{"models":[{"id":"elevenlabs/scribe-v2","label":"Scribe v2","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:16:30.000Z","description":"ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.","modality":"audio->transcription","inputModalities":"audio","outputModalities":"transcription","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withoutAudio":{"default":0.0000611111111111}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"deepseek/deepseek-v4.1-flash-1017","label":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.21225,"outputPrice":0.84825,"originalInputPrice":0.283,"originalOutputPrice":1.131,"discount":25,"contextLength":1048576,"releasedAt":"2026-10-17T08:27:04.000Z","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.021,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":28.6,"rankIntelligence":67,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":97,"totalSpeed":386,"rankInputPrice":153,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low","none"],"default_effort":"high","default_enabled":true,"mandatory":false}},{"id":"z-ai/glm-5.3-flash-abliterated","label":"GLM 5.3 Flash Abliterated","provider":"Zhipu AI","category":["fast","cheap","long-context"],"inputPrice":0.24,"outputPrice":1,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":null,"description":"Abliterated / uncensored version: safety refusals removed, NOT the same as the regular model. 已移除安全限制的版本，與正常版不同。","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.06,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"deepseek/deepseek-v4.1-flash-1017-abliterated","label":"DeepSeek V4.1 Flash 1017 Abliterated","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.24,"outputPrice":0.9,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":null,"description":"Abliterated / uncensored version: safety refusals removed, NOT the same as the regular model. 已移除安全限制的版本，與正常版不同。","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.05,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"z-ai/glm-5.3-abliterated","label":"GLM 5.3 Abliterated","provider":"Zhipu AI","category":["fast","long-context"],"inputPrice":2,"outputPrice":4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":null,"description":"Abliterated / uncensored version: safety refusals removed, NOT the same as the regular model. 已移除安全限制的版本，與正常版不同。","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.3,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-turbo-v2","label":"Eleven Turbo v2","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:17:18.000Z","description":"Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has a 30,000-character...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-flash-v2.5","label":"Eleven Flash v2.5","provider":"Elevenlabs","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:17:30.000Z","description":"Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit.","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-v3","label":"Eleven v3","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:17:52.000Z","description":"Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit.","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":80,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-flash-v2","label":"Eleven Flash v2","provider":"Elevenlabs","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:16:47.000Z","description":"Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-turbo-v2.5","label":"Eleven Turbo v2.5","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:16:58.000Z","description":"Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English languages, supports 32 languages, and has a 40,000-character...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-v4-turbo","label":"Eleven v4 Turbo","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:18:00.000Z","description":"Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-multilingual-v2","label":"Eleven Multilingual v2","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:17:12.000Z","description":"Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":80,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-v4","label":"Eleven v4","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:18:05.000Z","description":"Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":80,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/eleven-v3-conversational","label":"Eleven v3 Conversational","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:17:46.000Z","description":"Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request...","modality":"text->speech","inputModalities":"text","outputModalities":"speech","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"character","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":40,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.8-max","label":"Qwen3.8 Max","provider":"Qwen","category":["long-context"],"inputPrice":1.32,"outputPrice":3.9608,"originalInputPrice":1.65,"originalOutputPrice":4.951,"discount":20,"contextLength":1000000,"releasedAt":"2026-08-03T04:33:32.000Z","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,...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.1648,"cacheWritePrice":2,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh","default_enabled":true,"mandatory":true}},{"id":"minimax/minimax-m3","label":"MiniMax M3","provider":"MiniMax","category":["fast","cheap","long-context"],"inputPrice":0.3,"outputPrice":1.2,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-05-31T16:36:14.000Z","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,...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.06,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":18.9,"rankIntelligence":87,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":114,"totalSpeed":386,"rankInputPrice":153,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":524288,"input":0.6,"output":2.4,"cacheRead":0.12,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"z-ai/glm-5v-turbo","label":"GLM 5V Turbo","provider":"Zhipu AI","category":["long-context"],"inputPrice":1.2,"outputPrice":4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":202752,"releasedAt":"2026-04-01T16:37:38.000Z","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,...","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,response_format,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.24,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"deepseek/deepseek-v4-pro","label":"DeepSeek V4 Pro","provider":"DeepSeek","category":["long-context"],"inputPrice":1.65,"outputPrice":3.301,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-04-24T03:17:59.000Z","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,...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.138,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":23.1,"rankIntelligence":80,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":235,"totalSpeed":386,"rankInputPrice":301,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high"],"default_effort":"high","mandatory":false}},{"id":"moonshotai/kimi-k3","label":"Kimi K3","provider":"Moonshot AI","category":["long-context"],"inputPrice":2.827,"outputPrice":14.133,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-07-16T15:30:58.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.283,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low","none"],"default_effort":"max","default_enabled":true,"mandatory":false}},{"id":"deepseek/deepseek-v4-flash","label":"DeepSeek V4 Flash","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.14,"outputPrice":0.28,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-04-24T03:17:46.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.028,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":129,"totalSpeed":386,"rankInputPrice":89,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high"],"default_effort":"high","mandatory":false}},{"id":"google/gemini-4-argon","label":"Gemini 4 Argon","provider":"Google","category":["fast","long-context"],"inputPrice":2,"outputPrice":10,"originalInputPrice":4,"originalOutputPrice":20,"discount":50,"contextLength":1048576,"releasedAt":"2026-10-13T16:04:37.000Z","description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","modality":"text+image+file+audio+video->text","inputModalities":"audio,file,image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.1,"cacheWritePrice":0.1875,"reasoningOutputPrice":5,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":50.4,"rankIntelligence":20,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":212,"totalSpeed":386,"rankInputPrice":390,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","mandatory":true}},{"id":"qwen/qwen3.7-plus","label":"Qwen3.7 Plus","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.256,"outputPrice":1.024,"originalInputPrice":0.32,"originalOutputPrice":1.28,"discount":20,"contextLength":1000000,"releasedAt":"2026-06-03T13:03:03.000Z","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...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0448,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":[{"abovePromptTokens":256000,"input":0.7679999999999999,"output":3.0719999999999996,"cacheRead":null,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"google/gemini-3.1-flash-lite-preview","label":"Gemini 3.1 Flash Lite Preview","provider":"Google","category":["fast","cheap","long-context"],"inputPrice":0.25,"outputPrice":1.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-03-03T04:37:53.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.025,"cacheWritePrice":0.083333333,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":6.2,"rankIntelligence":108,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":9,"totalSpeed":386,"rankInputPrice":135,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3.7-max","label":"Qwen3.7 Max","provider":"Qwen","category":["long-context"],"inputPrice":1.32,"outputPrice":3.9608,"originalInputPrice":1.65,"originalOutputPrice":4.951,"discount":20,"contextLength":1000000,"releasedAt":"2026-05-21T15:21:01.000Z","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,...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.132,"cacheWritePrice":1.475,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"openai/gpt-5.3-codex","label":"GPT-5.3-Codex","provider":"OpenAI","category":["long-context"],"inputPrice":1.75,"outputPrice":14,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":"2026-02-24T18:52:44.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.175,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":191,"totalSpeed":386,"rankInputPrice":314,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","mandatory":false}},{"id":"google/gemini-3.1-pro-preview","label":"Gemini 3.1 Pro Preview","provider":"Google","category":["fast","long-context"],"inputPrice":1.8,"outputPrice":10.8,"originalInputPrice":2,"originalOutputPrice":12,"discount":10,"contextLength":1048576,"releasedAt":"2026-02-19T14:00:27.