{"data":[{"id":"alibaba/ZHIPU/GLM-5.3","created":1787029756,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/ccai-pro","created":1762328688,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/deepseek-v3.2","created":1785378301,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/deepseek-v4-flash","created":1785750126,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/deepseek-v4-flash-0731","created":1785563235,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/deepseek-v4-pro","created":1785750167,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/deepseek-v4-pro-0813","created":1787312621,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/glm-5.1","created":1782217829,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/glm-5.2","created":1782886358,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/glm-5.2-fast-preview","created":1783663475,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/kimi-k2.7-code","created":1784964952,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/kimi-k3","created":1787316025,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qvq-max","created":1760421475,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-audio-3.0-asr-flash","created":1785423064,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-coder-plus","created":1760421602,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-flash","created":1785750213,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-flash-character","created":1775811437,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0","created":1784029058,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0-2026-03-03","created":1784029530,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0-pro","created":1784029370,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0-pro-2026-03-03","created":1784029510,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0-pro-2026-04-22","created":1784029480,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-2.0-pro-2026-06-22","created":1782371883,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-3.0","created":1786606078,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-3.0-pro","created":1786606113,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit","created":1761529733,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit-max","created":1768724594,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit-max-2026-01-16","created":1768725487,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit-plus","created":1763974079,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit-plus-2025-10-30","created":1761810924,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-edit-plus-2025-12-15","created":1765813590,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-max","created":1767096300,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-max-2025-12-30","created":1779934775,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-plus","created":1764768412,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-image-plus-2026-01-09","created":1767939899,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-max","created":1779934703,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-mt-flash","created":1762433201,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-mt-lite","created":1764582262,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-mt-plus","created":1760421630,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-mt-turbo","created":1760421638,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-omni-turbo","created":1770800013,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus","created":1785750376,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-2025-01-25","created":1770026563,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-2025-04-28","created":1770015418,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-2025-07-14","created":1760413462,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-2025-09-11","created":1757646198,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-2025-12-01","created":1770026791,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-character","created":1775811400,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-plus-latest","created":1760421728,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-turbo","created":1770084150,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-vl-max","created":1760413112,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-vl-ocr-2025-11-20","created":1770024610,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen-vl-plus","created":1770083638,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen2-7b-instruct","created":1755780073,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-14b","created":1760411542,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-235b-a22b","created":1760413824,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-235b-a22b-instruct-2507","created":1770024280,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-235b-a22b-thinking-2507","created":1780387777,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-30b-a3b","created":1760413836,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-30b-a3b-instruct-2507","created":1770024970,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-30b-a3b-thinking-2507","created":1760411704,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-32b","created":1770009423,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-8b","created":1770026036,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-asr-flash-2026-02-10","created":1772530169,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-asr-flash-realtime","created":1782367385,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-asr-flash-realtime-2025-10-27","created":1783689838,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-asr-flash-realtime-2026-02-10","created":1782214862,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-480b-a35b-instruct","created":1778725553,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-flash","created":1778725608,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-next","created":1778725660,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-plus","created":1778725691,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-plus-2025-07-22","created":1760413448,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-coder-plus-2025-09-23","created":1761529698,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-livetranslate-flash","created":1764737072,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-livetranslate-flash-2025-12-01","created":1773991661,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-livetranslate-flash-realtime","created":1782992580,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-livetranslate-flash-realtime-2025-09-22","created":1782992727,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-max","created":1782136269,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-max-2025-09-23","created":1761529599,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-max-2026-01-23","created":1769481833,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-max-preview","created":1768287984,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-next-80b-a3b-instruct","created":1770024151,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-next-80b-a3b-thinking","created":1758533476,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-30b-a3b-captioner","created":1761550599,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash","created":1761550502,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash-2025-09-15","created":1761550525,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash-2025-12-01","created":1764590306,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash-realtime","created":1770800271,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash-realtime-2025-09-15","created":1770800291,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-omni-flash-realtime-2025-12-01","created":1770800281,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-s2s-flash-realtime","created":1760422451,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash","created":1767618047,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash-2025-09-18","created":1761550341,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash-2025-11-27","created":1764126017,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash-realtime","created":1770800230,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash-realtime-2025-09-18","created":1770800240,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-flash-realtime-2025-11-27","created":1764125786,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-instruct-flash","created":1770722141,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-instruct-flash-2026-01-26","created":1770722234,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-instruct-flash-realtime","created":1770173445,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-instruct-flash-realtime-2026-01-22","created":1770173511,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vc-2026-01-22","created":1770722334,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vc-realtime-2025-11-27","created":1764126288,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vc-realtime-2026-01-15","created":1768647298,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vd-2026-01-26","created":1770718124,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vd-realtime-2025-12-16","created":1770800217,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-tts-vd-realtime-2026-01-15","created":1770013406,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-235b-a22b-instruct","created":1760412732,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-235b-a22b-thinking","created":1760412724,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-flash","created":1785750518,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-flash-2025-10-15","created":1777534225,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-flash-2026-01-22","created":1777534194,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-plus","created":1777534314,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-plus-2025-09-23","created":1785983877,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3-vl-plus-2025-12-19","created":1777534335,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-122b-a10b","created":1785845568,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-27b","created":1773550369,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-35b-a3b","created":1782135921,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-397b-a17b","created":1786453689,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-flash","created":1785750474,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-flash-2026-02-23","created":1780631532,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-livetranslate-flash-realtime","created":1782992784,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-livetranslate-flash-realtime-2026-05-19","created":1782992822,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-flash","created":1775748281,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-flash-2026-03-15","created":1775748316,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-flash-realtime","created":1780984447,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-flash-realtime-2026-03-15","created":1780984108,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-plus","created":1779438700,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-plus-2026-03-15","created":1779885473,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-plus-realtime","created":1780984950,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-omni-plus-realtime-2026-03-15","created":1780984581,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-plus","created":1786372004,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-plus-2026-02-15","created":1786372035,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.5-plus-2026-04-20","created":1786372017,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-27b","created":1782207240,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-35b-a3b","created":1778725927,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-flash","created":1785750067,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-flash-2026-04-16","created":1779992807,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-max-preview","created":1782136330,"owned_by":"system","modalities":["llm","reasoning"]},{"id":"alibaba/qwen3.6-plus","created":1786372061,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.6-plus-2026-04-02","created":1786372084,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-flash","created":1785750420,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-flash-2026-07-15","created":1785147367,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-max","created":1786420843,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-max-2026-05-17","created":1781491466,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-max-2026-05-20","created":1781491364,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-max-2026-06-08","created":1781073628,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-max-preview","created":1779702409,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-plus","created":1786372099,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-plus-2026-05-26","created":1786372125,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.7-text-embedding","created":1786435205,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.8-2.4t-a95b","created":1786625995,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.8-27b","created":1787143672,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwen3.8-max","created":1786098182,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwq-plus","created":1760421593,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/qwq-plus-2025-03-05","created":1760421663,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/text-embedding-v3","created":1761552197,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/text-embedding-v4","created":1760428930,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/tongyi-tingwu-slp","created":1762328573,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/wan2.7-image","created":1782099945,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/wan2.7-image-pro","created":1782100407,"owned_by":"system","modalities":["unknown"]},{"id":"alibaba/z-image-turbo","created":1766371140,"owned_by":"system","modalities":["unknown"]},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","created":1780790400,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000100000","completion":"0.0000500000"},"owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","created":1760486400,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000010000","completion":"0.0000050000"},"owned_by":"","modalities":["llm","vision"]},{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","created":1763942400,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["llm","vision"]},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","created":1770163200,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["llm","vision"]},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","created":1776124800,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","created":1779926400,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","created":1784851200,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","created":1759104000,"context_length":200000,"max_input_tokens":1000000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000030000","completion":"0.0000150000"},"owned_by":"","modalities":["llm","vision"]},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","created":1771286400,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000030000","completion":"0.0000150000"},"owned_by":"","modalities":["llm","vision"]},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","created":1782691200,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000020000","completion":"0.0000100000"},"owned_by":"","modalities":["llm","vision"]},{"id":"cerebras/gemma-4-31b","owned_by":"Cerebras","modalities":["unknown"]},{"id":"cerebras/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"pricing":{"prompt":"0.0000003500","completion":"0.0000007500"},"owned_by":"Cerebras","modalities":["llm"]},{"id":"deepinfra/Audio8/Audio8-TTS-Preview-0.6b","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/BAAI/bge-base-en-v1.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/BAAI/bge-en-icl","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/BAAI/bge-large-en-v1.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/BAAI/bge-m3","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/BAAI/bge-m3-multi","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/Bria-3.2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/Bria-3.2-vector","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/blur_background","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/erase_foreground","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/expand","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/fibo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/fibo_edit","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Bria/remove_background","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seed-1.8","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seed-2.0-code","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seed-2.0-mini","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seed-2.0-pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seedance-1.5-Pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seedance-2.0","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ByteDance/Seedream-4","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Gryphe/MythoMax-L2-13b","context_length":4096,"max_input_tokens":4096,"max_output_tokens":4096,"pricing":{"prompt":"0.0000004000","completion":"0.0000004000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/MiniMaxAI/MiniMax-M2.7","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/MiniMaxAI/MiniMax-M3","owned_by":"deepinfra","modalities":["llm","vision","reasoning"]},{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000010000","completion":"0.0000010000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000003000","completion":"0.0000003000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Pixverse/Pixverse-6-T2V","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Pixverse/Pixverse-T2V","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Pixverse/Pixverse-T2V-HD","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/PrunaAI/p-image","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/PrunaAI/p-video","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen-Image-Edit","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen-Image-Max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"pricing":{"prompt":"0.0000003600","completion":"0.0000004000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-14B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"pricing":{"prompt":"0.0000001200","completion":"0.0000002400"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"pricing":{"prompt":"0.0000000710","completion":"0.0000001000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-30B-A3B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"pricing":{"prompt":"0.0000000900","completion":"0.0000004500"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-32B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"pricing":{"prompt":"0.0000000800","completion":"0.0000002800"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-ASR-0.6B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-ASR-1.7B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"pricing":{"prompt":"0.0000003000","completion":"0.0000010000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Embedding-0.6B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Embedding-4B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Embedding-8B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Max-Thinking","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"pricing":{"prompt":"0.0000000900","completion":"0.0000011000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-TTS","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-TTS-VoiceDesign","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.5-122B-A10B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.5-27B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.5-35B-A3B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.5-397B-A17B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.5-9B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.6-27B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.6-35B-A3B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.7-Max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.8-2.4T-A95B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.8-27B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Qwen/Qwen3.8-Max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ResembleAI/chatterbox-multilingual","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/ResembleAI/chatterbox-turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"pricing":{"prompt":"0.0000000400","completion":"0.0000000500"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000008500","completion":"0.0000008500"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Wan-AI/Wan2.2-T2V-A14B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Wan-AI/Wan2.6-T2I","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/Wan-AI/Wan2.6-T2V","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5-tts","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5-tts-voicedesign","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-fable-5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-haiku-4-5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-opus-4-7","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-opus-4-8","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-opus-5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-sonnet-4-6","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/anthropic/claude-sonnet-5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-1-Redux-dev","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-1-dev","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-1-schnell","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-1.1-pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-2-dev","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-2-klein-4b","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-2-klein-9b","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-2-max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX-2-pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/black-forest-labs/FLUX.1-Kontext-dev","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/bosonai/HiggsAudioV2.