 2023, offering enhanced image generation capabilities.\n","documentation_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/stable-diffusion-xl-base-v10","id":"stable-diffusion-xl","isNew":false,"licence_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["stabilityai/stable-diffusion-xl-base-1.0"],"api_base_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/api/","benchmark_results":[{"benchmark_name":"Arena-elo","benchmark_score":886},{"benchmark_name":"default","benchmark_score":886}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["image"],"reasoning":false,"response_format":[],"streaming":false,"use_case_tag":["image_generation"]},"model_parameters":{"parameters_type":"image_generation","params":[]},"nb_of_billion_parameters":3.5,"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/stable-diffusion-xl-base-v10","publishing_information":{"endpoint_publication_date":"24/10/2024","knowledge_cutoff":"None","languages":["*"],"licence_name":"OpenRail++","licence_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"25/07/2023","publisher":"stabilityai","series":"stable-diffusion","source":"huggingface","source_link":"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Image Generation"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"per_image"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"stable-diffusion-xl-base-v10","new":false,"openapi_url":"https://stable-diffusion-xl.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/stable-diffusion-xl-base-v10/openapi.json","tags":["Image Generation"],"version":"v1.0"},{"available":true,"category":"Speech To Text","category_v2":"Speech To Text","created_at":"2025-08-12T09:49:44Z","description":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper \"Robust Speech Recognition via Large-Scale Weak Supervision\" by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.\n","documentation_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3","id":"whisper-large-v3","isNew":false,"licence_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/whisper-large-v3"],"api_base_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"whisper-large-v3","benchmark_results":[{"benchmark_name":"Average WER","benchmark_score":7.44},{"benchmark_name":"AMI","benchmark_score":15.95},{"benchmark_name":"Earnings22","benchmark_score":11.29},{"benchmark_name":"Gigaspeech","benchmark_score":10.02},{"benchmark_name":"LS Clean","benchmark_score":2.01},{"benchmark_name":"LS Other","benchmark_score":3.91},{"benchmark_name":"SPGISpeech","benchmark_score":2.94}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["sound"],"output_modality":["text"],"reasoning":false,"response_format":["json","verbose_json","text"],"streaming":false,"use_case_tag":["speech_to_text","diarisation","translation"]},"model_parameters":{"parameters_type":"asr","params":{"input_languages":["*"],"max_audio_duration":10800,"max_audio_duration_unauthenticated":60,"max_audio_size":2048,"max_audio_size_unauthenticated":10,"output_languages":["*"],"supported_formats":["mp3","mp4","aac","m4a","wav","flac","ogg","opus","webm","mpeg","mpga"]}},"nb_of_billion_parameters":1.54,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3","publishing_information":{"endpoint_publication_date":"15/07/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/11/2023","publisher":"OpenAi","series":"Whisper","source":"huggingface","source_link":"https://huggingface.co/openai/whisper-large-v3"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.00004083,"price_unit":"audio_duration_seconds"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"whisper-large-v3","new":false,"openapi_url":"https://whisper-large-v3.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/whisper-large-v3/openapi.json","tags":["Automatic Speech Recognition","Diarisation","Translation"],"version":"v1.0"},{"available":true,"category":"Speech To Text","category_v2":"Speech To Text","created_at":"2025-08-12T09:49:44Z","description":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper \"Robust Speech Recognition via Large-Scale Weak Supervision\" by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.\nWhisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.\n","documentation_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3-turbo","id":"whisper-large-v3-turbo","isNew":false,"licence_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/whisper-large-v3-turbo"],"api_base_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","api_model_name":"whisper-large-v3-turbo","benchmark_results":[{"benchmark_name":"Average WER","benchmark_score":7.83},{"benchmark_name":"AMI","benchmark_score":16.13},{"benchmark_name":"Earnings22","benchmark_score":11.63},{"benchmark_name":"Gigaspeech","benchmark_score":10.14},{"benchmark_name":"LS Clean","benchmark_score":2.1},{"benchmark_name":"LS Other","benchmark_score":4.24},{"benchmark_name":"SPGISpeech","benchmark_score":2.97}],"deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["sound"],"output_modality":["text"],"reasoning":false,"response_format":["json","verbose_json","text"],"streaming":false,"use_case_tag":["speech_to_text"]},"model_parameters":{"parameters_type":"asr","params":{"input_languages":["*"],"max_audio_duration":10800,"max_audio_duration_unauthenticated":60,"max_audio_size":2048,"max_audio_size_unauthenticated":10,"output_languages":["*"],"supported_formats":["mp3","mp4","aac","m4a","wav","flac","ogg","opus","webm","mpeg","mpga"]}},"nb_of_billion_parameters":0.81,"quantization":"fp16"},"playground_url":"https://playground.endpoints.ai.ovh.net/whisper-large-v3-turbo","publishing_information":{"endpoint_publication_date":"15/07/2025","knowledge_cutoff":"None","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"01/09/2024","publisher":"OpenAi","series":"Whisper","source":"huggingface","source_link":"https://huggingface.co/openai/whisper-large-v3-turbo"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0.00001278,"price_unit":"audio_duration_seconds"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"whisper-large-v3-turbo","new":false,"openapi_url":"https://whisper-large-v3-turbo.