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"audio,file,image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.18,"cacheWritePrice":0.3375,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":124,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":3.6,"output":16.200000000000003,"cacheRead":0.36,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","mandatory":true}},{"id":"anthropic/claude-sonnet-4.6","label":"Claude Sonnet 4.6","provider":"Anthropic","category":["flagship","coding","long-context"],"inputPrice":3,"outputPrice":15,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-02-17T15:43:10.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.3,"cacheWritePrice":3.75,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":352,"totalSpeed":386,"rankInputPrice":378,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","medium","low"],"default_effort":"medium","mandatory":false}},{"id":"anthropic/claude-opus-4.6","label":"Claude Opus 4.6","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":5,"outputPrice":25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-02-04T15:30:50.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":6.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":364,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","medium","low"],"default_effort":"high","default_enabled":false,"supports_max_tokens":true,"mandatory":false}},{"id":"alibaba/wan3.0","label":"Wan3.0","provider":"Alibaba","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.05,"720p":0.1,"1080p":0.2},"withoutAudio":{"480p":0.05,"720p":0.1,"1080p":0.2}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/veo-3.1","label":"Veo 3.1","provider":"Google","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-03-23T14:45:48.494Z","description":"Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound. Supports scene extension (up to 20 chained clips for 140+ second narratives), frames-to-video transitions between two images, vertical video for Shorts, and 4K upscaling.","modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v","supportedParameters":"max_tokens,response_format,seed,temperature,top_p","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"4k":0.7,"720p":0.4,"1080p":0.4},"withoutAudio":{"4k":0.4,"720p":0.2,"1080p":0.2}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance/seedance-2.5","label":"Seedance 2.5","provider":"ByteDance","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":null,"description":"Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and first-and-last-frame control, up to 50 image, video, and audio reference assets, optional generated audio, and multilingual audiovisual generation.","modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v","supportedParameters":"frequency_penalty","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.1028056,"720p":0.234,"1080p":0.57},"withoutAudio":{"480p":0.1028056,"720p":0.234,"1080p":0.57}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"x-ai/grok-imagine-video","label":"Grok Imagine Video","provider":"xAI","category":["creative","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.07,"720p":0.07},"withoutAudio":{"480p":0.07,"720p":0.07}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance/seedance-2.0","label":"Seedance 2.0","provider":"ByteDance","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-04-15T00:02:42.904Z","description":"Seedance 2.0 is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It is particularly strong at preserving character consistency, visual style, and camera movement from reference material. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024","modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v","supportedParameters":"frequency_penalty","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.072,"720p":0.16,"1080p":0.36},"withoutAudio":{"480p":0.072,"720p":0.16,"1080p":0.36}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance/seedance-2.0-mini","label":"Seedance 2.0 Mini","provider":"ByteDance","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.04,"720p":0.08},"withoutAudio":{"480p":0.04,"720p":0.08}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"minimax/minimax-h3","label":"MiniMax H3","provider":"MiniMax","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.08,"1080p":0.14},"withoutAudio":{"720p":0.08,"1080p":0.14}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"x-ai/grok-imagine-video-1.5","label":"Grok Imagine Video 1.5","provider":"xAI","category":["creative","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.14,"720p":0.14},"withoutAudio":{"480p":0.14,"720p":0.14}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.7-flash","label":"Qwen3.7 Flash","provider":"Qwen","category":["fast","cheap","long-context"],"inputPrice":0.03,"outputPrice":0.13,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-07-27T22:16:01.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.006,"cacheWritePrice":0.038,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":[{"abovePromptTokens":32768,"input":0.1,"output":0.4,"cacheRead":null,"cacheWrite":null},{"abovePromptTokens":262144,"input":0.2,"output":0.8,"cacheRead":null,"cacheWrite":null}],"isFree":true,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"supports_max_tokens":true,"mandatory":false}},{"id":"qwen/qwen3-embedding-4b","label":"Qwen3 Embedding 4B","provider":"Qwen","category":["cheap"],"inputPrice":0.02,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2025-10-28T14:48:42.000Z","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.5-35b-a3b","label":"Qwen3.5-35B-A3B","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.25,"outputPrice":1,"originalInputPrice":0.3125,"originalOutputPrice":1.25,"discount":20,"contextLength":262144,"releasedAt":"2026-02-25T21:10:22.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"openai/gpt-oss-120b","label":"GPT-OSS 120B","provider":"OpenAI","category":["cheap"],"inputPrice":0.15,"outputPrice":0.6,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-08-05T17:17:11.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":3.8,"rankIntelligence":116,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":40,"totalSpeed":386,"rankInputPrice":92,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","mandatory":true}},{"id":"google/gemma-3-4b-it","label":"Gemma 3 4B","provider":"Google","category":["cheap"],"inputPrice":0.05,"outputPrice":0.1,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-03-13T22:38:30.000Z","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,...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,logit_bias,max_tokens,min_p,presence_penalty,repetition_penalty,response_format,seed,stop,structured_outputs,temperature,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.5-27b","label":"Qwen3.5-27B","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.208,"outputPrice":2.08,"originalInputPrice":0.26,"originalOutputPrice":2.6,"discount":20,"contextLength":262144,"releasedAt":"2026-02-25T21:10:10.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"z-ai/glm-4.7-flash","label":"GLM 4.7 Flash","provider":"Zhipu AI","category":["fast","cheap","long-context"],"inputPrice":0.0605,"outputPrice":0.4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":200000,"releasedAt":"2026-01-19T14:45:13.000Z","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,...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.01,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":135,"totalSpeed":386,"rankInputPrice":37,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"openai/gpt-oss-safeguard-20b","label":"GPT-OSS Safeguard 20B","provider":"OpenAI","category":["cheap"],"inputPrice":0.075,"outputPrice":0.3,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-10-29T15:47:16.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0375,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":true}},{"id":"openai/gpt-6-luna","label":"GPT-6 Luna","provider":"OpenAI","category":["cheap","long-context"],"inputPrice":0.09,"outputPrice":0.45,"originalInputPrice":0.1,"originalOutputPrice":0.5,"discount":10,"contextLength":1050000,"releasedAt":"2026-09-22T18:13:06.000Z","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.009,"cacheWritePrice":0.1125,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":18.5,"rankIntelligence":89,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":163,"totalSpeed":386,"rankInputPrice":46,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":0.18,"output":0.675,"cacheRead":0.018,"cacheWrite":0.225}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"z-ai/glm-5.3-flash","label":"GLM 5.3 Flash","provider":"Zhipu AI","category":["fast","cheap","long-context"],"inputPrice":0.15,"outputPrice":0.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-08-26T13:59:01.000Z","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.03,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":27.8,"rankIntelligence":70,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":303,"totalSpeed":386,"rankInputPrice":92,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low"],"default_effort":"max","default_enabled":true,"mandatory":true}},{"id":"qwen/qwen3-next-80b-a3b-instruct","label":"Qwen3 Next 80B A3B Instruct","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.09,"outputPrice":1.1,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-09-11T17:36:53.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.07,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"anthropic/claude-haiku-5.5","label":"Claude Haiku 5.5","provider":"Anthropic","category":["fast","cheap","long-context"],"inputPrice":0.1,"outputPrice":0.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-10-07T18:31:23.000Z","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.01,"cacheWritePrice":0.125,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":24.6,"rankIntelligence":76,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":66,"totalSpeed":386,"rankInputPrice":46,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":100000,"input":0.5,"output":2.5,"cacheRead":0.05,"cacheWrite":0.625}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","mandatory":false}},{"id":"qwen/qwen3.6-35b-a3b","label":"Qwen3.6 35B A3B","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.3,"outputPrice":1.8,"originalInputPrice":0.375,"originalOutputPrice":2.25,"discount":20,"contextLength":262144,"releasedAt":"2026-04-27T03:24:15.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.04,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3.5-397b-a17b","label":"Qwen3.5 397B A17B","provider":"Qwen","category":["long-context"],"inputPrice":0.44,"outputPrice":2.8,"originalInputPrice":0.55,"originalOutputPrice":3.5,"discount":20,"contextLength":262144,"releasedAt":"2026-02-16T06:23:38.