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-R1-0528","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"pricing":{"prompt":"0.0000005000","completion":"0.0000021500"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V3","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"pricing":{"prompt":"0.0000003200","completion":"0.0000008900"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"pricing":{"prompt":"0.0000002000","completion":"0.0000007700"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V3.1","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"pricing":{"prompt":"0.0000002100","completion":"0.0000007900"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V3.2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/embeddinggemma-300m","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-2.5-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":1000000,"pricing":{"prompt":"0.0000003000","completion":"0.0000025000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-2.5-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":1000000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-3-pro-image","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-3.1-flash-lite","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-3.1-pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-3.5-flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemini-3.7-flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-3-12b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000400","completion":"0.0000001300"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-3-27b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000800","completion":"0.0000001600"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-3-4b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000400","completion":"0.0000000800"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-4-26B-A4B-it","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-4-31B-it","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-4-31B-it-Ultra","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-4-31B-it-turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/gemma-4-E4B-it","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/nano-banana-2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/nano-banana-2-lite","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/nano-banana-pro","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/veo-3.1","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/google/veo-3.1-fast","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/hexgrad/Kokoro-82M","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/inclusionAI/Ling-3.0-flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/intfloat/e5-base-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/intfloat/e5-large-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/intfloat/multilingual-e5-large","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/intfloat/multilingual-e5-large-instruct","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/inworld-ai/realtime-tts-1.5-max","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/inworld-ai/realtime-tts-1.5-mini","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/inworld-ai/realtime-tts-2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000001000","completion":"0.0000003200"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1048576,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","context_length":327680,"max_input_tokens":327680,"max_output_tokens":327680,"pricing":{"prompt":"0.0000000800","completion":"0.0000003000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Llama-Guard-4-12B","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"pricing":{"prompt":"0.0000001800","completion":"0.0000001800"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000004000","completion":"0.0000004000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000200","completion":"0.0000000300"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/meta-models/Muse-Glimmer-30B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/microsoft/phi-4","context_length":16384,"max_input_tokens":16384,"max_output_tokens":16384,"pricing":{"prompt":"0.0000000700","completion":"0.0000001400"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000200","completion":"0.0000000400"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"pricing":{"prompt":"0.0000000500","completion":"0.0000000800"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000000750","completion":"0.0000002000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/mistralai/Voxtral-Mini-3B-2507","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/mistralai/Voxtral-Small-24B-2507","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/moonshotai/Kimi-K2.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/moonshotai/Kimi-K2.6","owned_by":"deepinfra","modalities":["llm","vision","reasoning"]},{"id":"deepinfra/moonshotai/Kimi-K2.7-Code","owned_by":"deepinfra","modalities":["llm","vision","reasoning","code"]},{"id":"deepinfra/moonshotai/Kimi-K3","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/Cosmos3-Nano","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/Cosmos3-Super","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","context_length":262144,"max_input_tokens":262144,"pricing":{"prompt":"0.0000000500","completion":"0.0000002000"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/Nemotron-Content-Safety-3.5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/nvidia/llama-nemotron-embed-vl-1b-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000370","completion":"0.0000001700"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/gpt-oss-120b-Turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/gpt-oss-120b-Ultra","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"pricing":{"prompt":"0.0000000300","completion":"0.0000001400"},"owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/whisper-large-v3","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/openai/whisper-large-v3-turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/all-MiniLM-L12-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/all-MiniLM-L6-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/all-mpnet-base-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/clip-ViT-B-32","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/clip-ViT-B-32-multilingual-v1","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/multi-qa-mpnet-base-dot-v1","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sentence-transformers/paraphrase-MiniLM-L6-v2","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/sesame/csm-1b","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/shibing624/text2vec-base-chinese","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/stabilityai/sdxl-turbo","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/stepfun-ai/Step-3.7-Flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/tencent/Hy3","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/thenlper/gte-base","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/thenlper/gte-large","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/thinkingmachines/Inkling","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/thinkingmachines/Inkling-Small","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-4.6","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-4.7","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-4.7-Flash","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-5","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-5.1","owned_by":"deepinfra","modalities":["unknown"]},{"id":"deepinfra/zai-org/GLM-5.2","owned_by":"deepinfra","modalities":["llm","reasoning","code"]},{"id":"grok/grok-4.20-0309-non-reasoning","created":1773014400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-4.20-0309-reasoning","created":1773014400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-4.20-multi-agent-0309","created":1773014400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-4.3","created":1776384000,"owned_by":"xai","modalities":["llm","vision","reasoning"]},{"id":"grok/grok-4.5","created":1782691200,"owned_by":"xai","modalities":["llm","vision","reasoning"]},{"id":"grok/grok-4.6","created":1785974400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-build-0.1","created":1776297600,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-imagine-image","created":1769558400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-imagine-image-2.0","created":1786147200,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-imagine-image-quality","created":1775174400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-imagine-video","created":1769558400,"owned_by":"xai","modalities":["unknown"]},{"id":"grok/grok-imagine-video-1.5","created":1779840000,"owned_by":"xai","modalities":["unknown"]},{"id":"openai/babbage-002","created":1692634615,"owned_by":"system","modalities":["llm"]},{"id":"openai/chat-latest","created":1777704602,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000300000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/chatgpt-image-latest","created":1765925279,"pricing":{"prompt":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/davinci-002","created":1692634301,"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo","created":1677610602,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"pricing":{"prompt":"0.0000005000","completion":"0.0000015000"},"owned_by":"openai","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo-0125","created":1706048358,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"pricing":{"prompt":"0.0000005000","completion":"0.0000015000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo-1106","created":1698959748,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"pricing":{"prompt":"0.0000010000","completion":"0.0000020000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo-16k","created":1683758102,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"pricing":{"prompt":"0.0000030000","completion":"0.0000040000"},"owned_by":"openai-internal","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo-instruct","created":1692901427,"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-3.5-turbo-instruct-0914","created":1694122472,"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-4","created":1687882411,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":4096,"pricing":{"prompt":"0.0000300000","completion":"0.0000600000"},"owned_by":"openai","modalities":["llm","vision"]},{"id":"openai/gpt-4-0613","created":1686588896,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":4096,"pricing":{"prompt":"0.0000300000","completion":"0.0000600000"},"owned_by":"openai","modalities":["llm"]},{"id":"openai/gpt-4-turbo","created":1712361441,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000100000","completion":"0.0000300000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4-turbo-2024-04-09","created":1712601677,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000100000","completion":"0.0000300000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1","created":1744316542,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1-2025-04-14","created":1744315746,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1-mini","created":1744318173,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000004000","completion":"0.0000016000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1-mini-2025-04-14","created":1744317547,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000004000","completion":"0.0000016000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1-nano","created":1744321707,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000001000","completion":"0.0000004000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4.1-nano-2025-04-14","created":1744321025,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"pricing":{"prompt":"0.0000001000","completion":"0.0000004000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o","created":1715367049,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-2024-05-13","created":1715368132,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000050000","completion":"0.0000150000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-2024-08-06","created":1722814719,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-2024-11-20","created":1739331543,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-mini","created":1721172741,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-mini-2024-07-18","created":1721172717,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"system","modalities":["llm","vision"]},{"id":"openai/gpt-4o-mini-search-preview","created":1741391161,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-4o-mini-search-preview-2025-03-11","created":1741390858,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-4o-mini-transcribe","created":1742068596,"context_length":16000,"max_input_tokens":16000,"max_output_tokens":2000,"pricing":{"prompt":"0.0000012500","completion":"0.0000050000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-4o-mini-transcribe-2025-03-20","created":1765610545,"context_length":16000,"max_input_tokens":16000,"max_output_tokens":2000,"pricing":{"prompt":"0.0000012500","completion":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-4o-mini-transcribe-2025-12-15","created":1765610407,"context_length":16000,"max_input_tokens":16000,"max_output_tokens":2000,"pricing":{"prompt":"0.0000012500","completion":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-4o-mini-tts","created":1742403959,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-4o-mini-tts-2025-03-20","created":1765610731,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-4o-mini-tts-2025-12-15","created":1765610837,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-4o-search-preview","created":1771905534,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-4o-search-preview-2025-03-11","created":1771905621,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-4o-transcribe","created":1742068463,"context_length":16000,"max_input_tokens":16000,"max_output_tokens":2000,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-4o-transcribe-diarize","created":1750798887,"context_length":16000,"max_input_tokens":16000,"max_output_tokens":2000,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-5","created":1754425777,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-5-2025-08-07","created":1754075360,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-5-chat-latest","created":1754073306,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-5-codex","created":1757527818,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","code","reasoning"]},{"id":"openai/gpt-5-mini","created":1754425928,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002500","completion":"0.0000020000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-mini-2025-08-07","created":1754425867,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002500","completion":"0.0000020000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-nano","created":1754426384,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000000500","completion":"0.0000004000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-nano-2025-08-07","created":1754426303,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000000500","completion":"0.0000004000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-pro","created":1759469822,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":272000,"pricing":{"prompt":"0.0000150000","completion":"0.0001200000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-pro-2025-10-06","created":1759469707,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":272000,"pricing":{"prompt":"0.0000150000","completion":"0.0001200000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5-search-api","created":1759514629,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-5-search-api-2025-10-14","created":1760043960,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-5.1","created":1762800673,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.1-2025-11-13","created":1762800353,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.1-chat-latest","created":1762547951,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.1-codex","created":1762988221,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision","code","reasoning"]},{"id":"openai/gpt-5.1-codex-max","created":1763671532,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"system","modalities":["llm","vision","code","reasoning"]},{"id":"openai/gpt-5.1-codex-mini","created":1763007109,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002500","completion":"0.0000020000"},"owned_by":"system","modalities":["llm","vision","code","reasoning"]},{"id":"openai/gpt-5.2","created":1765313051,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.2-2025-12-11","created":1765313028,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.2-chat-latest","created":1765344352,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.2-codex","created":1766164985,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.2-pro","created":1765343983,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000210000","completion":"0.0001680000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.2-pro-2025-12-11","created":1765343959,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000210000","completion":"0.0001680000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.3-chat-latest","created":1772236571,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.3-codex","created":1770537915,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000017500","completion":"0.0000140000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4","created":1772691852,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000025000","completion":"0.0000150000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.4-2026-03-05","created":1772654062,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000025000","completion":"0.0000150000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-mini","created":1773451123,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000007500","completion":"0.0000045000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-mini-2026-03-17","created":1773451076,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000007500","completion":"0.0000045000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-nano","created":1773450870,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002000","completion":"0.0000012500"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-nano-2026-03-17","created":1773450837,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002000","completion":"0.0000012500"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-pro","created":1772659601,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000300000","completion":"0.0001800000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.4-pro-2026-03-05","created":1772659657,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000300000","completion":"0.0001800000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.5","created":1776824847,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000300000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.5-2026-04-23","created":1776839241,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000300000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.5-pro","created":1776894349,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000300000","completion":"0.0001800000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.5-pro-2026-04-23","created":1776894470,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000300000","completion":"0.0001800000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-5.6-luna","created":1782228658,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000002000","completion":"0.0000012000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.6-sol","created":1782228018,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000300000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-5.6-terra","created":1782228459,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000020000","completion":"0.0000120000"},"owned_by":"system","modalities":["llm","vision","reasoning"]},{"id":"openai/gpt-audio","created":1756339249,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-audio-1.5","created":1771550885,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-audio-2025-08-28","created":1756256146,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000025000","completion":"0.0000100000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-audio-mini","created":1759512027,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-audio-mini-2025-10-06","created":1759512137,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000"},"owned_by":"system","modalities":["audio"]},{"id":"openai/gpt-audio-mini-2025-12-15","created":1765760008,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai-gpt-image-1","created":1745517030,"pricing":{"prompt":"0.0000050000"},"owned_by":"system","modalities":["image"]},{"id":"openai-gpt-image-1-mini","created":1758845821,"pricing":{"prompt":"0.0000020000"},"owned_by":"system","modalities":["image"]},{"id":"openai-gpt-image-1.5","created":1764030620,"pricing":{"image":"0.0130000000"},"owned_by":"system","modalities":["image"]},{"id":"openai/gpt-image-2","created":1776399795,"pricing":{"prompt":"0.0000050000","completion":"0.0000100000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-image-2-2026-04-21","created":1776399994,"pricing":{"prompt":"0.0000050000","completion":"0.0000100000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-live-transcribe","created":1785168034,"pricing":{},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime","created":1756271701,"context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000040000","completion":"0.0000160000","image":"0.0000050000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-realtime-1.5","created":1771461469,"context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000040000","completion":"0.0000160000","image":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-2","created":1778006032,"context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000040000","completion":"0.0000160000","image":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-2.1","created":1782254687,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"pricing":{"prompt":"0.0000040000","completion":"0.0000240000","image":"0.0000050000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-2.1-mini","created":1782254706,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0.0000008000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-2025-08-28","created":1756271773,"context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000040000","completion":"0.0000160000","image":"0.0000050000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-realtime-mini","created":1759517133,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/gpt-realtime-mini-2025-12-15","created":1765612007,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0.0000008000"},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-translate","created":1777950216,"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-realtime-whisper","created":1778012060,"pricing":{},"owned_by":"system","modalities":["unknown"]},{"id":"openai/gpt-transcribe","created":1785168027,"pricing":{},"owned_by":"system","modalities":["unknown"]},{"id":"openai/o1","created":1734375816,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000150000","completion":"0.0000600000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o1-2024-12-17","created":1734326976,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000150000","completion":"0.0000600000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o1-pro","created":1742251791,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0001500000","completion":"0.0006000000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o1-pro-2025-03-19","created":1742251504,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0001500000","completion":"0.0006000000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3","created":1744225308,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-2025-04-16","created":1744133301,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-deep-research","created":1749840121,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000100000","completion":"0.0000400000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-deep-research-2025-06-26","created":1750865219,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000100000","completion":"0.0000400000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-mini","created":1737146383,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000011000","completion":"0.0000044000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-mini-2025-01-31","created":1738010200,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000011000","completion":"0.0000044000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-pro","created":1748475349,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000200000","completion":"0.0000800000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o3-pro-2025-06-10","created":1749166761,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000200000","completion":"0.0000800000"},"owned_by":"system","modalities":["llm","reasoning"]},{"id":"openai/o4-mini","created":1744225351,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000011000","completion":"0.0000044000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/o4-mini-2025-04-16","created":1744133506,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000011000","completion":"0.0000044000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/o4-mini-deep-research","created":1749685485,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/o4-mini-deep-research-2025-06-26","created":1750866121,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"pricing":{"prompt":"0.0000020000","completion":"0.0000080000"},"owned_by":"system","modalities":["llm"]},{"id":"openai/omni-moderation-2024-09-26","created":1732734466,"owned_by":"system","modalities":["llm"]},{"id":"openai/omni-moderation-latest","created":1731689265,"owned_by":"system","modalities":["llm"]},{"id":"openai/sora-2","created":1759708615,"pricing":{},"owned_by":"system","modalities":["video"]},{"id":"openai/sora-2-pro","created":1759708663,"pricing":{},"owned_by":"system","modalities":["video"]},{"id":"openai/text-embedding-3-large","created":1705953180,"context_length":8191,"max_input_tokens":8191,"pricing":{"prompt":"0.0000001300","completion":"0.0000000000"},"owned_by":"system","modalities":["embedding"]},{"id":"openai/text-embedding-3-small","created":1705948997,"context_length":8191,"max_input_tokens":8191,"pricing":{"prompt":"0.0000000200","completion":"0.0000000000"},"owned_by":"system","modalities":["embedding"]},{"id":"openai/text-embedding-ada-002","created":1671217299,"context_length":8191,"max_input_tokens":8191,"pricing":{"prompt":"0.0000001000","completion":"0.0000000000"},"owned_by":"openai-internal","modalities":["embedding"]},{"id":"openai/tts-1","created":1681940951,"pricing":{},"owned_by":"openai-internal","modalities":["audio"]},{"id":"openai/tts-1-1106","created":1699053241,"pricing":{},"owned_by":"system","modalities":["audio"]},{"id":"openai/tts-1-hd","created":1699046015,"pricing":{},"owned_by":"system","modalities":["audio"]},{"id":"openai/tts-1-hd-1106","created":1699053533,"pricing":{},"owned_by":"system","modalities":["audio"]},{"id":"openai/whisper-1","created":1677532384,"pricing":{},"owned_by":"openai-internal","modalities":["audio"]},{"id":"openrouter/aion-labs/aion-2.0","canonical_slug":"aion-labs/aion-2.0-20260223","name":"AionLabs: Aion-2.0","created":1771881306,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000008","completion":"0.0000016"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/aion-labs/aion-3.0","canonical_slug":"aion-labs/aion-3.0-20260707","name":"AionLabs: Aion-3.0","created":1783443095,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000003","completion":"0.000006"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/aion-labs/aion-3.0-mini","canonical_slug":"aion-labs/aion-3.0-mini-20260707","name":"AionLabs: Aion-3.0-Mini","created":1783443096,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000007","completion":"0.0000014"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/aion-labs/aion-rp-llama-3.1-8b","canonical_slug":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000008","completion":"0.0000016"},"top_provider":{"context_length":32768,"max_completion_tokens":32768},"supported_parameters":["max_tokens","temperature","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/allenai/olmo-3-32b-think","canonical_slug":"allenai/olmo-3-32b-think-20251121","name":"AllenAI: Olmo 3 32B Think","created":1763758276,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000015","completion":"0.0000005"},"top_provider":{"context_length":65536,"max_completion_tokens":65536},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"allenai/Olmo-3-32B-Think","description":"Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/amazon/nova-2-lite-v1","canonical_slug":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","created":1764696672,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+video-\u003etext","tokenizer":"Nova"},"pricing":{"prompt":"0.0000003","completion":"0.0000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/amazon/nova-lite-v1","canonical_slug":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","created":1733437363,"context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Nova"},"pricing":{"prompt":"0.00000006","completion":"0.00000024"},"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/amazon/nova-micro-v1","canonical_slug":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","created":1733437237,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":5120,"architecture":{"modality":"text-\u003etext","tokenizer":"Nova"},"pricing":{"prompt":"0.000000035","completion":"0.00000014"},"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/amazon/nova-premier-v1","canonical_slug":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","created":1761950332,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Nova"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"hugging_face_id":"","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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/amazon/nova-pro-v1","canonical_slug":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","created":1733436303,"context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Nova"},"pricing":{"prompt":"0.0000008","completion":"0.0000032"},"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthracite-org/magnum-v4-72b","canonical_slug":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.000003","completion":"0.000005"},"top_provider":{"context_length":32768,"max_completion_tokens":4096},"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"],"hugging_face_id":"anthracite-org/magnum-v4-72b","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).","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-3-haiku","canonical_slug":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","created":1710288000,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":4096,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.00000025","completion":"0.00000125"},"top_provider":{"context_length":200000,"max_completion_tokens":4096,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","tool_choice","tools","top_k","top_p"],"description":"Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-fable-5","canonical_slug":"anthropic/claude-5-fable-20260609","name":"Anthropic: Claude Fable 5","created":1781007515,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.00001","completion":"0.00005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-fable-5:batch","canonical_slug":"anthropic/claude-5-fable-20260609","name":"Anthropic: Claude Fable 5 (batch)","created":1781007515,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-haiku-4.5","canonical_slug":"anthropic/claude-4.5-haiku-20251001","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000001","completion":"0.000005"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-haiku-4.5:batch","canonical_slug":"anthropic/claude-4.5-haiku-20251001","name":"Anthropic: Claude Haiku 4.5 (batch)","created":1760547638,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000005","completion":"0.0000025"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4","canonical_slug":"anthropic/claude-4-opus-20250522","name":"Anthropic: Claude Opus 4","created":1747931245,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000015","completion":"0.000075"},"top_provider":{"context_length":200000,"max_completion_tokens":32000},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","description":"Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.1","canonical_slug":"anthropic/claude-4.1-opus-20250805","name":"Anthropic: Claude Opus 4.1","created":1754411591,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000015","completion":"0.000075"},"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.1:batch","canonical_slug":"anthropic/claude-4.1-opus-20250805","name":"Anthropic: Claude Opus 4.1 (batch)","created":1754411591,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000075","completion":"0.0000375"},"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.5","canonical_slug":"anthropic/claude-4.5-opus-20251124","name":"Anthropic: Claude Opus 4.5","created":1764010580,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.5:batch","canonical_slug":"anthropic/claude-4.5-opus-20251124","name":"Anthropic: Claude Opus 4.5 (batch)","created":1764010580,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.6","canonical_slug":"anthropic/claude-4.6-opus-20260205","name":"Anthropic: Claude Opus 4.6","created":1770219050,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.6:batch","canonical_slug":"anthropic/claude-4.6-opus-20260205","name":"Anthropic: Claude Opus 4.6 (batch)","created":1770219050,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.7","canonical_slug":"anthropic/claude-4.7-opus-20260416","name":"Anthropic: Claude Opus 4.7","created":1776351100,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.7-fast","canonical_slug":"anthropic/claude-4.7-opus-fast-20260512","name":"Anthropic: Claude Opus 4.7 (Fast)","created":1778613011,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.00003","completion":"0.00015"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"description":"Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.7:batch","canonical_slug":"anthropic/claude-4.7-opus-20260416","name":"Anthropic: Claude Opus 4.7 (batch)","created":1776351100,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.8","canonical_slug":"anthropic/claude-4.8-opus-20260528","name":"Anthropic: Claude Opus 4.8","created":1779905091,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.8-fast","canonical_slug":"anthropic/claude-4.8-opus-fast-20260528","name":"Anthropic: Claude Opus 4.8 (Fast)","created":1779913703,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.00001","completion":"0.00005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-4.8:batch","canonical_slug":"anthropic/claude-4.8-opus-20260528","name":"Anthropic: Claude Opus 4.8 (batch)","created":1779905091,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5-20260723","name":"Claude Opus 5","created":1784912544,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-5-fast","canonical_slug":"anthropic/claude-opus-5-fast-20260723","name":"Claude Opus 5 (Fast)","created":1784912546,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.00001","completion":"0.00005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-opus-5:batch","canonical_slug":"anthropic/claude-opus-5-20260723","name":"Claude Opus 5 (batch)","created":1784912544,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000025","completion":"0.0000125"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-4","canonical_slug":"anthropic/claude-4-sonnet-20250522","name":"Anthropic: Claude Sonnet 4","created":1747930371,"context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","description":"Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-4.5","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":1},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-4.5:batch","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","name":"Anthropic: Claude Sonnet 4.5 (batch)","created":1759161676,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000015","completion":"0.0000075"},"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":1},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-4.6","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-4.6:batch","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","name":"Anthropic: Claude Sonnet 4.6 (batch)","created":1771342990,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.0000015","completion":"0.0000075"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p","verbosity"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5-20260630","name":"Anthropic: Claude Sonnet 5","created":1782843083,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000002","completion":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/anthropic/claude-sonnet-5:batch","canonical_slug":"anthropic/claude-sonnet-5-20260630","name":"Anthropic: Claude Sonnet 5 (batch)","created":1782843083,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Claude"},"pricing":{"prompt":"0.000001","completion":"0.000005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/arcee-ai/trinity-large-thinking","canonical_slug":"arcee-ai/trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","created":1775058318,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000022","completion":"0.00000085"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3,"top_p":0.8},"hugging_face_id":"arcee-ai/Trinity-Large-Thinking","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/arcee-ai/virtuoso-large","canonical_slug":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","created":1746478885,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":64000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000075","completion":"0.0000012"},"top_provider":{"context_length":131072,"max_completion_tokens":64000},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","description":"Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/baidu/ernie-4.5-vl-424b-a47b","canonical_slug":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","created":1751300903,"context_length":123000,"max_input_tokens":123000,"max_output_tokens":16000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000042","completion":"0.00000125"},"top_provider":{"context_length":123000,"max_completion_tokens":16000},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"baidu/ERNIE-4.5-VL-424B-A47B-PT","description":"ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-1.6","canonical_slug":"bytedance-seed/seed-1.6-20250625","name":"ByteDance Seed: Seed 1.6","created":1766504997,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000025","completion":"0.000002"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-1.6-flash","canonical_slug":"bytedance-seed/seed-1.6-flash-20250625","name":"ByteDance Seed: Seed 1.6 Flash","created":1766505011,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000075","completion":"0.0000003"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-2-1-turbo","canonical_slug":"bytedance-seed/seed-2-1-turbo-20260810","name":"ByteDance Seed: Seed 2.1 Turbo","created":1786552176,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000005","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-2.0-code","canonical_slug":"bytedance-seed/seed-2.0-code-20260730","name":"ByteDance Seed: Seed-2.0-Code","created":1786550701,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000005","completion":"0.000003"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-2.0-lite","canonical_slug":"bytedance-seed/seed-2.0-lite-20260309","name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000025","completion":"0.000002"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance-seed/seed-2.0-mini","canonical_slug":"bytedance-seed/seed-2.0-mini-20260224","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000001","completion":"0.0000004"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/bytedance/ui-tars-1.5-7b","canonical_slug":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":2048,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000001","completion":"0.0000002"},"top_provider":{"context_length":128000,"max_completion_tokens":2048},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"hugging_face_id":"ByteDance-Seed/UI-TARS-1.5-7B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition","canonical_slug":"venice/uncensored","name":"Venice: Uncensored","created":1752094966,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000002","completion":"0.0000009"},"top_provider":{"context_length":128000,"max_completion_tokens":8192},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","stop","temperature","top_k","top_p"],"hugging_face_id":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cohere/command-a","canonical_slug":"cohere/command-a-03-2025","name":"Cohere: Command A","created":1741894342,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"hugging_face_id":"CohereForAI/c4ai-command-a-03-2025","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cohere/command-r-08-2024","canonical_slug":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","created":1724976000,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"architecture":{"modality":"text-\u003etext","tokenizer":"Cohere"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cohere/command-r-plus-08-2024","canonical_slug":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","created":1724976000,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"architecture":{"modality":"text-\u003etext","tokenizer":"Cohere"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cohere/command-r7b-12-2024","canonical_slug":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","created":1734158152,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"architecture":{"modality":"text-\u003etext","tokenizer":"Cohere"},"pricing":{"prompt":"0.0000000375","completion":"0.00000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/cohere/north-mini-code:free","canonical_slug":"cohere/north-mini-code-20260617","name":"Cohere: North Mini Code (free)","created":1781723748,"context_length":256000,"architecture":{"modality":"text-\u003etext","tokenizer":"Cohere"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"CohereLabs/North-Mini-Code-1.0","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepcogito/cogito-v2.1-671b","canonical_slug":"deepcogito/cogito-v2.1-671b-20251118","name":"Deep Cogito: Cogito v2.1 671B","created":1763071233,"context_length":128000,"max_input_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000125","completion":"0.00000125"},"top_provider":{"context_length":128000},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","top_k","top_p"],"hugging_face_id":"","description":"Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-chat","canonical_slug":"deepseek/deepseek-chat-v3","name":"DeepSeek: DeepSeek V3","created":1735241320,"context_length":163840,"max_input_tokens":128000,"max_output_tokens":16000,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.0000002574","completion":"0.0000010287"},"top_provider":{"context_length":128000,"max_completion_tokens":16000},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V3","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-chat-v3-0324","canonical_slug":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.00000025","completion":"0.000001"},"top_provider":{"context_length":163840,"max_completion_tokens":163840},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-chat-v3.1","canonical_slug":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"context_length":163840,"max_input_tokens":163840,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000025","completion":"0.00000095"},"top_provider":{"context_length":163840,"max_completion_tokens":32768},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V3.1","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-r1","canonical_slug":"deepseek/deepseek-r1","name":"DeepSeek: R1","created":1737381095,"context_length":64000,"max_input_tokens":64000,"max_output_tokens":16000,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000007","completion":"0.0000025"},"top_provider":{"context_length":64000,"max_completion_tokens":16000},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-R1","description":"DeepSeek R1 is here: 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 in an inference pass....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-r1-0528","canonical_slug":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","created":1748455170,"context_length":163840,"max_input_tokens":163840,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000005","completion":"0.00000215"},"top_provider":{"context_length":163840,"max_completion_tokens":32768},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-r1-distill-llama-70b","canonical_slug":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","created":1737663169,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.0000008","completion":"0.0000008"},"top_provider":{"context_length":8192,"max_completion_tokens":8192},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v3.1-terminus","canonical_slug":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"context_length":163840,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.000001"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v3.2","canonical_slug":"deepseek/deepseek-v3.2-20251201","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"context_length":163840,"max_input_tokens":163840,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.000000269","completion":"0.0000004"},"top_provider":{"context_length":163840,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"deepseek-ai/DeepSeek-V3.2","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v3.2-exp","canonical_slug":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"context_length":163840,"max_input_tokens":163840,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":"0.00000027","completion":"0.00000041"},"top_provider":{"context_length":163840,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash-20260423","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"context_length":1048576,"max_input_tokens":1024000,"max_output_tokens":384000,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.0000000826","completion":"0.0000001652"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","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...","owned_by":"","modalities":["llm","reasoning"]},{"id":"openrouter/deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-20260731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"context_length":1310720,"max_input_tokens":1048576,"max_output_tokens":393216,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.00000008","completion":"0.00000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":384000},"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"],"hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v4-flash-vision-exp","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"context_length":1048576,"architecture":{"modality":"text+image-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.00000022","completion":"0.00000066"},"top_provider":{"context_length":1048576,"max_completion_tokens":384000},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","stop","temperature","tool_choice","tools","top_logprobs","top_p"],"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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro-20260423","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.0000016","completion":"0.0000032"},"top_provider":{"context_length":1048576,"max_completion_tokens":393216},"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"],"default_parameters":{"temperature":1,"top_p":1},"hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","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,...","owned_by":"","modalities":["llm","reasoning"]},{"id":"openrouter/deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-20260813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"context_length":1048576,"max_input_tokens":1048575,"max_output_tokens":384000,"architecture":{"modality":"text-\u003etext","tokenizer":"DeepSeek"},"pricing":{"prompt":"0.000001188","completion":"0.000003564"},"top_provider":{"context_length":1048575},"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"],"default_parameters":{"temperature":1,"top_p":1},"hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro-0813","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/dots-studio/dots-3-note-preview:free","canonical_slug":"dots-studio/dots-3-note-preview-20260813","name":"Dots