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/whisper-large-v3-turbo/openapi.json","tags":["Automatic Speech Recognition","Diarisation","Translation"],"version":"v1.0"},{"available":true,"category":"Reasoning LLM","category_v2":"Text Generation","created_at":"2025-08-28T13:02:25Z","description":"gpt-oss-20b delivers strong performance with fast inference and efficient reasoning. Ideal for a wide range of tasks, it offers flexible deployment for developers seeking powerful, customizable AI solutions.\n","documentation_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-20b","id":"gpt-oss-20b","isNew":false,"licence_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["openai/gpt-oss-20b"],"api_base_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/","benchmark_results":[{"benchmark_name":"MMLU-Pro","benchmark_score":73.6},{"benchmark_name":"LiveCodeBench","benchmark_score":72.1}],"context":"131k","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","model_specs":{"capabilities":{"batch":true,"fill_in_the_middle":false,"function_calling":true,"input_modality":["text"],"output_modality":["text"],"reasoning":true,"reasoning_efforts":["low","medium","high"],"response_format":["raw_text","json_object","json_schema"],"streaming":true,"use_case_tag":["code_chat","code_completion","code_explanation","emotion_detection","entity_extraction","multi_language_coding","multilingual","paraphrasing","sentiment_analysis","summarization","text_generation","text_only_compatible","translation"]},"model_parameters":{"parameters_type":"llm","params":{"context_size_k":131,"max_output_token_k":131}},"nb_of_billion_parameters":21,"quantization":"fp4"},"playground_url":"https://playground.endpoints.ai.ovh.net/gpt-oss-20b","publishing_information":{"endpoint_publication_date":"12/08/2025","knowledge_cutoff":"31/06/2024","languages":["*"],"licence_name":"Apache 2.0","licence_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"05/08/2025","publisher":"OpenAI","series":"gpt-oss","source":"huggingface","source_link":"https://huggingface.co/openai/gpt-oss-20b"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","tags":["Reasoning","Streaming"],"usage_information":{"avg_throughtput":2,"avg_throughtput_unit":"empirical","pricing":[{"price":0.04,"price_unit":"million_input_tokens"},{"price":0.15,"price_unit":"million_output_tokens"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"gpt-oss-20b","new":false,"openapi_url":"https://gpt-oss-20b.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/doc/gpt-oss-20b/openapi.json","tags":["Reasoning"],"version":"v1"},{"available":true,"category":"Text To Speech","category_v2":"Text To Speech","created_at":"2024-10-21T13:04:36Z","description":"This NVIDIA TTS model generates natural-sounding American English speech from raw text without requiring additional information.\n","documentation_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/readme","gradio_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-en-us","id":"nvr-tts-en-us","isNew":false,"licence_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/license","metadata":{"aliases":["NVIDIA-RIVA"],"api_base_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/api/v1/","deployment_information":{"datacenters":[{"country_code":"FR"}]},"model_base_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/api/v1","model_specs":{"capabilities":{"batch":false,"fill_in_the_middle":false,"function_calling":false,"input_modality":["text"],"output_modality":["sound"],"reasoning":false,"response_format":["audio"],"streaming":false,"use_case_tag":["text-to-speech","multi-speaker"]},"model_parameters":{"parameters_type":"tts","params":{"input_languages":["en-us"],"output_languages":["en-us"]}},"quantization":"fp32"},"playground_url":"https://playground.endpoints.ai.ovh.net/nvr-tts-en-us","publishing_information":{"endpoint_publication_date":"28/06/2024","knowledge_cutoff":"None","languages":["en-us"],"licence_name":"Riva license","licence_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/license","model_eol_date":"None","model_publication_date":"None","publisher":"NVIDIA Riva","series":"NVIDIA Riva","source":"NVIDIA"},"router_base_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","usage_information":{"avg_throughtput":1,"avg_throughtput_unit":"empirical","pricing":[{"price":0,"price_unit":"million_input_chars"}],"rate_limit":{"rate_limit_api":[{"rate_limit_unit":"req/m","rate_limit_value":400}],"rate_limit_api_anonymous":[{"rate_limit_unit":"req/m","rate_limit_value":2}],"rate_limit_playground":[{"rate_limit_unit":"req/m","rate_limit_value":2}]},"status":"live","statuses":["live"]}},"name":"nvr-tts-en-us","new":false,"openapi_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","router_openapi_url":"https://nvr-tts-en-us.endpoints.kepler.ai.cloud.ovh.net/doc/openapi.json","tags":["Text To Speech","Multi-speaker"],"version":"v1.0"}],"dataSha256":"d1c3f6c57986843936dd53712630f3acec0dfe3d614d9397667060b041de9e69","failure":null,"fetchedAt":"2026-11-04T21:29:27.556Z","firstFailureAt":null,"fresh":true,"rowCount":21,"status":"fresh","url":"https://catalog.endpoints.ai.ovh.net/rest/v1/models_v2"}},"summary":{"kilo":{"absentListingHistoryUnknown":0,"classifier":0,"conflictingPrice":2,"free":11,"freeChat":11,"historical":11,"listed":381,"metadataOnlyNotListed":0,"otherFree":0,"previouslyListedNowAbsent":11,"retired":4,"uncertain":12,"unknownPrice":10},"ovh":{"absentListingHistoryUnknown":0,"classifier":0,"conflictingPrice":0,"free":20,"freeChat":8,"historical":0,"listed":22,"metadataOnlyNotListed":0,"otherFree":12,"previouslyListedNowAbsent":0,"retired":1,"uncertain":1,"unknownPrice":1}}}