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.24,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"xiaomi/mimo-v2.6-flash","label":"MiMo-V2.6-Flash","provider":"Xiaomi","category":["fast","cheap","long-context"],"inputPrice":0.14,"outputPrice":0.28,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-09-21T20:07:44.000Z","description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","modality":"text+image+video+audio->text","inputModalities":"text,image,video,audio","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0028,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":26.7,"rankIntelligence":71,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":365,"totalSpeed":386,"rankInputPrice":89,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-v4.1-flash","label":"DeepSeek V4.1 Flash","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.21225,"outputPrice":0.84825,"originalInputPrice":0.283,"originalOutputPrice":1.131,"discount":25,"contextLength":1048576,"releasedAt":"2026-09-10T06:21:25.000Z","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.021,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":29,"totalSpeed":386,"rankInputPrice":152,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low","none"],"default_effort":"high","default_enabled":true,"mandatory":false}},{"id":"openai/gpt-5.6-luna","label":"GPT-5.6 Luna","provider":"OpenAI","category":["cheap","long-context"],"inputPrice":0.18,"outputPrice":1.08,"originalInputPrice":0.2,"originalOutputPrice":1.2,"discount":10,"contextLength":1050000,"releasedAt":"2026-07-09T09:54:24.000Z","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...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.018,"cacheWritePrice":0.225,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":161,"totalSpeed":386,"rankInputPrice":110,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":0.36,"output":2.16,"cacheRead":0.036,"cacheWrite":0.45}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3.6-plus","label":"Qwen3.6 Plus","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.26,"outputPrice":1.56,"originalInputPrice":0.325,"originalOutputPrice":1.95,"discount":20,"contextLength":1000000,"releasedAt":"2026-04-02T12:39:17.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0224,"cacheWritePrice":0.325,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":[{"abovePromptTokens":256000,"input":1.04,"output":3.12,"cacheRead":null,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-v4-flash-0731","label":"DeepSeek V4 Flash 0731","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.44,"outputPrice":1.32,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-07-31T06:21:48.000Z","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....","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.044,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":129,"totalSpeed":386,"rankInputPrice":89,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low"],"default_effort":"high","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3-coder-flash","label":"Qwen3 Coder Flash","provider":"Qwen","category":["fast","cheap","long-context"],"inputPrice":0.24,"outputPrice":1.2,"originalInputPrice":0.3,"originalOutputPrice":1.5,"discount":20,"contextLength":1000000,"releasedAt":"2025-09-17T13:25:36.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,logprobs,max_tokens,presence_penalty,response_format,seed,stop,temperature,tool_choice,tools,top_k,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0312,"cacheWritePrice":0.195,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":[{"abovePromptTokens":32768,"input":0.4,"output":2,"cacheRead":0.052,"cacheWrite":0.325},{"abovePromptTokens":131072,"input":0.6399999999999999,"output":3.2,"cacheRead":0.0832,"cacheWrite":0.5200000000000001},{"abovePromptTokens":262144,"input":1.2799999999999998,"output":7.68,"cacheRead":0.1664,"cacheWrite":1.0400000000000003}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-3.1-flash-lite","label":"Gemini 3.1 Flash Lite","provider":"Google","category":["fast","cheap","long-context"],"inputPrice":0.25,"outputPrice":1.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-05-07T15:47:08.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.03,"cacheWritePrice":0.08333,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":6.2,"rankIntelligence":108,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":9,"totalSpeed":386,"rankInputPrice":135,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","label":"Qwen3 VL 235B A22B Instruct","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.2,"outputPrice":0.88,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-09-23T23:04:47.000Z","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...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.11,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"z-ai/glm-4.5-air","label":"GLM 4.5 Air","provider":"Zhipu AI","category":["cheap"],"inputPrice":0.13,"outputPrice":0.85,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-07-25T19:20:58.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,presence_penalty,reasoning,repetition_penalty,seed,stop,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.025,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":229,"totalSpeed":386,"rankInputPrice":105,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-chat-v3.1","label":"DeepSeek V3.1","provider":"DeepSeek","category":["coding","cheap"],"inputPrice":0.21,"outputPrice":0.79,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":163840,"releasedAt":"2025-08-21T12:33:48.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.13,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"google/gemini-3.5-flash-lite","label":"Gemini 3.5 Flash Lite","provider":"Google","category":["fast","cheap","long-context"],"inputPrice":0.27,"outputPrice":2.25,"originalInputPrice":0.3,"originalOutputPrice":2.5,"discount":10,"contextLength":1048576,"releasedAt":"2026-07-21T15:12:06.000Z","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.","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.027,"cacheWritePrice":0.074997,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":11.7,"rankIntelligence":101,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":7,"totalSpeed":386,"rankInputPrice":153,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal","default_enabled":true,"mandatory":true}},{"id":"qwen/qwen3.5-122b-a10b","label":"Qwen3.5-122B-A10B","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.32,"outputPrice":2.56,"originalInputPrice":0.4,"originalOutputPrice":3.2,"discount":20,"contextLength":262144,"releasedAt":"2026-02-25T21:09:49.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-chat","label":"DeepSeek Chat","provider":"DeepSeek","category":["coding","cheap"],"inputPrice":0.26,"outputPrice":0.38,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":163840,"releasedAt":"2024-12-26T19:28:40.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.13,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.6-27b","label":"Qwen3.6 27B","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.48,"outputPrice":2.88,"originalInputPrice":0.6,"originalOutputPrice":3.6,"discount":20,"contextLength":262144,"releasedAt":"2026-04-27T01:57:44.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.12,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":true,"mandatory":false}},{"id":"z-ai/glm-4.6v","label":"GLM 4.6V","provider":"Zhipu AI","category":["cheap"],"inputPrice":0.3,"outputPrice":0.9,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-12-08T15:24:22.000Z","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...","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,presence_penalty,reasoning,repetition_penalty,response_format,seed,stop,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.055,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":259,"totalSpeed":386,"rankInputPrice":153,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"qwen/qwen3.8-27b","label":"Qwen3.8 27B","provider":"Qwen","category":["long-context"],"inputPrice":0.4,"outputPrice":2.4,"originalInputPrice":0.5,"originalOutputPrice":3,"discount":20,"contextLength":1024000,"releasedAt":"2026-08-14T15:55:10.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.08,"cacheWritePrice":0.552,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh","default_enabled":true,"mandatory":false}},{"id":"z-ai/glm-5.3-flashx","label":"GLM 5.3 FlashX","provider":"Zhipu AI","category":["fast","cheap","long-context"],"inputPrice":0.37,"outputPrice":1.25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-09-18T15:07:00.000Z","description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.075,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low"],"default_effort":"max","default_enabled":true,"mandatory":true}},{"id":"google/gemini-3-flash-preview","label":"Gemini 3 Flash Preview","provider":"Google","category":["fast","cheap","long-context"],"inputPrice":0.45,"outputPrice":2.7,"originalInputPrice":0.5,"originalOutputPrice":3,"discount":10,"contextLength":1048576,"releasedAt":"2025-12-17T15:57:58.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,file,audio,video","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.045,"cacheWritePrice":0.075,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":37,"totalSpeed":386,"rankInputPrice":205,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium","mandatory":false}},{"id":"xiaomi/mimo-v2.6-pro","label":"MiMo-V2.6-Pro","provider":"Xiaomi","category":["cheap","long-context"],"inputPrice":0.435,"outputPrice":0.87,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-09-21T20:07:39.000Z","description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","modality":"text+image+video+audio->text","inputModalities":"text,image,video,audio","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0036,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":29.9,"rankIntelligence":62,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":310,"totalSpeed":386,"rankInputPrice":201,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-r1-0528","label":"DeepSeek R1 0528","provider":"DeepSeek","category":["reasoning","cheap"],"inputPrice":0.5,"outputPrice":2.15,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":163840,"releasedAt":"2025-05-28T17:59:30.000Z","description":"May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.35,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":true}},{"id":"deepseek/deepseek-r1","label":"DeepSeek R1","provider":"DeepSeek","category":["reasoning"],"inputPrice":0.5,"outputPrice":2.15,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":64000,"releasedAt":"2025-01-20T13:51:35.000Z","description":"DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,presence_penalty,reasoning,repetition_penalty,response_format,seed,stop,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.35,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":376,"totalSpeed":386,"rankInputPrice":319,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":true}},{"id":"google/gemini-3.7-flash","label":"Gemini 3.7 Flash","provider":"Google","category":["fast","long-context"],"inputPrice":0.75,"outputPrice":3.75,"originalInputPrice":1.5,"originalOutputPrice":7.5,"discount":50,"contextLength":1048576,"releasedAt":"2026-08-13T17:03:01.