Studio: Dots3-Note Preview (free)","created":1786680361,"context_length":512000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":512000,"max_completion_tokens":512000},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-flash","canonical_slug":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","created":1750172488,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-flash-image","canonical_slug":"google/gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003"},"top_provider":{"context_length":32768,"max_completion_tokens":8192},"supported_parameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-flash-lite","canonical_slug":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000001","completion":"0.0000004","image":"0.0000001"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-flash-lite:batch","canonical_slug":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite (batch)","created":1753200276,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000005","completion":"0.0000002","image":"0.00000005"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-flash:batch","canonical_slug":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash (batch)","created":1750172488,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-pro","canonical_slug":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","created":1750169544,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-pro-preview","canonical_slug":"google/gemini-2.5-pro-preview-06-05","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-pro-preview-05-06","canonical_slug":"google/gemini-2.5-pro-preview-03-25","name":"Google: Gemini 2.5 Pro Preview 05-06","created":1746578513,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000125","completion":"0.00001","image":"0.00000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":65535},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-2.5-pro:batch","canonical_slug":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro (batch)","created":1750169544,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000000625","completion":"0.000005","image":"0.000000625"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3-flash-preview","canonical_slug":"google/gemini-3-flash-preview-20251217","name":"Google: Gemini 3 Flash Preview","created":1765987078,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000005","completion":"0.000003","image":"0.0000005"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3-flash-preview:batch","canonical_slug":"google/gemini-3-flash-preview-20251217","name":"Google: Gemini 3 Flash Preview (batch)","created":1765987078,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3-pro-image","canonical_slug":"google/gemini-3-pro-image-20260528","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"context_length":131072,"max_input_tokens":65536,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002"},"top_provider":{"context_length":65536,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3-pro-image-preview","canonical_slug":"google/gemini-3-pro-image-preview-20251120","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002"},"top_provider":{"context_length":65536,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-image","canonical_slug":"google/gemini-3.1-flash-image-20260528","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000005","completion":"0.000003"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-image-preview","canonical_slug":"google/gemini-3.1-flash-image-preview-20260226","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000005","completion":"0.000003"},"top_provider":{"context_length":65536,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-lite","canonical_slug":"google/gemini-3.1-flash-lite-20260507","name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-lite-image","canonical_slug":"google/gemini-3.1-flash-lite-image-20260630","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text+image-\u003etext+image","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000025","completion":"0.0000015"},"top_provider":{"context_length":65536,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","temperature","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-lite-preview","canonical_slug":"google/gemini-3.1-flash-lite-preview-20260303","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000025","completion":"0.0000015","image":"0.00000025"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-flash-lite:batch","canonical_slug":"google/gemini-3.1-flash-lite-20260507","name":"Google: Gemini 3.1 Flash Lite (batch)","created":1778168828,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000000125","completion":"0.00000075","image":"0.000000125"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-pro-preview","canonical_slug":"google/gemini-3.1-pro-preview-20260219","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-pro-preview-customtools","canonical_slug":"google/gemini-3.1-pro-preview-customtools-20260219","name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.1-pro-preview:batch","canonical_slug":"google/gemini-3.1-pro-preview-20260219","name":"Google: Gemini 3.1 Pro Preview (batch)","created":1771509627,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000001","completion":"0.000006","image":"0.000001"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.5-flash","canonical_slug":"google/gemini-3.5-flash-20260519","name":"Google: Gemini 3.5 Flash","created":1779193800,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000015","completion":"0.000009","image":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.5-flash-lite","canonical_slug":"google/gemini-3.5-flash-lite-20260721","name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","image":"0.0000003"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.5-flash-lite:batch","canonical_slug":"google/gemini-3.5-flash-lite-20260721","name":"Google: Gemini 3.5 Flash Lite (batch)","created":1784646726,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000015","completion":"0.00000125","image":"0.00000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.5-flash:batch","canonical_slug":"google/gemini-3.5-flash-20260519","name":"Google: Gemini 3.5 Flash (batch)","created":1779193800,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000075","completion":"0.0000045","image":"0.00000075"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.6-flash","canonical_slug":"google/gemini-3.6-flash-20260721","name":"Google: Gemini 3.6 Flash","created":1784646733,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.00000075","completion":"0.00000375","image":"0.00000075"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.6-flash:batch","canonical_slug":"google/gemini-3.6-flash-20260721","name":"Google: Gemini 3.6 Flash (batch)","created":1784646733,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.7-flash","canonical_slug":"google/gemini-3.7-flash-20260813","name":"Google: Gemini 3.7 Flash","created":1786640581,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemini-3.7-flash:batch","canonical_slug":"google/gemini-3.7-flash-20260813","name":"Google: Gemini 3.7 Flash (batch)","created":1786640581,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Gemini"},"pricing":{"prompt":"0.0000001875","completion":"0.0000009375","image":"0.0000001875"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-2-27b-it","canonical_slug":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":2048,"architecture":{"modality":"text-\u003etext","tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000065","completion":"0.00000065"},"top_provider":{"context_length":8192,"max_completion_tokens":2048},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"hugging_face_id":"google/gemma-2-27b-it","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-3-12b-it","canonical_slug":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.00000015"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"google/gemma-3-12b-it","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-3-27b-it","canonical_slug":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000008","completion":"0.00000045"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"google/gemma-3-27b-it","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-3-4b-it","canonical_slug":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":"0.00000005","completion":"0.0000001"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"google/gemma-3-4b-it","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-3n-e4b-it","canonical_slug":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","created":1747776824,"context_length":32768,"max_input_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000006","completion":"0.00000012"},"top_provider":{"context_length":32768},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","stop","structured_outputs","temperature","top_k","top_p"],"hugging_face_id":"google/gemma-3n-E4B-it","description":"Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-4-26b-a4b-it","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","name":"Google: Gemma 4 26B A4B ","created":1775227989,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Gemma"},"pricing":{"prompt":"0.00000007","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"google/gemma-4-26B-A4B-it","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-4-26b-a4b-it:free","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","name":"Google: Gemma 4 26B A4B  (free)","created":1775227989,"context_length":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Gemma"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"google/gemma-4-26B-A4B-it","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it-20260402","name":"Google: Gemma 4 31B","created":1775148486,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Gemma"},"pricing":{"prompt":"0.0000001","completion":"0.00000034"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"google/gemma-4-31B-it","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/gemma-4-31b-it:free","canonical_slug":"google/gemma-4-31b-it-20260402","name":"Google: Gemma 4 31B (free)","created":1775148486,"context_length":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Gemma"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"google/gemma-4-31B-it","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/lyria-3-clip-preview","canonical_slug":"google/lyria-3-clip-preview-20260330","name":"Google: Lyria 3 Clip Preview","created":1774907255,"context_length":1048576,"architecture":{"modality":"text+image-\u003etext+audio","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/google/lyria-3-pro-preview","canonical_slug":"google/lyria-3-pro-preview-20260330","name":"Google: Lyria 3 Pro Preview","created":1774907286,"context_length":1048576,"architecture":{"modality":"text+image-\u003etext+audio","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["max_tokens","response_format","seed","temperature","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/gryphe/mythomax-l2-13b","canonical_slug":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","created":1688256000,"context_length":8192,"max_input_tokens":4096,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000006","completion":"0.00000006"},"top_provider":{"context_length":4096,"max_completion_tokens":4096},"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"],"hugging_face_id":"Gryphe/MythoMax-L2-13b","description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","owned_by":"","modalities":["unknown"]},{"id":"openrouter/ibm-granite/granite-4.0-h-micro","canonical_slug":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","created":1760927695,"context_length":131000,"max_input_tokens":131000,"max_output_tokens":131000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000017","completion":"0.000000112"},"top_provider":{"context_length":131000,"max_completion_tokens":131000},"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"],"hugging_face_id":"ibm-granite/granite-4.0-h-micro","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/ibm-granite/granite-4.1-8b","canonical_slug":"ibm-granite/granite-4.1-8b-20260429","name":"IBM: Granite 4.1 8B","created":1777577071,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000005","completion":"0.0000001"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"ibm-granite/granite-4.1-8b","description":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/inception/mercury-2","canonical_slug":"inception/mercury-2-20260304","name":"Inception: Mercury 2","created":1772636275,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":50000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000025","completion":"0.00000075"},"top_provider":{"context_length":128000,"max_completion_tokens":50000},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{"temperature":0.75},"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/inclusionai/ling-2.6-1t","canonical_slug":"inclusionai/ling-2.6-1t-20260423","name":"inclusionAI: Ling-2.6-1T","created":1776948238,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000075","completion":"0.000000625"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"description":"Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/inclusionai/ling-2.6-flash","canonical_slug":"inclusionai/ling-2.6-flash-20260421","name":"inclusionAI: Ling-2.6-flash","created":1776795886,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000001","completion":"0.00000003"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"","description":"Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....","owned_by":"","modalities":["llm"]},{"id":"openrouter/inclusionai/ling-3.0-flash","canonical_slug":"inclusionai/ling-3.0-flash-20260723","name":"Ling-3.0-flash","created":1784818580,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000021","completion":"0.000000063"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"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"],"hugging_face_id":"inclusionAI/Ling-3.0-flash","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/inclusionai/ring-2.6-1t","canonical_slug":"inclusionai/ring-2.6-1t-20260508","name":"inclusionAI: Ring-2.6-1T","created":1778247440,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000075","completion":"0.000000625"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"description":"Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/kwaipilot/kat-coder-air-v2.5","canonical_slug":"kwaipilot/kat-coder-air-v2.5-20260710","name":"Kwaipilot: KAT-Coder-Air V2.5","created":1783714590,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":80000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":256000,"max_completion_tokens":80000},"supported_parameters":["logprobs","max_tokens","presence_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/kwaipilot/kat-coder-pro-v2","canonical_slug":"kwaipilot/kat-coder-pro-v2-20260327","name":"Kwaipilot: KAT-Coder-Pro V2","created":1774649310,"context_length":262144,"max_input_tokens":256000,"max_output_tokens":80000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":256000,"max_completion_tokens":80000},"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"],"hugging_face_id":"","description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/kwaipilot/kat-coder-pro-v2.5","canonical_slug":"kwaipilot/kat-coder-pro-v2.5-20260710","name":"Kwaipilot: KAT-Coder-Pro V2.5","created":1783714589,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":80000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000074","completion":"0.00000296"},"top_provider":{"context_length":256000,"max_completion_tokens":80000},"supported_parameters":["logprobs","max_tokens","presence_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/liquid/lfm-2.5-2.6b:free","canonical_slug":"liquid/lfm-2.5-2.6b-20260811","name":"LiquidAI: LFM2.5-2.6B (free)","created":1786470519,"context_length":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":65536,"max_completion_tokens":8192},"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"],"default_parameters":{"temperature":0.1},"hugging_face_id":"LiquidAI/LFM2.5-2.6B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mancer/weaver","canonical_slug":"mancer/weaver","name":"Mancer: Weaver (alpha)","created":1690934400,"context_length":8000,"max_input_tokens":8000,"max_output_tokens":6000,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.0000005","completion":"0.00000075"},"top_provider":{"context_length":8000,"max_completion_tokens":6000},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meituan/longcat-2.0","canonical_slug":"meituan/longcat-2.0-20260720","name":"Meituan: LongCat 2.0","created":1784554658,"context_length":1048756,"max_input_tokens":1048756,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":1048756,"max_completion_tokens":262144},"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"],"hugging_face_id":"meituan-longcat/LongCat-2.0","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-3.1-70b-instruct","canonical_slug":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.0000004","completion":"0.0000004"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"meta-llama/Meta-Llama-3.1-70B-Instruct","description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes \u0026 flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-3.1-8b-instruct","canonical_slug":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000005","completion":"0.00000008"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"meta-llama/Meta-Llama-3.1-8B-Instruct","description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes \u0026 flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-3.2-1b-instruct","canonical_slug":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","created":1727222400,"context_length":60000,"max_input_tokens":60000,"max_output_tokens":60000,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.000000027","completion":"0.000000201"},"top_provider":{"context_length":60000,"max_completion_tokens":60000},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-3.2-3b-instruct","canonical_slug":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","created":1727222400,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000005","completion":"0.00000033"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-3.3-70b-instruct","canonical_slug":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.0000001","completion":"0.00000032"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-4-maverick","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","name":"Meta: Llama 4 Maverick","created":1743881822,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Llama4"},"pricing":{"prompt":"0.0000002","completion":"0.0000008"},"top_provider":{"context_length":1048576,"max_completion_tokens":16384},"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"],"hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-4-scout","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","name":"Meta: Llama 4 Scout","created":1743881519,"context_length":1310720,"max_input_tokens":327680,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Llama4"},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":327680,"max_completion_tokens":16384},"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"],"hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta-llama/llama-guard-4-12b","canonical_slug":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","created":1745975193,"context_length":1048576,"max_input_tokens":163840,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000018","completion":"0.00000018"},"top_provider":{"context_length":163840,"max_completion_tokens":16384},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"meta-llama/Llama-Guard-4-12B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta/muse-glimmer-30b","canonical_slug":"meta/muse-glimmer-30b-20260810","name":"Meta: Muse Glimmer 30B","created":1786302394,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000011"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"meta-models/Muse-Glimmer-30B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta/muse-spark-1.1","canonical_slug":"meta/muse-spark-1.1-20260709","name":"Meta: Muse Spark 1.1","created":1784215741,"context_length":1048576,"max_input_tokens":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000125","completion":"0.00000425"},"top_provider":{"context_length":1048576,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/meta/muse-spark-1.2","canonical_slug":"meta/muse-spark-1.2-20260805","name":"Meta: Muse Spark 1.2","created":1785959287,"context_length":1048576,"max_input_tokens":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000125","completion":"0.00000425"},"top_provider":{"context_length":1048576,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","repetition_penalty","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/microsoft/phi-4","canonical_slug":"microsoft/phi-4","name":"Microsoft: Phi 4","created":1736489872,"context_length":16384,"max_input_tokens":16384,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000007","completion":"0.00000014"},"top_provider":{"context_length":16384,"max_completion_tokens":16384},"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"],"hugging_face_id":"microsoft/phi-4","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/microsoft/wizardlm-2-8x22b","canonical_slug":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","created":1713225600,"context_length":65535,"max_input_tokens":65535,"max_output_tokens":8000,"architecture":{"modality":"text-\u003etext","tokenizer":"Mistral","instruct_type":"vicuna"},"pricing":{"prompt":"0.00000062","completion":"0.00000062"},"top_provider":{"context_length":65535,"max_completion_tokens":8000},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"microsoft/WizardLM-2-8x22B","description":"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-01","canonical_slug":"minimax/minimax-01","name":"MiniMax: MiniMax-01","created":1736915462,"context_length":1000192,"max_input_tokens":1000192,"max_output_tokens":1000192,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000002","completion":"0.0000011"},"top_provider":{"context_length":1000192,"max_completion_tokens":1000192},"supported_parameters":["max_tokens","temperature","top_p"],"hugging_face_id":"MiniMaxAI/MiniMax-Text-01","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m1","canonical_slug":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","created":1750200414,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":40000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":1000000,"max_completion_tokens":40000},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m2","canonical_slug":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","created":1761252093,"context_length":204800,"max_input_tokens":204800,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000255","completion":"0.00000102"},"top_provider":{"context_length":204800,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"MiniMaxAI/MiniMax-M2","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m2-her","canonical_slug":"minimax/minimax-m2-her-20260123","name":"MiniMax: MiniMax