provider,model_or_service,dimension,tier,price,currency,unit,effective_notes,source,retrieved_at
openai,gpt-image-2.5-sunburst,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,image_input,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,cached_image_input,standard,2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,image_output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,image_input,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,cached_image_input,standard,2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,image_output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_input,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,cached_image_input,standard,2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_input,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,cached_image_input,standard,2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_output,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_input,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,cached_image_input,standard,2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_output,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,text_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,cached_text_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,cached_image_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_output,standard,40.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,text_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,cached_text_input,standard,0.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,cached_image_input,standard,0.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_output,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,text_input,batch,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,cached_text_input,batch,0.625,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_input,batch,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,cached_image_input,batch,1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_output,batch,15.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_input,batch,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,cached_text_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_input,batch,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,cached_image_input,batch,1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_output,batch,16.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_output,batch,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,text_input,batch,1.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,cached_text_input,batch,0.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_input,batch,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,cached_image_input,batch,0.13,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_output,batch,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,text_input,batch,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,cached_text_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_input,batch,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,cached_image_input,batch,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_output,batch,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_input,batch,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,cached_text_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_input,batch,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,cached_image_input,batch,1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_output,batch,16.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_output,batch,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_output low 1024x1024,standard,0.009,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output low 1024x1536,standard,0.013,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output low 1536x1024,standard,0.013,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output medium 1024x1024,standard,0.034,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output medium 1024x1536,standard,0.05,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output medium 1536x1024,standard,0.05,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output high 1024x1024,standard,0.133,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output high 1024x1536,standard,0.2,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,gpt-image-1.5,image_output high 1536x1024,standard,0.2,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1.5,2026-09-18
openai,chatgpt-image-latest,image_output low 1024x1024,standard,0.009,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output low 1024x1536,standard,0.013,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output low 1536x1024,standard,0.013,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output medium 1024x1024,standard,0.034,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output medium 1024x1536,standard,0.05,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output medium 1536x1024,standard,0.05,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output high 1024x1024,standard,0.133,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output high 1024x1536,standard,0.2,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,chatgpt-image-latest,image_output high 1536x1024,standard,0.2,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/chatgpt-image-latest,2026-09-18
openai,gpt-image-1,image_output low 1024x1024,standard,0.011,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output low 1024x1536,standard,0.016,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output low 1536x1024,standard,0.016,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output medium 1024x1024,standard,0.042,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output medium 1024x1536,standard,0.063,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output medium 1536x1024,standard,0.063,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output high 1024x1024,standard,0.167,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output high 1024x1536,standard,0.25,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1,image_output high 1536x1024,standard,0.25,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1,2026-09-18
openai,gpt-image-1-mini,image_output low 1024x1024,standard,0.005,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output low 1024x1536,standard,0.006,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output low 1536x1024,standard,0.006,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output medium 1024x1024,standard,0.011,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output medium 1024x1536,standard,0.015,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output medium 1536x1024,standard,0.015,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output high 1024x1024,standard,0.036,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output high 1024x1536,standard,0.052,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-1-mini,image_output high 1536x1024,standard,0.052,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/models/gpt-image-1-mini,2026-09-18
openai,gpt-image-2,image_output low 1024x1024,standard,0.006,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output low 1024x1536,standard,0.005,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output low 1536x1024,standard,0.005,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output medium 1024x1024,standard,0.053,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output medium 1024x1536,standard,0.041,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output medium 1536x1024,standard,0.041,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output high 1024x1024,standard,0.211,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output high 1024x1536,standard,0.165,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,gpt-image-2,image_output high 1536x1024,standard,0.165,USD,per image,Output-token equivalent; text/image input tokens billed on top. gpt-image-2 row from the guide's comparison table.,https://developers.openai.com/api/docs/guides/image-generation,2026-09-18