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.075,"cacheWritePrice":0.041666667,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"openai/gpt-5.4-mini","label":"GPT-5.4 Mini","provider":"OpenAI","category":["fast","long-context"],"inputPrice":0.675,"outputPrice":4.05,"originalInputPrice":0.75,"originalOutputPrice":4.5,"discount":10,"contextLength":400000,"releasedAt":"2026-03-17T11:49:38.000Z","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,...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0675,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":38,"totalSpeed":386,"rankInputPrice":242,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":false,"mandatory":false}},{"id":"google/gemini-3.8-flash","label":"Gemini 3.8 Flash","provider":"Google","category":["fast","long-context"],"inputPrice":0.75,"outputPrice":3.75,"originalInputPrice":1.5,"originalOutputPrice":7.5,"discount":50,"contextLength":1048576,"releasedAt":"2026-09-02T15:14:16.000Z","description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.075,"cacheWritePrice":0.041666667,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":30.1,"rankIntelligence":61,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":138,"totalSpeed":386,"rankInputPrice":242,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"google/gemini-3.6-flash","label":"Gemini 3.6 Flash","provider":"Google","category":["fast","long-context"],"inputPrice":0.675,"outputPrice":3.375,"originalInputPrice":0.75,"originalOutputPrice":3.75,"discount":10,"contextLength":1048576,"releasedAt":"2026-07-21T15:12:13.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0675,"cacheWritePrice":0.074997,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":45,"totalSpeed":386,"rankInputPrice":242,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"moonshotai/kimi-k2-0905","label":"Kimi K2 0905","provider":"Moonshot AI","category":["long-context"],"inputPrice":0.6,"outputPrice":2.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-09-04T21:25:47.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,max_tokens,presence_penalty,repetition_penalty,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"z-ai/glm-4.5","label":"GLM 4.5","provider":"Zhipu AI","category":["flagship"],"inputPrice":0.6,"outputPrice":2.2,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-07-25T19:22:27.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,response_format,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.11,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"z-ai/glm-4.5v","label":"GLM 4.5V","provider":"Zhipu AI","category":["flagship"],"inputPrice":0.6,"outputPrice":1.8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":65536,"releasedAt":"2025-08-11T14:24:48.000Z","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,...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,presence_penalty,reasoning,repetition_penalty,response_format,seed,stop,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.11,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":276,"totalSpeed":386,"rankInputPrice":224,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"z-ai/glm-4.6","label":"GLM 4.6","provider":"Zhipu AI","category":["long-context"],"inputPrice":0.6,"outputPrice":2.2,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":204800,"releasedAt":"2025-09-30T12:32:56.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.11,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":371,"totalSpeed":386,"rankInputPrice":223,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"deepseek/deepseek-v4-pro-0813","label":"DeepSeek V4 Pro 0813","provider":"DeepSeek","category":["long-context"],"inputPrice":0.8904,"outputPrice":2.6712,"originalInputPrice":1.272,"originalOutputPrice":3.816,"discount":30,"contextLength":1048576,"releasedAt":"2026-08-12T15:42:44.000Z","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.0889,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":23.1,"rankIntelligence":80,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":235,"totalSpeed":386,"rankInputPrice":301,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low"],"default_effort":"high","mandatory":false}},{"id":"z-ai/glm-5.3","label":"GLM 5.3","provider":"Zhipu AI","category":["long-context"],"inputPrice":1.0179,"outputPrice":3.96,"originalInputPrice":1.131,"originalOutputPrice":4.4,"discount":10,"contextLength":1048576,"releasedAt":"2026-08-18T20:57:35.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2547,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":31.7,"rankIntelligence":54,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":218,"totalSpeed":386,"rankInputPrice":303,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low"],"default_effort":"max","default_enabled":true,"mandatory":true}},{"id":"x-ai/grok-build-0.1","label":"Grok Build 0.1","provider":"xAI","category":["creative","long-context"],"inputPrice":0.9,"outputPrice":1.8,"originalInputPrice":1,"originalOutputPrice":2,"discount":10,"contextLength":256000,"releasedAt":"2026-05-20T17:28:43.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.18,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":192,"totalSpeed":386,"rankInputPrice":256,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":1.8,"output":3.6,"cacheRead":0.36,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":true}},{"id":"anthropic/claude-haiku-4.5","label":"Claude Haiku 4.5","provider":"Anthropic","category":["fast","long-context"],"inputPrice":1,"outputPrice":5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":200000,"releasedAt":"2025-10-15T17:00:38.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.1,"cacheWritePrice":1.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":226,"totalSpeed":386,"rankInputPrice":256,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"x-ai/grok-4.3","label":"Grok 4.3","provider":"xAI","category":["creative","long-context"],"inputPrice":1.125,"outputPrice":2.25,"originalInputPrice":1.25,"originalOutputPrice":2.5,"discount":10,"contextLength":1000000,"releasedAt":"2026-04-30T23:30:21.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.18,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":260,"totalSpeed":386,"rankInputPrice":275,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":2.25,"output":4.5,"cacheRead":0.36,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","none"],"default_effort":"low","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3.8-27b-abliterated-cyber","label":"Qwen3.8 27B Abliterated Cyber","provider":"Qwen","category":["fast","long-context"],"inputPrice":1,"outputPrice":6,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":256000,"releasedAt":null,"description":"Abliterated / uncensored version: safety refusals removed, NOT the same as the regular model. 已移除安全限制的版本，與正常版不同。","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-3.5-flash","label":"Gemini 3.5 Flash","provider":"Google","category":["fast","long-context"],"inputPrice":1.35,"outputPrice":8.1,"originalInputPrice":1.5,"originalOutputPrice":9,"discount":10,"contextLength":1048576,"releasedAt":"2026-05-19T12:30:00.000Z","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...","modality":"text+image+file+audio+video->text","inputModalities":"text,image,video,file,audio","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.135,"cacheWritePrice":0.074997,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":52,"totalSpeed":386,"rankInputPrice":307,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"qwen/qwen3.8-2.4t-a95b","label":"Qwen3.8 2.4T A95B","provider":"Qwen","category":["long-context"],"inputPrice":1.6,"outputPrice":4.8,"originalInputPrice":2,"originalOutputPrice":6,"discount":20,"contextLength":1048576,"releasedAt":"2026-08-12T16:21:42.000Z","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, with 95 billion active parameters out of 2.4 trillion total. It is...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh","default_enabled":true,"mandatory":true}},{"id":"openai/gpt-6.1-sol","label":"GPT-6.1 Sol","provider":"OpenAI","category":["long-context"],"inputPrice":2,"outputPrice":10,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1050000,"releasedAt":"2026-09-29T17:28:02.000Z","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":2.5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":46.3,"rankIntelligence":29,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":305,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":4,"output":15,"cacheRead":0.4,"cacheWrite":5}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"openai/gpt-6-sol","label":"GPT-6 Sol","provider":"OpenAI","category":["long-context"],"inputPrice":1.8,"outputPrice":9,"originalInputPrice":2,"originalOutputPrice":10,"discount":10,"contextLength":1050000,"releasedAt":"2026-09-22T18:12:55.000Z","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.18,"cacheWritePrice":2.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":3.6,"output":13.5,"cacheRead":0.36,"cacheWrite":4.5}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"openai/gpt-5.6-terra","label":"GPT-5.6 Terra","provider":"OpenAI","category":["long-context"],"inputPrice":1.8,"outputPrice":10.8,"originalInputPrice":2,"originalOutputPrice":12,"discount":10,"contextLength":1050000,"releasedAt":"2026-07-09T09:54:17.000Z","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...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.18,"cacheWritePrice":2.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":187,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":3.6,"output":21.6,"cacheRead":0.36,"cacheWrite":4.5}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"x-ai/grok-4.6","label":"Grok 4.6","provider":"xAI","category":["creative","long-context"],"inputPrice":1.8,"outputPrice":5.4,"originalInputPrice":2,"originalOutputPrice":6,"discount":10,"contextLength":500000,"releasedAt":"2026-08-12T15:35:57.000Z","description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.45,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":255,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":3.6,"output":10.8,"cacheRead":0.9,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high","default_enabled":true,"mandatory":true}},{"id":"x-ai/grok-4.5","label":"Grok 4.5","provider":"xAI","category":["creative","long-context"],"inputPrice":1.8,"outputPrice":5.4,"originalInputPrice":2,"originalOutputPrice":6,"discount":10,"contextLength":500000,"releasedAt":"2026-07-08T15:05:54.000Z","description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.45,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":324,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":3.6,"output":10.8,"cacheRead":0.9,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"high","default_enabled":true,"mandatory":true}},{"id":"anthropic/claude-sonnet-5.5","label":"Claude Sonnet 5.5","provider":"Anthropic","category":["flagship","coding","long-context"],"inputPrice":2,"outputPrice":10,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-09-28T18:04:46.000Z","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":2.5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":41.5,"rankIntelligence":37,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":170,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","mandatory":true}},{"id":"anthropic/claude-sonnet-5","label":"Claude Sonnet 5","provider":"Anthropic","category":["flagship","coding","long-context"],"inputPrice":2,"outputPrice":10,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-06-30T18:11:23.000Z","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,...