M2-her","created":1769177239,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":2048,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":65536,"max_completion_tokens":2048},"supported_parameters":["max_tokens","temperature","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m2.1","canonical_slug":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","created":1766454997,"context_length":204800,"max_input_tokens":204800,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":204800,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.9},"hugging_face_id":"MiniMaxAI/MiniMax-M2.1","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m2.5","canonical_slug":"minimax/minimax-m2.5-20260211","name":"MiniMax: MiniMax M2.5","created":1770908502,"context_length":204800,"max_input_tokens":198000,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000027","completion":"0.00000095"},"top_provider":{"context_length":198000,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"MiniMaxAI/MiniMax-M2.5","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m2.7","canonical_slug":"minimax/minimax-m2.7-20260318","name":"MiniMax: MiniMax M2.7","created":1773836697,"context_length":204800,"max_input_tokens":204800,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":204800,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"MiniMaxAI/MiniMax-M2.7","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m3","canonical_slug":"minimax/minimax-m3-20260531","name":"MiniMax: MiniMax M3","created":1780245374,"context_length":1048576,"max_input_tokens":524288,"max_output_tokens":512000,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":524288,"max_completion_tokens":512000},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"MiniMaxAI/Minimax-M3","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/minimax/minimax-m3:batch","canonical_slug":"minimax/minimax-m3-20260531","name":"MiniMax: MiniMax M3 (batch)","created":1780245374,"context_length":524288,"max_input_tokens":524288,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000012"},"top_provider":{"context_length":524288},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"MiniMaxAI/Minimax-M3","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/codestral-2508","canonical_slug":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","created":1754079630,"context_length":256000,"max_input_tokens":256000,"architecture":{"modality":"text+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000003","completion":"0.0000009"},"top_provider":{"context_length":256000},"supported_parameters":["frequency_penalty","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"","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)","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/ministral-14b-2512","canonical_slug":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000002","completion":"0.0000002"},"top_provider":{"context_length":262144},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Ministral-3-14B-Instruct-2512","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/ministral-3b-2512","canonical_slug":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000001","completion":"0.0000001"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Ministral-3-3B-Instruct-2512","description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/ministral-8b","canonical_slug":"mistralai/ministral-8b","name":"Mistral: Ministral 8B","created":1729123200,"context_length":128000,"max_input_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.00000011","completion":"0.00000011"},"top_provider":{"context_length":128000},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_p"],"default_parameters":{"temperature":0.3},"description":"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/ministral-8b-2512","canonical_slug":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.00000015","completion":"0.00000015"},"top_provider":{"context_length":262144},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Ministral-3-8B-Instruct-2512","description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-large","canonical_slug":"mistralai/mistral-large","name":"Mistral Large","created":1708905600,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":8191,"architecture":{"modality":"text+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":128000},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"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/)....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-large-2407","canonical_slug":"mistralai/mistral-large-2407","name":"Mistral Large 2407","created":1731978415,"context_length":131072,"max_input_tokens":131072,"architecture":{"modality":"text+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"","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/)....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-large-2512","canonical_slug":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000005","completion":"0.0000015"},"top_provider":{"context_length":262144},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.0645},"hugging_face_id":"","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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-medium-3","canonical_slug":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","created":1746627341,"context_length":131072,"max_input_tokens":131072,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000004","completion":"0.000002"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-medium-3-5","canonical_slug":"mistralai/mistral-medium-3.5-20260430","name":"Mistral: Mistral Medium 3.5","created":1777570439,"context_length":262144,"max_input_tokens":262144,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000015","completion":"0.0000075"},"top_provider":{"context_length":262144},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-medium-3.1","canonical_slug":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","created":1755095639,"context_length":131072,"max_input_tokens":131072,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000004","completion":"0.000002"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-nemo","canonical_slug":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","created":1721347200,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.000000019","completion":"0.00000003"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-saba","canonical_slug":"mistralai/mistral-saba-2502","name":"Mistral: Saba","created":1739803239,"context_length":32768,"max_input_tokens":32768,"architecture":{"modality":"text+file-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000002","completion":"0.0000006"},"top_provider":{"context_length":32768},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-small-24b-instruct-2501","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.00000005","completion":"0.00000008"},"top_provider":{"context_length":32768,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Mistral-Small-24B-Instruct-2501","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-small-2603","canonical_slug":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","created":1773695685,"context_length":262144,"max_input_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":262144},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"mistralai/Mistral-Small-4-119B-2603","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-small-3.1-24b-instruct","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.000000351","completion":"0.000000555"},"top_provider":{"context_length":128000,"max_completion_tokens":128000},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mistral-small-3.2-24b-instruct","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.00000009375","completion":"0.00000025"},"top_provider":{"context_length":256000,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/mixtral-8x22b-instruct","canonical_slug":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text+file-\u003etext","tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":65536},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.3},"hugging_face_id":"mistralai/Mixtral-8x22B-Instruct-v0.1","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/mistralai/voxtral-small-24b-2507","canonical_slug":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"context_length":32000,"max_input_tokens":32000,"architecture":{"modality":"text+file+audio-\u003etext","tokenizer":"Mistral"},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":32000},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.2,"top_p":0.95},"hugging_face_id":"mistralai/Voxtral-Small-24B-2507","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2","canonical_slug":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":100352,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000057","completion":"0.0000023"},"top_provider":{"context_length":131072,"max_completion_tokens":100352},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"moonshotai/Kimi-K2-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2-0905","canonical_slug":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":100352,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":100352},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2-thinking","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":100352,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000025"},"top_provider":{"context_length":262144,"max_completion_tokens":100352},"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"],"hugging_face_id":"moonshotai/Kimi-K2-Thinking","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2.5","canonical_slug":"moonshotai/kimi-k2.5-0127","name":"MoonshotAI: Kimi K2.5","created":1769487076,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000045","completion":"0.00000225"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"moonshotai/Kimi-K2.5","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2.6","canonical_slug":"moonshotai/kimi-k2.6-20260420","name":"MoonshotAI: Kimi K2.6","created":1776699402,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000009405","completion":"0.00000396"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"moonshotai/Kimi-K2.6","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...","owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"openrouter/moonshotai/kimi-k2.7-code","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000067","completion":"0.0000034"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"moonshotai/Kimi-K2.7-Code","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k2.7-code:batch","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","name":"MoonshotAI: Kimi K2.7 Code (batch)","created":1781266361,"context_length":262144,"max_input_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000095","completion":"0.000004"},"top_provider":{"context_length":262144},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"moonshotai/Kimi-K2.7-Code","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3-20260715","name":"MoonshotAI: Kimi K3","created":1784215858,"context_length":1048576,"max_input_tokens":1048576,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":1048576},"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"],"default_parameters":{"top_p":0.95},"hugging_face_id":"moonshotai/Kimi-K3","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/morph/morph-v3-fast","canonical_slug":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","created":1751910002,"context_length":81920,"max_input_tokens":81920,"max_output_tokens":38000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000008","completion":"0.0000012"},"top_provider":{"context_length":81920,"max_completion_tokens":38000},"supported_parameters":["max_tokens","stop","temperature"],"hugging_face_id":"","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: \u003cinstruction\u003e{instruction}\u003c/instruction\u003e \u003ccode\u003e{initial_code}\u003c/code\u003e \u003cupdate\u003e{edit_snippet}\u003c/update\u003e...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/morph/morph-v3-large","canonical_slug":"morph/morph-v3-large","name":"Morph: Morph V3 Large","created":1751910858,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000009","completion":"0.0000019"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"supported_parameters":["logprobs","max_tokens","response_format","stop","structured_outputs","temperature","top_logprobs"],"hugging_face_id":"","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: \u003cinstruction\u003e{instruction}\u003c/instruction\u003e \u003ccode\u003e{initial_code}\u003c/code\u003e...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nex-agi/nex-n2-mini","canonical_slug":"nex-agi/nex-n2-mini","name":"Nex AGI: Nex-N2-Mini","created":1782312964,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000025","completion":"0.0000001"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.95},"hugging_face_id":"nex-agi/Nex-N2-Mini","description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nex-agi/nex-n2-pro","canonical_slug":"nex-agi/nex-n2-pro","name":"Nex AGI: Nex-N2-Pro","created":1780937140,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000025","completion":"0.000001"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":0.7,"top_p":0.95},"hugging_face_id":"nex-agi/Nex-N2-Pro","description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nousresearch/hermes-3-llama-3.1-405b","canonical_slug":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","created":1723766400,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.000001","completion":"0.000001"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-405B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nousresearch/hermes-3-llama-3.1-70b","canonical_slug":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","created":1723939200,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"chatml"},"pricing":{"prompt":"0.0000007","completion":"0.0000007"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-70B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nousresearch/hermes-4-405b","canonical_slug":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","created":1756235463,"context_length":131072,"max_input_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000001","completion":"0.000003"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"hugging_face_id":"NousResearch/Hermes-4-405B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nousresearch/hermes-4-70b","canonical_slug":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","created":1756236182,"context_length":131072,"max_input_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3"},"pricing":{"prompt":"0.00000013","completion":"0.0000004"},"top_provider":{"context_length":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","temperature","top_k","top_p"],"hugging_face_id":"NousResearch/Hermes-4-70B","description":"Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-nano-30b-a3b","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000005","completion":"0.0000002"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-nano-30b-a3b:free","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B (free)","created":1765731275,"context_length":256000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","canonical_slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","name":"NVIDIA: Nemotron 3 Nano Omni (free)","created":1777393095,"context_length":256000,"architecture":{"modality":"text+image+audio+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-super-120b-a12b","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"context_length":1000000,"max_input_tokens":262144,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000085","completion":"0.0000004"},"top_provider":{"context_length":262144,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-super-120b-a12b:free","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","name":"NVIDIA: Nemotron 3 Super (free)","created":1773245239,"context_length":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-ultra-550b-a55b","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"context_length":512288,"max_input_tokens":512288,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000036"},"top_provider":{"context_length":512288},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-ultra-550b-a55b:batch","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","name":"NVIDIA: Nemotron 3 Ultra (batch)","created":1780551208,"context_length":512288,"max_input_tokens":512288,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000036"},"top_provider":{"context_length":512288},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3-ultra-550b-a55b:free","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","name":"NVIDIA: Nemotron 3 Ultra (free)","created":1780551208,"context_length":1000000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3.5-content-safety:free","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","created":1780581864,"context_length":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":128000,"max_completion_tokens":8192},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"hugging_face_id":"nvidia/Nemotron-3.5-Content-Safety","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3.5-lightning","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000008","completion":"0.0000002"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"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"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-3.5-lightning:free","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","name":"NVIDIA: Nemotron 3.5 Lightning (free)","created":1786452751,"context_length":1000000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-nano-12b-v2-vl:free","canonical_slug":"nvidia/nemotron-nano-12b-v2-vl","name":"NVIDIA: Nemotron Nano 12B 2 VL (free)","created":1761675565,"context_length":128000,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":128000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","description":"NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/nvidia/nemotron-nano-9b-v2:free","canonical_slug":"nvidia/nemotron-nano-9b-v2","name":"NVIDIA: Nemotron Nano 9B V2 (free)","created":1757106807,"context_length":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":128000},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","description":"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-3.5-turbo","canonical_slug":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","created":1685232000,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000005","completion":"0.0000015"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-3.5-turbo-0613","canonical_slug":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"context_length":4095,"max_input_tokens":4095,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000001","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":4096},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-3.5-turbo-16k","canonical_slug":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000003","completion":"0.000004"},"top_provider":{"context_length":16385,"max_completion_tokens":4096},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-3.5-turbo-instruct","canonical_slug":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","created":1695859200,"context_length":4095,"max_input_tokens":4095,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT","instruct_type":"chatml"},"pricing":{"prompt":"0.0000015","completion":"0.000002"},"top_provider":{"context_length":4095,"max_completion_tokens":4096,"is_moderated":true},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-3.5-turbo:batch","canonical_slug":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo (batch)","created":1685232000,"context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000025","completion":"0.00000075"},"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":true},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4","canonical_slug":"openai/gpt-4","name":"OpenAI: GPT-4","created":1685232000,"context_length":8191,"max_input_tokens":8191,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00003","completion":"0.00006"},"top_provider":{"context_length":8191,"max_completion_tokens":4096},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4-turbo","canonical_slug":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","created":1712620800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4-turbo-preview","canonical_slug":"openai/gpt-4-turbo-preview","name":"OpenAI: GPT-4 Turbo Preview","created":1706140800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00001","completion":"0.00003"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"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"],"description":"The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4-turbo:batch","canonical_slug":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo (batch)","created":1712620800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000005","completion":"0.000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"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"],"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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1","canonical_slug":"openai/gpt-4.1-2025-04-14","name":"OpenAI: GPT-4.1","created":1744651385,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000002","completion":"0.000008"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1-mini","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000004","completion":"0.0000016"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1-mini:batch","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","name":"OpenAI: GPT-4.1 Mini (batch)","created":1744651381,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000002","completion":"0.0000008"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1-nano","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000001","completion":"0.0000004"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1-nano:batch","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","name":"OpenAI: GPT-4.1 Nano (batch)","created":1744651369,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000005","completion":"0.0000002"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4.1:batch","canonical_slug":"openai/gpt-4.1-2025-04-14","name":"OpenAI: GPT-4.1 (batch)","created":1744651385,"context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000001","completion":"0.000004"},"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o","canonical_slug":"openai/gpt-4o","name":"OpenAI: GPT-4o","created":1715558400,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-2024-05-13","canonical_slug":"openai/gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000005","completion":"0.000015"},"top_provider":{"context_length":128000,"max_completion_tokens":4096},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-2024-08-06","canonical_slug":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-2024-11-20","canonical_slug":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"hugging_face_id":"","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 \u0026 readability. It’s also better at working with uploaded...