openai,sora-2,video_output 720p (720x1280|1280x720),standard,0.1,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2,video_output 720p (720x1280|1280x720),batch,0.05,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 720p (720x1280|1280x720),standard,0.3,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 720p (720x1280|1280x720),batch,0.15,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 1024p (1024x1792|1792x1024),standard,0.5,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 1024p (1024x1792|1792x1024),batch,0.25,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 1080p (1080x1920|1920x1080),standard,0.7,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output 1080p (1080x1920|1920x1080),batch,0.35,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,text-embedding-3-small,input,standard,0.02,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,text-embedding-3-large,input,standard,0.13,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,text-embedding-ada-002,input,standard,0.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,omni-moderation-latest,input,standard,0.0,USD,per call,Free,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,content_provenance_checks,call,standard,0.0,USD,per call,No price listed on the pricing page; strict rate limits instead (UNVERIFIED that it is free),https://developers.openai.com/api/docs/pricing,2026-09-18
anthropic,claude-fable-5-1,input,standard,10,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,output,standard,50,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,cached_input_write_5m,standard,12.5,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,cached_input_write_1h,standard,20,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,cached_input_read,standard,0.25,USD,per 1M tokens,0.025x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,input,batch,5.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5-1,output,batch,25.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,input,standard,10,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,output,standard,50,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,cached_input_write_5m,standard,12.5,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,cached_input_write_1h,standard,20,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,cached_input_read,standard,0.25,USD,per 1M tokens,0.025x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,input,batch,5.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5-1,output,batch,25.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,input,standard,10,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,output,standard,50,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,cached_input_write_5m,standard,12.5,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,cached_input_write_1h,standard,20,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,cached_input_read,standard,1.0,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,input,batch,5.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-fable-5,output,batch,25.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,input,standard,10,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,output,standard,50,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,cached_input_write_5m,standard,12.5,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,cached_input_write_1h,standard,20,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,cached_input_read,standard,1.0,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,input,batch,5.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-mythos-5,output,batch,25.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,input,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,output,standard,25,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,cached_input_write_5m,standard,6.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,cached_input_write_1h,standard,10,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,cached_input_read,standard,0.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,input,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,output,batch,12.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,input,fast,10,USD,per 1M tokens,speed: fast (research preview); applies across full context; caching + data residency multipliers stack; not available on Batch or clouds,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,output,fast,50,USD,per 1M tokens,speed: fast (research preview),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-5,tool_use_system_prompt_overhead_tokens,standard,406,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,input,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,output,standard,25,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,cached_input_write_5m,standard,6.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,cached_input_write_1h,standard,10,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,cached_input_read,standard,0.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,input,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,output,batch,12.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,input,fast,10,USD,per 1M tokens,speed: fast (research preview); applies across full context; caching + data residency multipliers stack; not available on Batch or clouds,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,output,fast,50,USD,per 1M tokens,speed: fast (research preview),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-8,tool_use_system_prompt_overhead_tokens,standard,410,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,input,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,output,standard,25,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,cached_input_write_5m,standard,6.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,cached_input_write_1h,standard,10,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,cached_input_read,standard,0.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,input,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,output,batch,12.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,tool_use_system_prompt_overhead_tokens,standard,804,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,input,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,output,standard,25,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,cached_input_write_5m,standard,6.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,cached_input_write_1h,standard,10,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,cached_input_read,standard,0.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,input,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,output,batch,12.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,tool_use_system_prompt_overhead_tokens,standard,589,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,input,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,output,standard,25,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,cached_input_write_5m,standard,6.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,cached_input_write_1h,standard,10,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,cached_input_read,standard,0.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,input,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,output,batch,12.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-5-20251101,tool_use_system_prompt_overhead_tokens,standard,588,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,input,standard,2,USD,per 1M tokens,introductory $2/$10 made permanent on 2026-08-10 (planned $3/$15 increase cancelled),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,output,standard,10,USD,per 1M tokens,introductory $2/$10 made permanent on 2026-08-10 (planned $3/$15 increase cancelled),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,cached_input_write_5m,standard,2.5,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,cached_input_write_1h,standard,4,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,cached_input_read,standard,0.2,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,input,batch,1.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,output,batch,5.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-5,tool_use_system_prompt_overhead_tokens,standard,474,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,input,standard,3,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,output,standard,15,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,cached_input_write_5m,standard,3.75,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,cached_input_write_1h,standard,6,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,cached_input_read,standard,0.3,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,input,batch,1.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,output,batch,7.