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":2.5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":274,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","default_enabled":true,"mandatory":false}},{"id":"openai/gpt-4o","label":"GPT-4o","provider":"OpenAI","category":["flagship"],"inputPrice":2.25,"outputPrice":9,"originalInputPrice":2.5,"originalOutputPrice":10,"discount":10,"contextLength":128000,"releasedAt":"2024-05-13T00:00:00.000Z","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 while being twice as...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":1.125,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":47,"totalSpeed":386,"rankInputPrice":371,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-5.4","label":"GPT-5.4","provider":"OpenAI","category":["long-context"],"inputPrice":2.25,"outputPrice":13.5,"originalInputPrice":2.5,"originalOutputPrice":15,"discount":10,"contextLength":1050000,"releasedAt":"2026-03-05T18:12:32.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.225,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":null,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":4.5,"output":20.25,"cacheRead":0.45,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":false,"mandatory":false}},{"id":"moonshotai/kimi-k3.1-pro","label":"Kimi K3.1 Pro","provider":"Moonshot AI","category":["long-context"],"inputPrice":2,"outputPrice":10,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-10-23T17:56:28.000Z","description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":2,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","high","low","none"],"default_effort":"max","default_enabled":true,"mandatory":false}},{"id":"qwen/qwen3.8-27b-abliterated","label":"Qwen3.8 27B Abliterated","provider":"Qwen","category":["fast"],"inputPrice":2.4,"outputPrice":18,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":null,"description":"Abliterated / uncensored version: safety refusals removed, NOT the same as the regular model. 已移除安全限制的版本，與正常版不同。","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":2.4,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"anthropic/claude-sonnet-4.5","label":"Claude Sonnet 4.5","provider":"Anthropic","category":["flagship","coding","long-context"],"inputPrice":3,"outputPrice":15,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2025-09-29T16:01:16.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.3,"cacheWritePrice":3.75,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":360,"totalSpeed":386,"rankInputPrice":378,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":6,"output":22.5,"cacheRead":0.6,"cacheWrite":7.5}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"anthropic/claude-opus-5.5","label":"Claude Opus 5.5","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":4,"outputPrice":20,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-09-22T16:32:12.000Z","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":59.1,"rankIntelligence":5,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":201,"totalSpeed":386,"rankInputPrice":390,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","mandatory":true}},{"id":"openai/gpt-5.6-sol","label":"GPT-5.6 Sol","provider":"OpenAI","category":["long-context"],"inputPrice":4.5,"outputPrice":27,"originalInputPrice":5,"originalOutputPrice":30,"discount":10,"contextLength":1050000,"releasedAt":"2026-07-09T09:54:10.000Z","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...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":"2026-02-16","maxCompletionTokens":128000,"cacheReadPrice":0.45,"cacheWritePrice":5.625,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":186,"totalSpeed":386,"rankInputPrice":390,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":9,"output":40.5,"cacheRead":0.9,"cacheWrite":11.25}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"anthropic/claude-opus-4.7","label":"Claude Opus 4.7","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":5,"outputPrice":25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-04-16T14:51:40.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":6.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":336,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","default_enabled":false,"mandatory":false}},{"id":"anthropic/claude-opus-5","label":"Claude Opus 5","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":5,"outputPrice":25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-07-24T17:02:24.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":6.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":326,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","default_enabled":true,"mandatory":false}},{"id":"anthropic/claude-opus-4.5","label":"Claude Opus 4.5","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":5,"outputPrice":25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":200000,"releasedAt":"2025-11-24T18:56:20.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_k,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":6.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":333,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"anthropic/claude-opus-4.8","label":"Claude Opus 4.8","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":5,"outputPrice":25,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-05-27T18:04:51.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":6.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":294,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","default_enabled":false,"mandatory":false}},{"id":"openai/gpt-5.5","label":"GPT-5.5","provider":"OpenAI","category":["long-context"],"inputPrice":5,"outputPrice":30,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1050000,"releasedAt":"2026-04-24T17:31:33.000Z","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...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":251,"totalSpeed":386,"rankInputPrice":408,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":10,"output":45,"cacheRead":1,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":true,"mandatory":false}},{"id":"openai/gpt-6-astra","label":"GPT-6 Astra","provider":"OpenAI","category":["long-context"],"inputPrice":9,"outputPrice":45,"originalInputPrice":10,"originalOutputPrice":50,"discount":10,"contextLength":1050000,"releasedAt":"2026-09-04T20:13:58.000Z","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","modality":"text+image+file->text","inputModalities":"file,image,text","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,tool_choice,tools","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.9,"cacheWritePrice":11.25,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":51.6,"rankIntelligence":18,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":356,"totalSpeed":386,"rankInputPrice":433,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":272000,"input":18,"output":67.5,"cacheRead":1.8,"cacheWrite":22.5}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","default_enabled":true,"mandatory":true}},{"id":"anthropic/claude-fable-5.1","label":"Claude Fable 5.1","provider":"Anthropic","category":["long-context"],"inputPrice":10,"outputPrice":50,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-09-01T18:03:58.000Z","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.25,"cacheWritePrice":12.5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":47.2,"rankIntelligence":27,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":304,"totalSpeed":386,"rankInputPrice":433,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","mandatory":true}},{"id":"anthropic/claude-fable-5","label":"Claude Fable 5","provider":"Anthropic","category":["long-context"],"inputPrice":10,"outputPrice":50,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-06-09T12:18:35.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_completion_tokens,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,tool_choice,tools,verbosity","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":1,"cacheWritePrice":12.5,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":277,"totalSpeed":386,"rankInputPrice":433,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","mandatory":true}},{"id":"klingai/kling-v3.0-t2v-std","label":"Kling V3.0 T2v Std","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text->video","inputModalities":"text","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.252},"withoutAudio":{"720p":0.168}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v2.6-t2v-std","label":"Kling V2.6 T2v Std","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text->video","inputModalities":"text","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.042},"withoutAudio":{"720p":0.042}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"stealth/glyph-cluster","label":"Glyph Cluster","provider":"Stealth","category":["cheap","long-context"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":256000,"releasedAt":null,"description":null,"modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":true,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"nvidia/nemotron-3.5-lightning-free","label":"Nemotron 3.5 Lightning Free","provider":"NVIDIA","category":["cheap","long-context"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":null,"description":null,"modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":true,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v2.6-i2v","label":"Kling V2.6 I2v","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.14},"withoutAudio":{"720p":0.07}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v2.5-turbo-i2v-std","label":"Kling V2.5 Turbo I2v Std","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.042},"withoutAudio":{"720p":0.042}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v2.6-t2v","label":"Kling V2.6 