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","created":1721260800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-mini-2024-07-18","canonical_slug":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o-mini:batch","canonical_slug":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini (batch)","created":1721260800,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000075","completion":"0.0000003"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-4o:batch","canonical_slug":"openai/gpt-4o","name":"OpenAI: GPT-4o (batch)","created":1715558400,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.000005"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5","canonical_slug":"openai/gpt-5-2025-08-07","name":"OpenAI: GPT-5","created":1754587413,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.00001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-codex:batch","canonical_slug":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex (batch)","created":1758643403,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000625","completion":"0.000005"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-image","canonical_slug":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image","created":1760447986,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext+image","tokenizer":"GPT"},"pricing":{"prompt":"0.00001","completion":"0.00001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-image-mini","canonical_slug":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext+image","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-mini","canonical_slug":"openai/gpt-5-mini-2025-08-07","name":"OpenAI: GPT-5 Mini","created":1754587407,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000025","completion":"0.000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-mini:batch","canonical_slug":"openai/gpt-5-mini-2025-08-07","name":"OpenAI: GPT-5 Mini (batch)","created":1754587407,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000125","completion":"0.000001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-nano","canonical_slug":"openai/gpt-5-nano-2025-08-07","name":"OpenAI: GPT-5 Nano","created":1754587402,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000005","completion":"0.0000004"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-nano:batch","canonical_slug":"openai/gpt-5-nano-2025-08-07","name":"OpenAI: GPT-5 Nano (batch)","created":1754587402,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000025","completion":"0.0000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-pro","canonical_slug":"openai/gpt-5-pro-2025-10-06","name":"OpenAI: GPT-5 Pro","created":1759776663,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000015","completion":"0.00012"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5-pro:batch","canonical_slug":"openai/gpt-5-pro-2025-10-06","name":"OpenAI: GPT-5 Pro (batch)","created":1759776663,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000075","completion":"0.00006"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.1","canonical_slug":"openai/gpt-5.1-20251113","name":"OpenAI: GPT-5.1","created":1763060305,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.00001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.1-codex","canonical_slug":"openai/gpt-5.1-codex-20251113","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.00001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.1-codex-max","canonical_slug":"openai/gpt-5.1-codex-max-20251204","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.00001"},"top_provider":{"context_length":400000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.1-codex-mini","canonical_slug":"openai/gpt-5.1-codex-mini-20251113","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000025","completion":"0.000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.1:batch","canonical_slug":"openai/gpt-5.1-20251113","name":"OpenAI: GPT-5.1 (batch)","created":1763060305,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000625","completion":"0.000005"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2","canonical_slug":"openai/gpt-5.2-20251211","name":"OpenAI: GPT-5.2","created":1765389775,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000175","completion":"0.000014"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2-chat","canonical_slug":"openai/gpt-5.2-chat-20251211","name":"OpenAI: GPT-5.2 Chat","created":1765389783,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000175","completion":"0.000014"},"top_provider":{"context_length":128000,"max_completion_tokens":32000},"supported_parameters":["max_completion_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2-codex","canonical_slug":"openai/gpt-5.2-codex-20260114","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000175","completion":"0.000014"},"top_provider":{"context_length":400000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2-pro","canonical_slug":"openai/gpt-5.2-pro-20251211","name":"OpenAI: GPT-5.2 Pro","created":1765389780,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000021","completion":"0.000168"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2-pro:batch","canonical_slug":"openai/gpt-5.2-pro-20251211","name":"OpenAI: GPT-5.2 Pro (batch)","created":1765389780,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000105","completion":"0.000084"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.2:batch","canonical_slug":"openai/gpt-5.2-20251211","name":"OpenAI: GPT-5.2 (batch)","created":1765389775,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000875","completion":"0.000007"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.3-codex","canonical_slug":"openai/gpt-5.3-codex-20260224","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000175","completion":"0.000014"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4","canonical_slug":"openai/gpt-5.4-20260305","name":"OpenAI: GPT-5.4","created":1772734352,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.000015"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-image-2","canonical_slug":"openai/gpt-5.4-image-2-20260421","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext+image","tokenizer":"GPT"},"pricing":{"prompt":"0.000008","completion":"0.000015"},"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","top_logprobs"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-mini","canonical_slug":"openai/gpt-5.4-mini-20260317","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000075","completion":"0.0000045"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-mini:batch","canonical_slug":"openai/gpt-5.4-mini-20260317","name":"OpenAI: GPT-5.4 Mini (batch)","created":1773748178,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000375","completion":"0.00000225"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-nano","canonical_slug":"openai/gpt-5.4-nano-20260317","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000002","completion":"0.00000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-nano:batch","canonical_slug":"openai/gpt-5.4-nano-20260317","name":"OpenAI: GPT-5.4 Nano (batch)","created":1773748187,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000001","completion":"0.000000625"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-pro","canonical_slug":"openai/gpt-5.4-pro-20260305","name":"OpenAI: GPT-5.4 Pro","created":1772734366,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00003","completion":"0.00018"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4-pro:batch","canonical_slug":"openai/gpt-5.4-pro-20260305","name":"OpenAI: GPT-5.4 Pro (batch)","created":1772734366,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000015","completion":"0.00009"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.4:batch","canonical_slug":"openai/gpt-5.4-20260305","name":"OpenAI: GPT-5.4 (batch)","created":1772734352,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.0000075"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.5","canonical_slug":"openai/gpt-5.5-20260423","name":"OpenAI: GPT-5.5","created":1777051893,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000005","completion":"0.00003"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.5-pro","canonical_slug":"openai/gpt-5.5-pro-20260423","name":"OpenAI: GPT-5.5 Pro","created":1777051896,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00003","completion":"0.00018"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.5-pro:batch","canonical_slug":"openai/gpt-5.5-pro-20260423","name":"OpenAI: GPT-5.5 Pro (batch)","created":1777051896,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000015","completion":"0.00009"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.5:batch","canonical_slug":"openai/gpt-5.5-20260423","name":"OpenAI: GPT-5.5 (batch)","created":1777051893,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.000015"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna-20260709","name":"OpenAI: GPT-5.6 Luna","created":1783590864,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000002","completion":"0.0000012"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-luna-pro","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000002","completion":"0.0000012"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-luna-pro:batch","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","name":"OpenAI: GPT-5.6 Luna Pro (batch)","created":1783590867,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000001","completion":"0.0000006"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-luna:batch","canonical_slug":"openai/gpt-5.6-luna-20260709","name":"OpenAI: GPT-5.6 Luna (batch)","created":1783590864,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000001","completion":"0.0000006"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol-20260709","name":"OpenAI: GPT-5.6 Sol","created":1783590850,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.000015"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-sol-pro","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.000015"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-sol-pro:batch","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","name":"OpenAI: GPT-5.6 Sol Pro (batch)","created":1783590854,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.0000075"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-sol:batch","canonical_slug":"openai/gpt-5.6-sol-20260709","name":"OpenAI: GPT-5.6 Sol (batch)","created":1783590850,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000125","completion":"0.0000075"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra-20260709","name":"OpenAI: GPT-5.6 Terra","created":1783590857,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000002","completion":"0.000012"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-terra-pro","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000002","completion":"0.000012"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-terra-pro:batch","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","name":"OpenAI: GPT-5.6 Terra Pro (batch)","created":1783590861,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000001","completion":"0.000006"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5.6-terra:batch","canonical_slug":"openai/gpt-5.6-terra-20260709","name":"OpenAI: GPT-5.6 Terra (batch)","created":1783590857,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000001","completion":"0.000006"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-5:batch","canonical_slug":"openai/gpt-5-2025-08-07","name":"OpenAI: GPT-5 (batch)","created":1754587413,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000625","completion":"0.000005"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-audio","canonical_slug":"openai/gpt-audio","name":"OpenAI: GPT Audio","created":1768862569,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+audio-\u003etext+audio","tokenizer":"GPT"},"pricing":{"prompt":"0.0000025","completion":"0.00001"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-audio-mini","canonical_slug":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","created":1768859419,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"architecture":{"modality":"text+audio-\u003etext+audio","tokenizer":"GPT"},"pricing":{"prompt":"0.0000006","completion":"0.0000024"},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-chat-latest","canonical_slug":"openai/gpt-chat-latest-20260505","name":"OpenAI: GPT Chat Latest","created":1778000212,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000005","completion":"0.00003"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000003","completion":"0.00000017"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"openai/gpt-oss-120b","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-oss-20b","canonical_slug":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000003","completion":"0.00000013"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"openai/gpt-oss-20b","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-oss-20b:free","canonical_slug":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b (free)","created":1754414229,"context_length":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"hugging_face_id":"openai/gpt-oss-20b","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/gpt-oss-safeguard-20b","canonical_slug":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000000075","completion":"0.0000003"},"top_provider":{"context_length":131072,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"openai/gpt-oss-safeguard-20b","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o1","canonical_slug":"openai/o1-2024-12-17","name":"OpenAI: o1","created":1734459999,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000015","completion":"0.00006"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o1-pro","canonical_slug":"openai/o1-pro","name":"OpenAI: o1-pro","created":1742423211,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00015","completion":"0.0006"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o1-pro:batch","canonical_slug":"openai/o1-pro","name":"OpenAI: o1-pro (batch)","created":1742423211,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000075","completion":"0.0003"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o1:batch","canonical_slug":"openai/o1-2024-12-17","name":"OpenAI: o1 (batch)","created":1734459999,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000075","completion":"0.00003"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3","canonical_slug":"openai/o3-2025-04-16","name":"OpenAI: o3","created":1744823457,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000002","completion":"0.000008"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-mini","canonical_slug":"openai/o3-mini-2025-01-31","name":"OpenAI: o3 Mini","created":1738351721,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000011","completion":"0.0000044"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-mini-high","canonical_slug":"openai/o3-mini-high-2025-01-31","name":"OpenAI: o3 Mini High","created":1739372611,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000011","completion":"0.0000044"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-mini-high:batch","canonical_slug":"openai/o3-mini-high-2025-01-31","name":"OpenAI: o3 Mini High (batch)","created":1739372611,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-mini:batch","canonical_slug":"openai/o3-mini-2025-01-31","name":"OpenAI: o3 Mini (batch)","created":1738351721,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-pro","canonical_slug":"openai/o3-pro-2025-06-10","name":"OpenAI: o3 Pro","created":1749598352,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00002","completion":"0.00008"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3-pro:batch","canonical_slug":"openai/o3-pro-2025-06-10","name":"OpenAI: o3 Pro (batch)","created":1749598352,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00001","completion":"0.00004"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o3:batch","canonical_slug":"openai/o3-2025-04-16","name":"OpenAI: o3 (batch)","created":1744823457,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.000001","completion":"0.000004"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o4-mini","canonical_slug":"openai/o4-mini-2025-04-16","name":"OpenAI: o4 Mini","created":1744820942,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000011","completion":"0.0000044"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o4-mini-high","canonical_slug":"openai/o4-mini-high-2025-04-16","name":"OpenAI: o4 Mini High","created":1744824212,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.0000011","completion":"0.0000044"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o4-mini-high:batch","canonical_slug":"openai/o4-mini-high-2025-04-16","name":"OpenAI: o4 Mini High (batch)","created":1744824212,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openai/o4-mini:batch","canonical_slug":"openai/o4-mini-2025-04-16","name":"OpenAI: o4 Mini (batch)","created":1744820942,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"GPT"},"pricing":{"prompt":"0.00000055","completion":"0.0000022"},"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","tool_choice","tools"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/auto","canonical_slug":"openrouter/auto","name":"Auto Router","created":1699401600,"context_length":2000000,"max_input_tokens":2000000,"architecture":{"modality":"text+image+file+audio+video-\u003etext+image","tokenizer":"Router"},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{},"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"],"description":"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/auto-beta","canonical_slug":"openrouter/auto-beta","name":"Auto Router (Beta)","created":1784311165,"context_length":2000000,"max_input_tokens":2000000,"architecture":{"modality":"text+image+file+audio+video-\u003etext+image","tokenizer":"Router"},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{},"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"],"description":"Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/bodybuilder","canonical_slug":"openrouter/bodybuilder","name":"Body Builder (beta)","created":1764903653,"context_length":128000,"max_input_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{},"hugging_face_id":"","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:...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/free","canonical_slug":"openrouter/free","name":"Free Models Router","created":1769917427,"context_length":200000,"max_input_tokens":200000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/fusion","canonical_slug":"openrouter/fusion","name":"OpenRouter: Fusion","created":1781371647,"context_length":1000000,"max_input_tokens":1000000,"architecture":{"modality":"text-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{},"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/openrouter/pareto-code","canonical_slug":"openrouter/pareto-code","name":"Pareto Code Router","created":1776747900,"context_length":2000000,"max_input_tokens":2000000,"architecture":{"modality":"text-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"-1","completion":"-1"},"top_provider":{},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perceptron/perceptron-mk1","canonical_slug":"perceptron/perceptron-mk1-20260512","name":"Perceptron: Perceptron Mk1","created":1778597029,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000015","completion":"0.0000015"},"top_provider":{"context_length":32768,"max_completion_tokens":8192},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perplexity/sonar","canonical_slug":"perplexity/sonar","name":"Perplexity: Sonar","created":1738013808,"context_length":127072,"max_input_tokens":127072,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000001","completion":"0.000001"},"top_provider":{"context_length":127072},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perplexity/sonar-deep-research","canonical_slug":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","created":1741311246,"context_length":128000,"max_input_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.000002","completion":"0.000008"},"top_provider":{"context_length":128000},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perplexity/sonar-pro","canonical_slug":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","created":1741312423,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":8000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":200000,"max_completion_tokens":8000},"supported_parameters":["frequency_penalty","max_tokens","presence_penalty","temperature","top_k","top_p","web_search_options"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perplexity/sonar-pro-search","canonical_slug":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","created":1761854366,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":8000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000003","completion":"0.000015"},"top_provider":{"context_length":200000,"max_completion_tokens":8000},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p","web_search_options"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/perplexity/sonar-reasoning-pro","canonical_slug":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"context_length":128000,"max_input_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":"0.000002","completion":"0.000008"},"top_provider":{"context_length":128000},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","temperature","top_k","top_p","web_search_options"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/poolside/laguna-s-2.1","canonical_slug":"poolside/laguna-s-2.1-20260720","name":"Poolside: Laguna S 2.1","created":1784652683,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000009","completion":"0.00000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"hugging_face_id":"poolside/Laguna-S-2.1","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](\u003chttps://poolside.ai/\u003e). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/poolside/laguna-s-2.1:free","canonical_slug":"poolside/laguna-s-2.1-20260720","name":"Poolside: Laguna S 2.1 (free)","created":1784652683,"context_length":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"hugging_face_id":"poolside/Laguna-S-2.1","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](\u003chttps://poolside.ai/\u003e). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/poolside/laguna-xs-2.1","canonical_slug":"poolside/laguna-xs-2.1-20260625","name":"Poolside: Laguna XS 2.1","created":1783002429,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000006","completion":"0.00000012"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"hugging_face_id":"poolside/Laguna-XS-2.1","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/poolside/laguna-xs-2.1:free","canonical_slug":"poolside/laguna-xs-2.1-20260625","name":"Poolside: Laguna XS 2.1 (free)","created":1783002429,"context_length":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":262144,"max_completion_tokens":32768},"supported_parameters":["include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools"],"hugging_face_id":"poolside/Laguna-XS-2.1","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-2.5-72b-instruct","canonical_slug":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000036","completion":"0.0000004"},"top_provider":{"context_length":32768,"max_completion_tokens":16384},"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"],"hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-2.5-7b-instruct","canonical_slug":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000001","completion":"0.0000002"},"top_provider":{"context_length":32768,"max_completion_tokens":32768},"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"],"hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-2.5-coder-32b-instruct","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000066","completion":"0.000001"},"top_provider":{"context_length":32768,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","logit_bias","max_tokens","min_p","presence_penalty","repetition_penalty","seed","stop","temperature","top_k","top_p"],"hugging_face_id":"Qwen/Qwen2.5-Coder-32B-Instruct","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**...