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-6,tool_use_system_prompt_overhead_tokens,standard,589,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,input,standard,3,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,output,standard,15,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,cached_input_write_5m,standard,3.75,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,cached_input_write_1h,standard,6,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,cached_input_read,standard,0.3,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,input,batch,1.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,output,batch,7.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-5-20250929,tool_use_system_prompt_overhead_tokens,standard,588,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,input,standard,1,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,output,standard,5,USD,per 1M tokens,,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,cached_input_write_5m,standard,1.25,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,cached_input_write_1h,standard,2,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,cached_input_read,standard,0.1,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,input,batch,0.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,output,batch,2.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-haiku-4-5-20251001,tool_use_system_prompt_overhead_tokens,standard,588,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,input,standard,15,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,output,standard,75,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,cached_input_write_5m,standard,18.75,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,cached_input_write_1h,standard,30,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,cached_input_read,standard,1.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,input,batch,7.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,output,batch,37.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-1-20250805,tool_use_system_prompt_overhead_tokens,standard,315,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,input,standard,15,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,output,standard,75,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,cached_input_write_5m,standard,18.75,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,cached_input_write_1h,standard,30,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,cached_input_read,standard,1.5,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,input,batch,7.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,output,batch,37.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-20250514,tool_use_system_prompt_overhead_tokens,standard,315,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,input,standard,3,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,output,standard,15,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,cached_input_write_5m,standard,3.75,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,cached_input_write_1h,standard,6,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,cached_input_read,standard,0.3,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,input,batch,1.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,output,batch,7.5,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-sonnet-4-20250514,tool_use_system_prompt_overhead_tokens,standard,315,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,input,standard,0.8,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,output,standard,4,USD,per 1M tokens,retired on the Claude API; price kept for Bedrock/Google Cloud availability,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,cached_input_write_5m,standard,1.0,USD,per 1M tokens,1.25x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,cached_input_write_1h,standard,1.6,USD,per 1M tokens,2x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,cached_input_read,standard,0.08,USD,per 1M tokens,0.1x base input,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,input,batch,0.4,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,output,batch,2.0,USD,per 1M tokens,"Message Batches API, 50% off",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-3-5-haiku-20241022,tool_use_system_prompt_overhead_tokens,standard,355,USD,input tokens per request,tool_choice any/tool,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-7,fast_mode,fast,,USD,per 1M tokens,fast mode removed 2026-07-24: speed: fast returns an error,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude-opus-4-6,fast_mode,fast,,USD,per 1M tokens,fast mode removed 2026-06-29: speed: fast runs at standard speed and standard price; usage.speed reports standard,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,long_context_1M,input_over_200k_multiplier,standard,1.0,USD,multiplier,Claude 4.6+ and Mythos Preview: full 1M context at standard pricing (no long-context premium); caching and batch discounts apply across the window,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,inference_geo=us,all_token_dimensions_multiplier,standard,1.1,USD,multiplier,Claude 4.6+ only; global (default) = 1.0; also Foundry US Data Zone Standard; 400 on earlier models,https://platform.claude.com/docs/en/manage-claude/data-residency,2026-09-18
anthropic,bedrock_vertex_regional_endpoints,regional_or_multiregion_premium,standard,0.1,USD,fraction over global endpoint price,Sonnet 4.5 / Haiku 4.5 / Opus 4.5 and later on partner clouds; provider invoices,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,claude_platform_on_aws,claude_consumption_unit,standard,0.01,USD,per CCU,100 CCU = $1 of standard list price after discounts; hourly metering to AWS Marketplace,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,microsoft_foundry,claude_consumption_unit,standard,0.01,USD,per CCU,"Azure Marketplace CCU billing, same conversion",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,web_search,search,standard,10.0,USD,"per 1,000 searches",plus token costs for search results; errors not billed; each search = 1 use regardless of result count,https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool,2026-09-18
anthropic,web_fetch,fetch,standard,0.0,USD,per fetch,"no extra charge; fetched content billed as input tokens (~2,500 tokens per 10 kB page)",https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool,2026-09-18
anthropic,code_execution,container_hour,standard,0.05,USD,per hour per container,"beyond 1,550 free hours/org/month; 5-minute minimum per execution; billed even if tool not called when files are preloaded",https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool,2026-09-18
anthropic,code_execution,free_hours_per_month,standard,1550,USD,hours per organization per month,free tier,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,code_execution,with_web_search_or_web_fetch,standard,0.0,USD,per request,free when web_search_20260209+/web_fetch_20260209+ is in the request (only token costs),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,managed_agents,session_runtime,standard,0.08,USD,per session-hour,metered to the ms while status=running; replaces container-hour billing; tokens at model rates; no batch discount,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,bash_20250124,tool_definition_overhead_tokens,standard,244,USD,input tokens per request,"Opus 4.6, Sonnet 4.6 and earlier",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,text_editor_20250429,tool_definition_overhead_tokens,standard,700,USD,input tokens per request,Claude 4.x text editor,https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,computer_toolset_20260801,toolset_definition_overhead_tokens,standard,4500,USD,input tokens per request,"~4,520 on Fable 5/Mythos 5/Opus 5/Opus 4.8, ~4,590 on Sonnet 5; disabling zoom saves ~410; screenshots billed as image input",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,computer_20251124|computer_20250124,tool_definition_overhead_tokens,standard,735,USD,input tokens per request,plus 466-499 system prompt tokens (measured with computer_20250124),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,browser_toolset_20260801,toolset_definition_overhead_tokens,standard,6600,USD,input tokens per request,"~6,610 Fable 5/Mythos 5/Opus 5/Opus 4.8, ~6,670 Sonnet 5; all four optional members +~880",https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