T2v","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text->video","inputModalities":"text","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.14},"withoutAudio":{"720p":0.07}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v3.0-t2v","label":"Kling V3.0 T2v","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text->video","inputModalities":"text","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.336},"withoutAudio":{"720p":0.224}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v3.0-i2v-std","label":"Kling V3.0 I2v Std","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.252},"withoutAudio":{"720p":0.168}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"klingai/kling-v2.5-turbo-t2v-std","label":"Kling V2.5 Turbo T2v Std","provider":"Klingai","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text->video","inputModalities":"text","outputModalities":"video","videoModes":"t2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.042},"withoutAudio":{"720p":0.042}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"alibaba/wan3.0-prime","label":"Wan3.0 Prime","provider":"Alibaba","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.068,"720p":0.14,"1080p":0.28},"withoutAudio":{"480p":0.068,"720p":0.14,"1080p":0.28}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"reflection/beam","label":"Beam","provider":"Reflection AI","category":["cheap","long-context"],"inputPrice":0.25,"outputPrice":1,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":null,"description":null,"modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.04,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":17.7,"rankIntelligence":92,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":8,"totalSpeed":386,"rankInputPrice":193,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"inclusionai/ling-3.1-flash-1019","label":"Ling 3.1 Flash 1019","provider":"inclusionAI","category":["fast","cheap","long-context"],"inputPrice":0.3,"outputPrice":0.9,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-10-30T00:00:00.000Z","description":null,"modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.06,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":29.6,"rankIntelligence":64,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":153,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"x-ai/grok-4.7","label":"Grok 4.7","provider":"xAI","category":["creative","long-context"],"inputPrice":2,"outputPrice":6,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":500000,"releasedAt":"2026-09-21T16:19:01.000Z","description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_logprobs,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.5,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":35.2,"rankIntelligence":45,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":253,"totalSpeed":386,"rankInputPrice":320,"totalInputPrice":454},"tokenPriceTiers":[{"abovePromptTokens":200000,"input":4,"output":12,"cacheRead":1,"cacheWrite":null}],"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high","default_enabled":true,"mandatory":true}},{"id":"meta/muse-wonder","label":"Muse Wonder","provider":"Meta","category":["long-context"],"inputPrice":4,"outputPrice":20,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":"2026-10-12T00:00:00.000Z","description":"Muse Wonder is Meta's frontier model for coding, long-running agents, and advanced computer use. It plans long tasks, delegates work to sub-agents, and recovers from errors.","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":43.6,"rankIntelligence":33,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":111,"totalSpeed":386,"rankInputPrice":390,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium","mandatory":true}},{"id":"cohere/rerank-4-fast","label":"Rerank 4 Fast","provider":"Cohere","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2026-04-06T02:24:29.000Z","description":"Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...","modality":"text->rerank","inputModalities":"text","outputModalities":"rerank","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"search","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":0.002,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"cohere/rerank-4-pro","label":"Rerank 4 Pro","provider":"Cohere","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2026-04-06T03:30:47.000Z","description":"Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...","modality":"text->rerank","inputModalities":"text","outputModalities":"rerank","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"search","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":0.0025,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"cohere/rerank-v3.5","label":"Rerank v3.5","provider":"Cohere","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":4096,"releasedAt":"2026-04-05T19:09:18.000Z","description":"Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search...","modality":"text->rerank","inputModalities":"text","outputModalities":"rerank","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"search","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":0.001,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"elevenlabs/scribe-v2-medical","label":"Scribe v2 Medical","provider":"Elevenlabs","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-10-07T15:06:59.000Z","description":"ElevenLabs Scribe v2 Medical is a speech-to-text model tuned for clinical and medical terminology, with word-level timestamps, optional speaker diarization, and audio-event tagging.","modality":"audio->transcription","inputModalities":"audio","outputModalities":"transcription","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withoutAudio":{"default":0.0000611111111111}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"perplexity/pplx-embed-v1-0.6b","label":"Pplx Embed V1 0.6B","provider":"Perplexity","category":["cheap"],"inputPrice":0.004,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3-embedding-8b","label":"Qwen3 Embedding 8B","provider":"Qwen","category":["cheap"],"inputPrice":0.01,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2025-10-28T19:43:42.000Z","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3-embedding-0.6b","label":"Qwen3 Embedding 0.6B","provider":"Qwen","category":["cheap"],"inputPrice":0.07,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"amazon/titan-embed-text-v2","label":"Titan Embed Text V2","provider":"Amazon","category":["cheap"],"inputPrice":0.02,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/text-embedding-3-small","label":"Text Embedding 3 Small","provider":"OpenAI","category":["fast","cheap"],"inputPrice":0.021,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":"2025-10-30T20:50:55.000Z","description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces...","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-4-lite","label":"Voyage 4 Lite","provider":"Voyage","category":["fast","cheap"],"inputPrice":0.02,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-3.5-lite","label":"Voyage 3.5 Lite","provider":"Voyage","category":["fast","cheap"],"inputPrice":0.02,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/text-embedding-005","label":"Text Embedding 005","provider":"Google","category":["cheap"],"inputPrice":0.15,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":2048,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/text-multilingual-embedding-002","label":"Text Multilingual Embedding 002","provider":"Google","category":["cheap"],"inputPrice":0.025,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":2048,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-oss-20b","label":"GPT-OSS 20B","provider":"OpenAI","category":["cheap"],"inputPrice":0.03,"outputPrice":0.13,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2025-08-05T17:17:09.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.03,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":68,"totalSpeed":386,"rankInputPrice":24,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low"],"default_effort":"medium","mandatory":true}},{"id":"perplexity/pplx-embed-v1-4b","label":"Pplx Embed V1 4B","provider":"Perplexity","category":["cheap"],"inputPrice":0.03,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"typesafe-ai/jev","label":"Jev","provider":"Typesafe Ai","category":["cheap"],"inputPrice":0.042,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->decisions","inputModalities":"text","outputModalities":"decisions","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-3.5","label":"Voyage 3.5","provider":"Voyage","category":["cheap"],"inputPrice":0.06,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-4","label":"Voyage 4","provider":"Voyage","category":["cheap"],"inputPrice":0.06,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"mistralai/mistral-embed-2312","label":"Mistral Embed 2312","provider":"Mistral","category":["cheap"],"inputPrice":0.1,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/text-embedding-ada-002","label":"Text Embedding Ada 002","provider":"OpenAI","category":["cheap"],"inputPrice":0.1,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":"2025-10-30T23:09:58.000Z","description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-4-large","label":"Voyage 4 Large","provider":"Voyage","category":["cheap"],"inputPrice":0.12,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-finance-2","label":"Voyage Finance 2","provider":"Voyage","category":["cheap"],"inputPrice":0.12,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-code-2","label":"Voyage Code 2","provider":"Voyage","category":["cheap"],"inputPrice":0.12,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":16000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-law-2","label":"Voyage Law 2","provider":"Voyage","category":["cheap"],"inputPrice":0.12,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":16000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/text-embedding-3-large","label":"Text Embedding 3 Large","provider":"OpenAI","category":["cheap"],"inputPrice":0.13,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2025-10-30T22:21:06.000Z","description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two...","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemma-4-31b-it","label":"Gemma 4 31B","provider":"Google","category":["cheap","long-context"],"inputPrice":0.09,"outputPrice":0.34,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2026-04-02T16:48:06.000Z","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...","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.05,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":false,"mandatory":false}},{"id":"mistralai/codestral-embed-2505","label":"Codestral Embed 2505","provider":"Mistral","category":["coding","cheap"],"inputPrice":0.15,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemma-4-26b-a4b-it","label":"Gemma 4 26B A4B","provider":"Google","category":["cheap","long-context"],"inputPrice":0.09,"outputPrice":0.34,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2026-04-03T14:53:09.000Z","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...","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.05,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":false,"mandatory":false}},{"id":"google/gemini-embedding-001","label":"Gemini Embedding 001","provider":"Google","category":["fast","cheap"],"inputPrice":0.15,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":20000,"releasedAt":"2025-10-31T20:43:30.000Z","description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark...","modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-code-3","label":"Voyage Code 3","provider":"Voyage","category":["cheap"],"inputPrice":0.18,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"voyage/voyage-3-large","label":"Voyage 3 Large","provider":"Voyage","category":["cheap"],"inputPrice":0.18,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32000,"releasedAt":null,"description":null,"modality":"text->embeddings","inputModalities":"text","outputModalities":"embeddings","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3-coder","label":"Qwen3 Coder","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.3,"outputPrice":1,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-07-23T00:29:06.