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-plus","canonical_slug":"qwen/qwen-plus-2025-01-25","name":"Qwen: Qwen-Plus","created":1738409840,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000026","completion":"0.00000078"},"top_provider":{"context_length":1000000,"max_completion_tokens":32768},"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"],"hugging_face_id":"","description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-plus-2025-07-28","canonical_slug":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","created":1757347599,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000026","completion":"0.00000078"},"top_provider":{"context_length":1000000,"max_completion_tokens":32768},"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"],"hugging_face_id":"","description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen-plus-2025-07-28:thinking","canonical_slug":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728 (thinking)","created":1757347599,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000026","completion":"0.00000078"},"top_provider":{"context_length":1000000,"max_completion_tokens":32768},"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"],"hugging_face_id":"","description":"Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen2.5-vl-72b-instruct","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.0000008","completion":"0.000001"},"top_provider":{"context_length":128000,"max_completion_tokens":128000},"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"],"hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-14b","canonical_slug":"qwen/qwen3-14b-04-28","name":"Qwen: Qwen3 14B","created":1745876478,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000012","completion":"0.00000024"},"top_provider":{"context_length":40960,"max_completion_tokens":16384},"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"],"hugging_face_id":"Qwen/Qwen3-14B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-235b-a22b","canonical_slug":"qwen/qwen3-235b-a22b-04-28","name":"Qwen: Qwen3 235B A22B","created":1745875757,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.000000455","completion":"0.00000182"},"top_provider":{"context_length":131072,"max_completion_tokens":8192},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"Qwen/Qwen3-235B-A22B","description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-235b-a22b-2507","canonical_slug":"qwen/qwen3-235b-a22b-07-25","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000009","completion":"0.00000055"},"top_provider":{"context_length":262144,"max_completion_tokens":16384},"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"],"hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-235b-a22b-thinking-2507","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000023","completion":"0.0000023"},"top_provider":{"context_length":131072},"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"],"hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-30b-a3b","canonical_slug":"qwen/qwen3-30b-a3b-04-28","name":"Qwen: Qwen3 30B A3B","created":1745878604,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000013","completion":"0.00000052"},"top_provider":{"context_length":131072,"max_completion_tokens":8192},"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"],"hugging_face_id":"Qwen/Qwen3-30B-A3B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-30b-a3b-instruct-2507","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"context_length":262144,"max_input_tokens":128000,"max_output_tokens":32000,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000004815","completion":"0.00000019305"},"top_provider":{"context_length":128000,"max_completion_tokens":32000},"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"],"hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-30b-a3b-thinking-2507","canonical_slug":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","created":1756399192,"context_length":81920,"max_input_tokens":81920,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000002","completion":"0.0000024"},"top_provider":{"context_length":81920,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"Qwen/Qwen3-30B-A3B-Thinking-2507","description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-32b","canonical_slug":"qwen/qwen3-32b-04-28","name":"Qwen: Qwen3 32B","created":1745875945,"context_length":131072,"max_input_tokens":40960,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.00000008","completion":"0.00000028"},"top_provider":{"context_length":40960,"max_completion_tokens":16384},"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"],"hugging_face_id":"Qwen/Qwen3-32B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-8b","canonical_slug":"qwen/qwen3-8b-04-28","name":"Qwen: Qwen3 8B","created":1745876632,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":"0.000000117","completion":"0.000000455"},"top_provider":{"context_length":131072,"max_completion_tokens":8192},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3-8B","description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-coder","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000003","completion":"0.000001"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-coder-30b-a3b-instruct","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000007","completion":"0.00000028"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-coder-flash","canonical_slug":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000195","completion":"0.000000975"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-coder-next","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","name":"Qwen: Qwen3 Coder Next","created":1770164101,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000012","completion":"0.0000008"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3-Coder-Next","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-coder-plus","canonical_slug":"qwen/qwen3-coder-plus","name":"Qwen: Qwen3 Coder Plus","created":1758662707,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000065","completion":"0.00000325"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"hugging_face_id":"","description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-max","canonical_slug":"qwen/qwen3-max","name":"Qwen: Qwen3 Max","created":1758662808,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000078","completion":"0.0000039"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":1,"top_p":1},"hugging_face_id":"","description":"Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-max-thinking","canonical_slug":"qwen/qwen3-max-thinking-20260123","name":"Qwen: Qwen3 Max Thinking","created":1770671901,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000078","completion":"0.0000039"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"description":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-next-80b-a3b-instruct","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000009","completion":"0.0000011"},"top_provider":{"context_length":262144,"max_completion_tokens":16384},"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"],"hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-next-80b-a3b-thinking","canonical_slug":"qwen/qwen3-next-80b-a3b-thinking-2509","name":"Qwen: Qwen3 Next 80B A3B Thinking","created":1757612284,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000015","completion":"0.0000012"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-235b-a22b-instruct","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000021","completion":"0.0000019"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.7,"top_p":0.8},"hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-235b-a22b-thinking","canonical_slug":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","created":1758668690,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000004","completion":"0.000004"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.8,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-30b-a3b-instruct","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000013","completion":"0.00000052"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.7,"top_p":0.8},"hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-30b-a3b-thinking","canonical_slug":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","created":1759794479,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000002","completion":"0.0000024"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.8,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-32b-instruct","canonical_slug":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","created":1761231332,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.000000104","completion":"0.000000416"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.7,"top_p":0.8},"hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-8b-instruct","canonical_slug":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"context_length":262144,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000117","completion":"0.000000455"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.7,"top_p":0.8},"hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3-vl-8b-thinking","canonical_slug":"qwen/qwen3-vl-8b-thinking","name":"Qwen: Qwen3 VL 8B Thinking","created":1760463746,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000018","completion":"0.0000021"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3-VL-8B-Thinking","description":"Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-122b-a10b","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000026","completion":"0.00000208"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.5-122B-A10B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-27b","canonical_slug":"qwen/qwen3.5-27b-20260224","name":"Qwen: Qwen3.5-27B","created":1772053810,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000195","completion":"0.00000156"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.5-27B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-35b-a3b","canonical_slug":"qwen/qwen3.5-35b-a3b-20260224","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000025","completion":"0.00000125"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.5-35B-A3B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-397b-a17b","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000039","completion":"0.00000234"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"default_parameters":{"temperature":0.6,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.5-397B-A17B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-9b","canonical_slug":"qwen/qwen3.5-9b-20260310","name":"Qwen: Qwen3.5-9B","created":1773152396,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000001","completion":"0.00000015"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"Qwen/Qwen3.5-9B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-flash-02-23","canonical_slug":"qwen/qwen3.5-flash-20260224","name":"Qwen: Qwen3.5-Flash","created":1772053776,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000065","completion":"0.00000026"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-plus-02-15","canonical_slug":"qwen/qwen3.5-plus-20260216","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.00000026","completion":"0.00000156"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.5-plus-20260420","canonical_slug":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000003","completion":"0.0000018"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.6-27b","canonical_slug":"qwen/qwen3.6-27b-20260422","name":"Qwen: Qwen3.6 27B","created":1777255064,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000006","completion":"0.0000036"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"hugging_face_id":"Qwen/Qwen3.6-27B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.6-35b-a3b","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000014","completion":"0.000001"},"top_provider":{"context_length":262144,"max_completion_tokens":262144},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.6-35B-A3B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.6-flash","canonical_slug":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","created":1777261362,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.0000001875","completion":"0.000001125"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.6-max-preview","canonical_slug":"qwen/qwen3.6-max-preview-20260420","name":"Qwen: Qwen3.6 Max Preview","created":1777260242,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.000001027","completion":"0.000006162"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"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"],"description":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.6-plus","canonical_slug":"qwen/qwen3.6-plus-04-02","name":"Qwen: Qwen3.6 Plus","created":1775133557,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen3"},"pricing":{"prompt":"0.000000325","completion":"0.00000195"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"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"],"hugging_face_id":"","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...","owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"openrouter/qwen/qwen3.7-flash","canonical_slug":"qwen/qwen3.7-flash-20260727","name":"Qwen: Qwen3.7 Flash","created":1785190561,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000003","completion":"0.00000013"},"top_provider":{"context_length":1000000,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","temperature","tool_choice","tools","top_logprobs","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.7-max","canonical_slug":"qwen/qwen3.7-max-20260520","name":"Qwen: Qwen3.7 Max","created":1779376861,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.000001475","completion":"0.000004425"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072},"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"],"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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.7-plus","canonical_slug":"qwen/qwen3.7-plus-20260602","name":"Qwen: Qwen3.7 Plus","created":1780491783,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000032","completion":"0.00000128"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072},"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"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.8-2.4t-a95b","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":262144},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.8-2.4T-A95B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.8-27b","canonical_slug":"qwen/qwen3.8-27b-20260814","name":"Qwen: Qwen3.8 27B","created":1786722910,"context_length":1000000,"max_input_tokens":262144,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.00000045","completion":"0.0000032"},"top_provider":{"context_length":262144,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"Qwen/Qwen3.8-27B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/qwen/qwen3.8-max","canonical_slug":"qwen/qwen3.8-max-20260803","name":"Qwen: Qwen3.8 Max","created":1785731612,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Qwen"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":1000000,"max_completion_tokens":131072},"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"],"description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/rekaai/reka-edge","canonical_slug":"rekaai/reka-edge-2603","name":"Reka Edge","created":1774026965,"context_length":16384,"max_input_tokens":16384,"max_output_tokens":16384,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000001","completion":"0.0000001"},"top_provider":{"context_length":16384,"max_completion_tokens":16384},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"RekaAI/reka-edge-2603","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/rekaai/reka-flash-3","canonical_slug":"rekaai/reka-flash-3","name":"Reka Flash 3","created":1741812813,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000001","completion":"0.0000002"},"top_provider":{"context_length":65536,"max_completion_tokens":65536},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"hugging_face_id":"RekaAI/reka-flash-3","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/relace/relace-apply-3","canonical_slug":"relace/relace-apply-3","name":"Relace: Relace Apply 3","created":1758891572,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000085","completion":"0.00000125"},"top_provider":{"context_length":256000,"max_completion_tokens":128000},"supported_parameters":["max_tokens","seed","stop"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/relace/relace-search","canonical_slug":"relace/relace-search-20251208","name":"Relace: Relace Search","created":1765213560,"context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000001","completion":"0.000003"},"top_provider":{"context_length":256000,"max_completion_tokens":128000},"supported_parameters":["max_tokens","response_format","seed","stop","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/sakana/fugu-ultra","canonical_slug":"sakana/fugu-ultra-20260615","name":"Sakana: Fugu Ultra","created":1782276303,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000005","completion":"0.00003"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/sakana/sakana-namazu","canonical_slug":"sakana/namazu-20260811","name":"Sakana: Sakana Namazu","created":1786410129,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000095","completion":"0.000004"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/sao10k/l3-lunaris-8b","canonical_slug":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000004","completion":"0.00000005"},"top_provider":{"context_length":8192,"max_completion_tokens":16384},"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"],"hugging_face_id":"Sao10K/L3-8B-Lunaris-v1","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/sao10k/l3.1-euryale-70b","canonical_slug":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000085","completion":"0.00000085"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"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"],"hugging_face_id":"Sao10K/L3.1-70B-Euryale-v2.2","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).","owned_by":"","modalities":["unknown"]},{"id":"openrouter/sao10k/l3.3-euryale-70b","canonical_slug":"sao10k/l3.3-euryale-70b-v2.3","name":"Sao10K: Llama 3.3 Euryale 70B","created":1734535928,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.00000065","completion":"0.00000075"},"top_provider":{"context_length":131072,"max_completion_tokens":16384},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","top_logprobs","top_p"],"hugging_face_id":"Sao10K/L3.3-70B-Euryale-v2.3","description":"Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).","owned_by":"","modalities":["unknown"]},{"id":"openrouter/stealth/ox-alpha","canonical_slug":"stealth/ox-alpha","name":"Ox Alpha","created":1787256295,"context_length":1048576,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"description":"Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/stepfun/step-3.5-flash","canonical_slug":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","created":1769728337,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000001","completion":"0.0000003"},"top_provider":{"context_length":262144,"max_completion_tokens":65536},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"stepfun-ai/Step-3.5-Flash","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/stepfun/step-3.7-flash","canonical_slug":"stepfun/step-3.7-flash-20260528","name":"StepFun: Step 3.7 Flash","created":1779985069,"context_length":262144,"max_input_tokens":256000,"max_output_tokens":256000,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000002","completion":"0.00000115"},"top_provider":{"context_length":256000,"max_completion_tokens":256000},"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"],"hugging_face_id":"stepfun-ai/Step-3.7-Flash","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/tencent/hunyuan-a13b-instruct","canonical_slug":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","created":1751987664,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000014","completion":"0.00000057"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","response_format","structured_outputs","temperature","top_k","top_p"],"hugging_face_id":"tencent/Hunyuan-A13B-Instruct","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/tencent/hy-mt2-1.8b","canonical_slug":"tencent/hy-mt2-1.8b-20260521","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000044","completion":"0.000000177"},"top_provider":{"context_length":8192,"max_completion_tokens":4096},"supported_parameters":["max_completion_tokens","max_tokens","stop","temperature"],"hugging_face_id":"tencent/Hy-MT2-1.8B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/tencent/hy-mt2-30b-a3b","canonical_slug":"tencent/hy-mt2-30b-a3b-20260521","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"context_length":8192,"max_input_tokens":8192,"max_output_tokens":4096,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000074","completion":"0.000000295"},"top_provider":{"context_length":8192,"max_completion_tokens":4096},"supported_parameters":["max_completion_tokens","max_tokens","response_format","stop","structured_outputs","temperature"],"hugging_face_id":"tencent/Hy-MT2-30B-A3B","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/tencent/hy3","canonical_slug":"tencent/hy3-20260706","name":"Tencent: Hy3","created":1783344048,"context_length":262144,"max_input_tokens":262144,"max_output_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000132","completion":"0.000000528"},"top_provider":{"context_length":262144,"max_completion_tokens":128000},"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"],"default_parameters":{"temperature":0.9,"top_p":1},"hugging_face_id":"tencent/Hy3","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:...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/tencent/hy3-preview","canonical_slug":"tencent/hy3-preview-20260421","name":"Tencent: Hy3 preview","created":1776878150,"context_length":262144,"max_input_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000018","completion":"0.0000006"},"top_provider":{"context_length":262144},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"default_parameters":{"temperature":0.9,"top_p":1},"hugging_face_id":"tencent/Hy3-preview","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thedrummer/cydonia-24b-v4.1","canonical_slug":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000005"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"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"],"hugging_face_id":"thedrummer/cydonia-24b-v4.1","description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thedrummer/rocinante-12b","canonical_slug":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","created":1727654400,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"architecture":{"modality":"text-\u003etext","tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.00000025","completion":"0.0000005"},"top_provider":{"context_length":65536,"max_completion_tokens":65536},"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"],"hugging_face_id":"TheDrummer/Rocinante-12B-v1.1","description":"Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thedrummer/skyfall-36b-v2","canonical_slug":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000055","completion":"0.0000008"},"top_provider":{"context_length":32768,"max_completion_tokens":32768},"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"],"hugging_face_id":"TheDrummer/Skyfall-36B-v2","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.