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.1,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"anthropic/claude-fable-5.2","label":"Claude Fable 5.2","provider":"Anthropic","category":["long-context"],"inputPrice":8,"outputPrice":40,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":null,"description":"Claude Fable 5.2 supports agentic coding, knowledge work, and research with always-on adaptive thinking and adjustable reasoning effort from low through max.","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":10,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":61.8,"rankIntelligence":3,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":252,"totalSpeed":386,"rankInputPrice":428,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","mandatory":true}},{"id":"qwen/qwen3.5-flash-02-23","label":"Qwen3.5 Flash 02 23","provider":"Qwen","category":["fast","cheap","long-context"],"inputPrice":0.065,"outputPrice":0.26,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-02-25T21:09:36.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,presence_penalty,reasoning,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":0.08125,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"bytedance-seed/seed-1.6-flash","label":"Seed 1.6 Flash","provider":"ByteDance Seed","category":["fast","cheap","long-context"],"inputPrice":0.075,"outputPrice":0.3,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-12-23T15:50:11.000Z","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...","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,reasoning,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":"2026-11-11T00:00:00.000Z","aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"bytedance-seed/seed-2.0-mini","label":"Seed-2.0-Mini","provider":"ByteDance Seed","category":["fast","cheap","long-context"],"inputPrice":0.1,"outputPrice":0.4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2026-02-26T18:38:27.000Z","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,...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","mandatory":false}},{"id":"qwen/qwen3-coder-next","label":"Qwen3 Coder Next","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.12,"outputPrice":0.8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2026-02-04T00:15:01.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.07,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3-coder-30b-a3b-instruct","label":"Qwen3 Coder 30B A3B Instruct","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.07,"outputPrice":0.28,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-07-31T14:32:59.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3-vl-30b-a3b-instruct","label":"Qwen3 VL 30B A3B Instruct","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.15,"outputPrice":0.6,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-10-06T23:47:56.000Z","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...","modality":"text+image->text","inputModalities":"text,image","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance-seed/seed-1.6","label":"Seed 1.6","provider":"ByteDance Seed","category":["cheap","long-context"],"inputPrice":0.25,"outputPrice":2,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2025-12-23T15:49:57.000Z","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.","modality":"text+image+video->text","inputModalities":"image,text,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,reasoning,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":"2026-11-11T00:00:00.000Z","aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"bytedance-seed/seed-2.0-lite","label":"Seed-2.0-Lite","provider":"ByteDance Seed","category":["fast","cheap","long-context"],"inputPrice":0.25,"outputPrice":2,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":262144,"releasedAt":"2026-03-10T15:40:31.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","mandatory":false}},{"id":"qwen/qwen3.5-plus-02-15","label":"Qwen3.5 Plus 02 15","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.26,"outputPrice":1.56,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-02-16T08:10:16.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":0.325,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"google/gemini-2.5-flash-image","label":"Gemini 2.5 Flash Image","provider":"Google","category":["fast","cheap"],"inputPrice":0.3,"outputPrice":2.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2025-10-07T20:53:51.000Z","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,...","modality":"text+image->text+image","inputModalities":"image,text","outputModalities":"image,text","videoModes":null,"supportedParameters":"max_tokens,response_format,seed,stop,structured_outputs,temperature,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"qwen/qwen3.5-plus-20260420","label":"Qwen3.5 Plus 20260420","provider":"Qwen","category":["cheap","long-context"],"inputPrice":0.3,"outputPrice":1.8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1000000,"releasedAt":"2026-04-27T03:42:48.000Z","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...","modality":"text+image+video->text","inputModalities":"text,image,video","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":0.375,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"qwen/qwen-2.5-72b-instruct","label":"Qwen2.5 72B Instruct","provider":"Qwen","category":["flagship","cheap"],"inputPrice":0.36,"outputPrice":0.4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":32768,"releasedAt":"2024-09-19T00:00:00.000Z","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...","modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":"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","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-3.1-flash-image-preview","label":"Gemini 3.1 Flash Image Preview","provider":"Google","category":["fast","cheap"],"inputPrice":0.5,"outputPrice":3,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":65536,"releasedAt":"2026-02-26T15:25:58.000Z","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...","modality":"text+image->text+image","inputModalities":"image,text","outputModalities":"image,text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":60,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","minimal"],"default_effort":"minimal","default_enabled":true,"mandatory":false}},{"id":"google/gemini-3.1-flash-image","label":"Gemini 3.1 Flash Image","provider":"Google","category":["fast","cheap"],"inputPrice":0.5,"outputPrice":3,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2026-06-18T03:41:05.000Z","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...","modality":"text+image->text+image","inputModalities":"image,text","outputModalities":"image,text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,reasoning_effort,response_format,seed,structured_outputs,temperature,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","minimal"],"default_effort":"minimal","default_enabled":true,"mandatory":false}},{"id":"x-ai/grok-4.20","label":"Grok 4.20","provider":"xAI","category":["creative","long-context"],"inputPrice":1.25,"outputPrice":2.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":2000000,"releasedAt":"2026-03-31T17:43:39.000Z","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...","modality":"text+image+file->text","inputModalities":"text,image,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,logprobs,max_tokens,reasoning,response_format,seed,structured_outputs,temperature,tool_choice,tools,top_logprobs,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":176,"totalSpeed":386,"rankInputPrice":275,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"default_enabled":false,"mandatory":false}},{"id":"google/gemini-3-pro-image","label":"Gemini 3 Pro Image","provider":"Google","category":["fast"],"inputPrice":2,"outputPrice":12,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":131072,"releasedAt":"2026-06-18T03:40:54.000Z","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...","modality":"text+image->text+image","inputModalities":"image,text","outputModalities":"image,text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,response_format,seed,stop,structured_outputs,temperature,tool_choice,tools,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":true}},{"id":"anthropic/claude-opus-4.1","label":"Claude Opus 4.1","provider":"Anthropic","category":["flagship","coding","creative","long-context"],"inputPrice":15,"outputPrice":75,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":200000,"releasedAt":"2025-08-05T16:33:11.000Z","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...","modality":"text+image+file->text","inputModalities":"image,text,file","outputModalities":"text","videoModes":null,"supportedParameters":"include_reasoning,max_tokens,reasoning,stop,temperature,tool_choice,tools,top_k,top_p","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":1.5,"cacheWritePrice":18.75,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":{"intelligenceIndex":null,"rankIntelligence":null,"totalIntelligence":118,"rankCoding":null,"totalCoding":0,"rankSpeed":null,"totalSpeed":386,"rankInputPrice":445,"totalInputPrice":454},"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"mandatory":false}},{"id":"qwen/qwen-image-3-pro","label":"Qwen Image 3 Pro","provider":"Qwen","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"max_tokens,presence_penalty,response_format,seed,temperature,top_p","pricePerImage":0.075,"billingModel":"image","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-omni-1.2-flash","label":"Gemini Omni 1.2 Flash","provider":"Google","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":null,"description":"Gemini Omni 1.2 Flash is a multimodal video generation model. It turns a text prompt, or a still image, into a short video clip of 3 to 15 seconds with native audio, in 720p or 1080p. / Gemini Omni 1.2 Flash 是多模態影片生成模型，可依文字提示或單張圖片生成 3 到 15 秒、含原生音訊的短片，提供 720p 與 1080p。","modality":"text+image+video->text+video","inputModalities":"text,image,video","outputModalities":"text,video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"720p":0.069504,"1080p":0.104256},"withoutAudio":{"720p":0.069504,"1080p":0.104256}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","low"],"default_effort":"low","mandatory":true}},{"id":"qwen/qwen-image-3","label":"Qwen Image 3","provider":"Qwen","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"max_tokens,presence_penalty,response_format,seed,temperature,top_p","pricePerImage":0.03,"billingModel":"image","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance/seedance-1-5-pro","label":"Seedance 1.5 Pro","provider":"ByteDance","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-03-23T14:53:28.339Z","description":"ByteDance's next-generation audio-visual generation model with a 4.5B parameter Dual-Branch Diffusion Transformer architecture. Seedance 1.5 Pro generates video and audio simultaneously in a single unified pass — eliminating the timing issues of sequential audio dubbing. Supports multi-language lip-sync (English, Mandarin, Japanese, Korean, Spanish, and more), cinematic camera control (pan, tilt, zoom, orbit), multi-character dialogue, and character consistency across shots. Produces clips from 4–12 seconds at up to 1080p. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024","modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":"frequency_penalty","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.0230592,"720p":0.05184,"1080p":0.11664},"withoutAudio":{"480p":0.0115296,"720p":0.02592,"1080p":0.05832}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":"2026-11-11T00:00:00.000Z","aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"x-ai/grok-imagine-image-2.0","label":"Grok Imagine Image 2.0","provider":"xAI","category":["creative","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":null,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"logprobs,max_tokens,response_format,seed,temperature,top_logprobs,top_p","pricePerImage":0.06,"billingModel":"image","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"bytedance/seedance-2.0-fast","label":"Seedance 2.0 Fast","provider":"ByteDance","category":["cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-04-15T00:02:42.904Z","description":"Seedance 2.0 Fast is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video. It prioritizes generation speed and lower cost over maximum output quality. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024","modality":"text+image+audio+video->video","inputModalities":"text,image,video,audio","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":"frequency_penalty","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.0538048,"720p":0.12096},"withoutAudio":{"480p":0.0538048,"720p":0.12096}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"x-ai/grok-imagine-video-1.5-lite","label":"Grok Imagine Video 1.5 Lite","provider":"xAI","category":["fast","creative","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":null,"description":null,"modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":null,"pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.02,"720p":0.03,"1080p":0.14},"withoutAudio":{"480p":0.02,"720p":0.03,"1080p":0.14}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"minimax/hailuo-3-max","label":"MiniMax Hailuo 3 Max","provider":"MiniMax","category":["fast","cheap"],"inputPrice":0,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":0,"releasedAt":"2026-09-02T01:41:50.000Z","description":"MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video generation with...","modality":"text+image->video","inputModalities":"text,image","outputModalities":"video","videoModes":"t2v,i2v","supportedParameters":"max_tokens,temperature,top_p","pricePerImage":null,"billingModel":"second","pricePerMegapixel":null,"pricePerSecondJson":{"withAudio":{"480p":0.05,"720p":0.08},"withoutAudio":{"480p":0.05,"720p":0.08}},"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"cloudflare/clef-flash","label":"Clef Flash","provider":"Cloudflare","category":["fast","cheap"],"inputPrice":0.09,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":24576,"releasedAt":"2026-10-01T16:09:33.000Z","description":"Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus...","modality":"text+image->decisions","inputModalities":"text,image","outputModalities":"decisions","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-embedding-2-preview","label":"Gemini Embedding 2 Preview","provider":"Google","category":["fast","cheap"],"inputPrice":0.2,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":8192,"releasedAt":"2026-04-17T14:34:25.000Z","description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...","modality":"text+image+file+audio+video->embeddings","inputModalities":"text,image,file,audio,video","outputModalities":"embeddings","videoModes":null,"supportedParameters":"","pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"cloudflare/clef","label":"Clef","provider":"Cloudflare","category":["cheap"],"inputPrice":0.24,"outputPrice":0,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":65537,"releasedAt":"2026-10-01T16:09:32.000Z","description":"Clef is Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions...","modality":"text+image->decisions","inputModalities":"text,image","outputModalities":"decisions","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":null,"pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"google/gemini-nano-banana-2.1","label":"Gemini Nano Banana 2.1","provider":"Google","category":["fast"],"inputPrice":1.5,"outputPrice":7.5,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":65536,"releasedAt":"2026-10-06T15:33:45.000Z","description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","modality":"text+image->text+image","inputModalities":"image,text","outputModalities":"image,text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["high","minimal","none"],"default_effort":"minimal","default_enabled":true,"mandatory":false}},{"id":"openai/gpt-image-1-mini","label":"GPT Image 1 Mini","provider":"OpenAI","category":["fast","long-context"],"inputPrice":2,"outputPrice":8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":"2026-06-24T00:00:00.000Z","description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"frequency_penalty,logit_bias,logprobs,max_tokens,presence_penalty,response_format,seed,stop,structured_outputs,temperature,top_logprobs,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":8,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.2,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":"2026-12-01T00:00:00.000Z","aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-image-2.5-sunburst","label":"GPT Image 2.5 Sunburst","provider":"OpenAI","category":["long-context"],"inputPrice":5,"outputPrice":30,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"frequency_penalty,logit_bias,logprobs,max_tokens,presence_penalty,response_format,seed,stop,structured_outputs,temperature,top_logprobs,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":1.25,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-image-2.5-flare","label":"GPT Image 2.5 Flare","provider":"OpenAI","category":["long-context"],"inputPrice":5,"outputPrice":30,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"frequency_penalty,logit_bias,logprobs,max_tokens,presence_penalty,response_format,seed,stop,structured_outputs,temperature,top_logprobs,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":1.25,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-5.4-image-2","label":"GPT-5.4 Image 2","provider":"OpenAI","category":["long-context"],"inputPrice":8,"outputPrice":15,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":272000,"releasedAt":"2026-04-21T18:52:08.000Z","description":"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...","modality":"text+image+file->text+image","inputModalities":"image,text,file","outputModalities":"image,text","videoModes":null,"supportedParameters":"frequency_penalty,include_reasoning,logit_bias,logprobs,max_tokens,presence_penalty,reasoning,reasoning_effort,response_format,seed,stop,structured_outputs,top_logprobs","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":{"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","default_enabled":false,"mandatory":false}},{"id":"openai/gpt-image-2.6-sunburst","label":"GPT Image 2.6 Sunburst","provider":"OpenAI","category":["long-context"],"inputPrice":8,"outputPrice":8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-image-2.6-flare","label":"GPT Image 2.6 Flare","provider":"OpenAI","category":["long-context"],"inputPrice":8,"outputPrice":8,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":null,"description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":30,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"openai/gpt-image-1","label":"GPT Image 1","provider":"OpenAI","category":["long-context"],"inputPrice":10,"outputPrice":10,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":400000,"releasedAt":"2026-06-24T00:00:00.000Z","description":null,"modality":"text+image->image","inputModalities":"text,image","outputModalities":"image","videoModes":null,"supportedParameters":"frequency_penalty,logit_bias,logprobs,max_tokens,presence_penalty,response_format,seed,stop,structured_outputs,temperature,top_logprobs,top_p","pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":40,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":null,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":false,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null},{"id":"deepseek/deepseek-v4-flash-0731free","label":"DeepSeek V4 Flash 0731 (Free)","provider":"DeepSeek","category":["fast","cheap","long-context"],"inputPrice":0.2,"outputPrice":0.4,"originalInputPrice":null,"originalOutputPrice":null,"discount":null,"contextLength":1048576,"releasedAt":null,"description":null,"modality":"text->text","inputModalities":"text","outputModalities":"text","videoModes":null,"supportedParameters":null,"pricePerImage":null,"billingModel":"token","pricePerMegapixel":null,"pricePerSecondJson":null,"pricePerImageTiersJson":null,"pricePerCharacter":null,"pricePerSearch":null,"pricePerRequest":null,"pricePerImageToken":null,"knowledgeCutoff":null,"maxCompletionTokens":null,"cacheReadPrice":0.03,"cacheWritePrice":null,"reasoningOutputPrice":null,"effectiveDeprecationDate":null,"aa":null,"tokenPriceTiers":null,"isFree":true,"freeRpmLimit":null,"freeDailyLimit":null,"reasoningMeta":null}]}