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thedrummer/unslopnemo-12b","canonical_slug":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"context_length":1024000,"max_input_tokens":1024000,"max_output_tokens":1024000,"architecture":{"modality":"text-\u003etext","tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000004","completion":"0.0000004"},"top_provider":{"context_length":1024000,"max_completion_tokens":1024000},"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"],"hugging_face_id":"TheDrummer/UnslopNemo-12B-v4.1","description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thinkingmachines/inkling","canonical_slug":"thinkingmachines/inkling-20260715","name":"Thinking Machines: Inkling","created":1784325956,"context_length":1048576,"max_input_tokens":524288,"max_output_tokens":262144,"architecture":{"modality":"text+image+audio-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000095","completion":"0.00000405"},"top_provider":{"context_length":524288,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"hugging_face_id":"thinkingmachines/Inkling","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thinkingmachines/inkling-small","canonical_slug":"thinkingmachines/inkling-small-20260730","name":"Thinking Machines: Inkling Small","created":1785443117,"context_length":1048576,"max_input_tokens":524288,"max_output_tokens":262144,"architecture":{"modality":"text+image+audio-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000045","completion":"0.0000012"},"top_provider":{"context_length":524288,"max_completion_tokens":262144},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"hugging_face_id":"thinkingmachines/Inkling-Small","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/thinkingmachines/inkling:batch","canonical_slug":"thinkingmachines/inkling-20260715","name":"Thinking Machines: Inkling (batch)","created":1784325956,"context_length":524288,"max_input_tokens":524288,"architecture":{"modality":"text+image+audio-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000001","completion":"0.00000405"},"top_provider":{"context_length":524288},"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"],"hugging_face_id":"thinkingmachines/Inkling","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/undi95/remm-slerp-l2-13b","canonical_slug":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","created":1689984000,"context_length":6144,"max_input_tokens":6144,"max_output_tokens":6144,"architecture":{"modality":"text-\u003etext","tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":"0.00000045","completion":"0.00000065"},"top_provider":{"context_length":6144,"max_completion_tokens":6144},"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"],"hugging_face_id":"Undi95/ReMM-SLERP-L2-13B","description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","owned_by":"","modalities":["unknown"]},{"id":"openrouter/upstage/solar-pro-3","canonical_slug":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","created":1769481200,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000015","completion":"0.0000006"},"top_provider":{"context_length":131072,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/upstage/solar-pro4","canonical_slug":"upstage/solar-pro4-20260810","name":"Upstage: Solar Pro 4","created":1786371636,"context_length":524288,"max_input_tokens":524288,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000003","completion":"0.00000012"},"top_provider":{"context_length":524288,"max_completion_tokens":131072},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","structured_outputs","temperature","tool_choice","tools","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/writer/palmyra-x5","canonical_slug":"writer/palmyra-x5-20250428","name":"Writer: Palmyra X5","created":1769003823,"context_length":1040000,"max_input_tokens":1040000,"max_output_tokens":8192,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.000006"},"top_provider":{"context_length":1040000,"max_completion_tokens":8192,"is_moderated":true},"supported_parameters":["max_tokens","stop","temperature","top_k","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-4.20","canonical_slug":"x-ai/grok-4.20-20260309","name":"SpaceXAI: Grok 4.20","created":1774979019,"context_length":2000000,"max_input_tokens":2000000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.00000125","completion":"0.0000025"},"top_provider":{"context_length":2000000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-4.20-multi-agent","canonical_slug":"x-ai/grok-4.20-multi-agent-20260309","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"context_length":2000000,"max_input_tokens":2000000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.00000125","completion":"0.0000025"},"top_provider":{"context_length":2000000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-4.3","canonical_slug":"x-ai/grok-4.3-20260430","name":"SpaceXAI: Grok 4.3","created":1777591821,"context_length":1000000,"max_input_tokens":1000000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.00000125","completion":"0.0000025"},"top_provider":{"context_length":1000000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-4.5","canonical_slug":"x-ai/grok-4.5-20260708","name":"SpaceXAI: Grok 4.5","created":1783523154,"context_length":500000,"max_input_tokens":500000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":500000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-4.6","canonical_slug":"x-ai/grok-4.6-20260810","name":"SpaceXAI: Grok 4.6","created":1786548957,"context_length":500000,"max_input_tokens":500000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":500000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/x-ai/grok-build-0.1","canonical_slug":"x-ai/grok-build-0.1-20260520","name":"SpaceXAI: Grok Build 0.1","created":1779298123,"context_length":256000,"max_input_tokens":256000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Grok"},"pricing":{"prompt":"0.000001","completion":"0.000002"},"top_provider":{"context_length":256000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/xiaomi/mimo-v2.5","canonical_slug":"xiaomi/mimo-v2.5-20260422","name":"Xiaomi: MiMo-V2.5","created":1776874269,"context_length":1050000,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text+image+audio+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000014","completion":"0.00000028"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"XiaomiMiMo/MiMo-V2.5","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/xiaomi/mimo-v2.5-pro","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"context_length":1050000,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000435","completion":"0.00000087"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","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....","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.5","canonical_slug":"z-ai/glm-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":98304,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000022"},"top_provider":{"context_length":131072,"max_completion_tokens":98304},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.75},"hugging_face_id":"zai-org/GLM-4.5","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.5-air","canonical_slug":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":98304,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000013","completion":"0.00000085"},"top_provider":{"context_length":131072,"max_completion_tokens":98304},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":0.75},"hugging_face_id":"zai-org/GLM-4.5-Air","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.5v","canonical_slug":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","created":1754922288,"context_length":65536,"max_input_tokens":65536,"max_output_tokens":16384,"architecture":{"modality":"text+image-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.0000018"},"top_provider":{"context_length":65536,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":0.75},"hugging_face_id":"zai-org/GLM-4.5V","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.6","canonical_slug":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"context_length":204800,"max_input_tokens":202752,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000005","completion":"0.000002"},"top_provider":{"context_length":202752,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":0.6},"hugging_face_id":"zai-org/GLM-4.6","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.6v","canonical_slug":"z-ai/glm-4.6-20251208","name":"Z.ai: GLM 4.6V","created":1765207462,"context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000003","completion":"0.0000009"},"top_provider":{"context_length":131072,"max_completion_tokens":32768},"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"],"default_parameters":{"temperature":0.8,"top_p":0.6},"hugging_face_id":"zai-org/GLM-4.6V","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.7","canonical_slug":"z-ai/glm-4.7-20251222","name":"Z.ai: GLM 4.7","created":1766378014,"context_length":204800,"max_input_tokens":202752,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000004","completion":"0.00000175"},"top_provider":{"context_length":202752,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-4.7","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-4.7-flash","canonical_slug":"z-ai/glm-4.7-flash-20260119","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"context_length":202752,"max_input_tokens":202752,"max_output_tokens":16384,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.00000006","completion":"0.0000004"},"top_provider":{"context_length":202752,"max_completion_tokens":16384},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-4.7-Flash","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5","canonical_slug":"z-ai/glm-5-20260211","name":"Z.ai: GLM 5","created":1770829182,"context_length":204800,"max_input_tokens":198000,"max_output_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000006","completion":"0.00000192"},"top_provider":{"context_length":198000,"max_completion_tokens":128000},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-5","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5-turbo","canonical_slug":"z-ai/glm-5-turbo-20260315","name":"Z.ai: GLM 5 Turbo","created":1773583573,"context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000012","completion":"0.000004"},"top_provider":{"context_length":202752,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5.1","canonical_slug":"z-ai/glm-5.1-20260406","name":"Z.ai: GLM 5.1","created":1775578025,"context_length":204800,"max_input_tokens":200000,"max_output_tokens":128000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000966","completion":"0.000003036"},"top_provider":{"context_length":200000,"max_completion_tokens":128000},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-5.1","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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2-20260616","name":"Z.ai: GLM 5.2","created":1781631930,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.000000966","completion":"0.000003036"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-5.2","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5.2:batch","canonical_slug":"z-ai/glm-5.2-20260616","name":"Z.ai: GLM 5.2 (batch)","created":1781631930,"context_length":1048575,"max_input_tokens":1048575,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000014","completion":"0.0000044"},"top_provider":{"context_length":1048575},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-5.2","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5.2:free","canonical_slug":"z-ai/glm-5.2-20260616","name":"Z.ai: GLM 5.2 (free)","created":1781631930,"context_length":256000,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":256000,"max_completion_tokens":256000},"supported_parameters":["frequency_penalty","include_reasoning","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"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"zai-org/GLM-5.2","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3-20260816","name":"Z.ai: GLM 5.3","created":1787086655,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000014","completion":"0.0000044"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"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...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/z-ai/glm-5v-turbo","canonical_slug":"z-ai/glm-5v-turbo-20260401","name":"Z.ai: GLM 5V Turbo","created":1775061458,"context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Other"},"pricing":{"prompt":"0.0000012","completion":"0.000004"},"top_provider":{"context_length":202752,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"hugging_face_id":"","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,...","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~anthropic/claude-fable-latest","canonical_slug":"~anthropic/claude-fable-latest","name":"Anthropic: Claude Fable Latest","created":1781029944,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.00001","completion":"0.00005"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"description":"This model always redirects to the latest model in the Claude Fable family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~anthropic/claude-haiku-latest","canonical_slug":"~anthropic/claude-haiku-latest","name":"Anthropic Claude Haiku Latest","created":1777318492,"context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000001","completion":"0.000005"},"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"description":"This model always redirects to the latest model in the Anthropic Claude Haiku family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~anthropic/claude-opus-latest","canonical_slug":"~anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","created":1776795361,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000005","completion":"0.000025"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"hugging_face_id":"","description":"This model always redirects to the latest model in the Claude Opus family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~anthropic/claude-sonnet-latest","canonical_slug":"~anthropic/claude-sonnet-latest","name":"Anthropic Claude Sonnet Latest","created":1777318368,"context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000002","completion":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"description":"This model always redirects to the latest model in the Anthropic Claude Sonnet family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~deepseek/deepseek-v4-flash-latest","canonical_slug":"~deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","created":1785606009,"context_length":1310720,"max_input_tokens":262144,"max_output_tokens":262144,"architecture":{"modality":"text-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000000065","completion":"0.00000018"},"top_provider":{"context_length":1048576,"max_completion_tokens":1048576},"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"],"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~google/gemini-flash-latest","canonical_slug":"~google/gemini-flash-latest","name":"Google Gemini Flash Latest","created":1777318398,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000000375","completion":"0.000001875","image":"0.000000375"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"description":"This model always redirects to the latest model in the Google Gemini Flash family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~google/gemini-pro-latest","canonical_slug":"~google/gemini-pro-latest","name":"Google Gemini Pro Latest","created":1777318451,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"architecture":{"modality":"text+image+file+audio+video-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000002","completion":"0.000012","image":"0.000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"description":"This model always redirects to the latest model in the Google Gemini Pro family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~moonshotai/kimi-latest","canonical_slug":"~moonshotai/kimi-latest","name":"MoonshotAI Kimi Latest","created":1777318428,"context_length":1048576,"max_input_tokens":974842,"max_output_tokens":974842,"architecture":{"modality":"text+image+video-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.0000026","completion":"0.000013"},"top_provider":{"context_length":974842,"max_completion_tokens":974842},"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"],"default_parameters":{"top_p":0.95},"description":"This model always redirects to the latest model in the MoonshotAI Kimi family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~openai/gpt-latest","canonical_slug":"~openai/gpt-latest","name":"OpenAI GPT Latest","created":1777318334,"context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.0000025","completion":"0.000015"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"description":"This model always redirects to the latest model in the OpenAI GPT family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~openai/gpt-mini-latest","canonical_slug":"~openai/gpt-mini-latest","name":"OpenAI GPT Mini Latest","created":1777318471,"context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.00000075","completion":"0.0000045"},"top_provider":{"context_length":400000,"max_completion_tokens":128000},"supported_parameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"description":"This model always redirects to the latest model in the OpenAI GPT Mini family.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~x-ai/grok-latest","canonical_slug":"~x-ai/grok-latest","name":"xAI: Grok Latest","created":1783519360,"context_length":500000,"max_input_tokens":500000,"architecture":{"modality":"text+image+file-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.000002","completion":"0.000006"},"top_provider":{"context_length":500000},"supported_parameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"description":"This model always redirects to the latest Grok model from xAI.","owned_by":"","modalities":["unknown"]},{"id":"openrouter/~z-ai/glm-latest","canonical_slug":"~z-ai/glm-latest","name":"Z.ai: GLM Latest","created":1787151053,"context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"architecture":{"modality":"text-\u003etext","tokenizer":"Router"},"pricing":{"prompt":"0.0000014","completion":"0.0000044"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":1,"top_p":0.95},"description":"This model always redirects to the latest GLM model from Z.ai.","owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-fable-5","name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000100000","completion":"0.0000500000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-haiku-4-5","name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":8192,"pricing":{"prompt":"0.0000010000","completion":"0.0000050000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-4-1","name":"claude-opus-4-1","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"pricing":{"prompt":"0.0000150000","completion":"0.0000750000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-4-5","name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-4-6","name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-4-7","name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-4-8","name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-opus-5","name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000050000","completion":"0.0000250000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-sonnet-4-5","name":"claude-sonnet-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000030000","completion":"0.0000150000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-sonnet-4-6","name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"pricing":{"prompt":"0.0000030000","completion":"0.0000150000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/claude-sonnet-5","name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000020000","completion":"0.0000100000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/codestral-2","name":"codestral-2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000003000","completion":"0.0000009000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-1.5-pro-002","name":"gemini-1.5-pro-002","owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.0-flash-001","name":"gemini-2.0-flash-001","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":8192,"pricing":{"prompt":"0.0000001500","completion":"0.0000006000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.0-flash-lite-001","name":"gemini-2.0-flash-lite-001","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":8192,"pricing":{"prompt":"0.0000000750","completion":"0.0000003000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-flash","name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"pricing":{"prompt":"0.0000003000","completion":"0.0000025000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"pricing":{"prompt":"0.0000001000","completion":"0.0000004000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-flash-preview-04-17","name":"gemini-2.5-flash-preview-04-17","owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-flash-tts","name":"gemini-2.5-flash-tts","owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-pro","name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"pricing":{"prompt":"0.0000012500","completion":"0.0000100000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-pro-exp-03-25","name":"gemini-2.5-pro-exp-03-25","owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-2.5-pro-tts","name":"gemini-2.5-pro-tts","owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3-flash-preview","name":"gemini-3-flash-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"pricing":{"prompt":"0.0000005000","completion":"0.0000030000"},"owned_by":"","modalities":["llm","vision"]},{"id":"vertex/gemini-3-pro-image","name":"gemini-3-pro-image","context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"pricing":{"prompt":"0.0000020000","completion":"0.0000120000","image":"0.0011000000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.1-flash-image","name":"gemini-3.1-flash-image","context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"pricing":{"prompt":"0.0000005000","completion":"0.0000030000","image":"0.0005600000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.1-flash-image-preview","name":"gemini-3.1-flash-image-preview","context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"pricing":{"prompt":"0.0000005000","completion":"0.0000030000","image":"0.0005600000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000002500","completion":"0.0000015000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.1-flash-lite-image","name":"gemini-3.1-flash-lite-image","context_length":65536,"max_input_tokens":65536,"max_output_tokens":4096,"pricing":{"prompt":"0.0000002500","completion":"0.0000015000","image":"0.0002800000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.1-pro-preview","name":"gemini-3.1-pro-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000020000","completion":"0.0000120000"},"owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"vertex/gemini-3.5-flash","name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000015000","completion":"0.0000090000"},"owned_by":"","modalities":["llm","vision","reasoning"]},{"id":"vertex/gemini-3.5-flash-lite","name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000003000","completion":"0.0000025000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.6-flash","name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000007500","completion":"0.0000037500"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-3.7-flash","name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"pricing":{"prompt":"0.0000007500","completion":"0.0000037500"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-embedding-2","name":"gemini-embedding-2","context_length":8192,"max_input_tokens":8192,"pricing":{"prompt":"0.0000002000","completion":"0.0000000000","image":"0.0001200000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/gemini-live-2.5-flash-native-audio","name":"gemini-live-2.5-flash-native-audio","owned_by":"","modalities":["unknown"]},{"id":"vertex/mistral-medium-3","name":"mistral-medium-3","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8191,"pricing":{"prompt":"0.0000004000","completion":"0.0000020000"},"owned_by":"","modalities":["unknown"]},{"id":"vertex/mistral-ocr-2505","name":"mistral-ocr-2505","pricing":{},"owned_by":"","modalities":["unknown"]},{"id":"vertex/mistral-small-2503","name":"mistral-small-2503","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"pricing":{"prompt":"0.0000001000","completion":"0.0000003000"},"owned_by":"","modalities":["unknown"]}],"extra_fields":{"request_type":"list_models","latency":1060,"chunk_index":0}}