anthropic,priority_tier,capacity_commitment,priority,,USD,contract,"no longer available for purchase; existing commitments run to contract end; token prices unchanged; burndown: cache read 0.1, 5m write 1.25, 1h write 2.0, inference_geo us 1.1",https://platform.claude.com/docs/en/api/service-tiers,2026-09-18
anthropic,files_api,storage,standard,,USD,n/a,no storage price documented on the pricing page; Files API ~500 RPM; files can expire via expires_in_seconds,https://platform.claude.com/docs/en/build-with-claude/files,2026-09-18
anthropic,token_counting,request,standard,0.0,USD,per request,"free; separate RPM limits (Start 5,000 / Build 10,000 / Scale 20,000)",https://platform.claude.com/docs/en/build-with-claude/token-counting,2026-09-18
anthropic,claude_code,n/a,standard,,USD,n/a,not priced on the platform pricing page (consumer/Team plans; API usage at model rates),https://platform.claude.com/docs/en/about-claude/pricing,2026-09-18
gemini,gemini-3.8-flash,input,standard,0.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $1.5,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,output,standard,3.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $7.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cached_input,standard,0.075,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.15,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cache_storage_hour,standard,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,input,batch,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,output,batch,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cached_input,batch,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cache_storage_hour,batch,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,input,flex,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,output,flex,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cached_input,flex,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cache_storage_hour,flex,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,input,priority,1.35,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $2.7,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,output,priority,6.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $13.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cached_input,priority,0.135,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.27,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,cache_storage_hour,priority,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,free_tier,free,0,USD,per 1M tokens,input/output/caching free of charge (standard & priority rows); Batch/Flex not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.8-flash,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash,2026-09-18
gemini,gemini-3.5-flash,input,standard,1.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,output,standard,9.0,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cached_input,standard,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,input,batch,0.75,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,output,batch,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cached_input,batch,0.075,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cache_storage_hour,batch,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,input,flex,0.75,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,output,flex,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cached_input,flex,0.08,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cache_storage_hour,flex,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,input,priority,2.7,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,output,priority,16.2,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cached_input,priority,0.27,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,cache_storage_hour,priority,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,free_tier,free,0,USD,per 1M tokens,input/output/caching free of charge; Batch/Flex not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash,2026-09-18
gemini,gemini-3.5-flash-lite,input,standard,0.3,USD,per 1M tokens,text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,output,standard,2.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cached_input,standard,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,input,batch,0.15,USD,per 1M tokens,text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,output,batch,1.25,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cached_input,batch,0.02,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cache_storage_hour,batch,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,input,flex,0.15,USD,per 1M tokens,text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,output,flex,1.25,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cached_input,flex,0.02,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cache_storage_hour,flex,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,input,priority,0.54,USD,per 1M tokens,text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,output,priority,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cached_input,priority,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,cache_storage_hour,priority,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,free_tier,free,0,USD,per 1M tokens,input/output free of charge on all four rows (page lists Batch/Flex as 'Free of charge' too); caching not available on free tier,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.5-flash-lite,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,input,standard,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,audio_input,standard,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,output,standard,1.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_input,standard,0.025,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_audio_input,standard,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,input,batch,0.125,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,audio_input,batch,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,output,batch,0.75,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_input,batch,0.0125,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_audio_input,batch,0.025,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cache_storage_hour,batch,0.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,input,flex,0.125,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,audio_input,flex,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,output,flex,0.75,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_input,flex,0.0125,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_audio_input,flex,0.025,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cache_storage_hour,flex,0.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,input,priority,0.45,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,audio_input,priority,0.9,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,output,priority,2.7,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_input,priority,0.045,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cached_audio_input,priority,0.09,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,cache_storage_hour,priority,1.8,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,free_tier,free,0,USD,per 1M tokens,input/output free of charge; caching not available on free tier,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3.1-flash-lite,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite,2026-09-18
gemini,gemini-3-flash-preview,input,standard,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,audio_input,standard,1.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,output,standard,3.0,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_input,standard,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_audio_input,standard,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,input,batch,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,audio_input,batch,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,output,batch,1.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_input,batch,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_audio_input,batch,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cache_storage_hour,batch,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,input,flex,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,audio_input,flex,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,output,flex,1.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_input,flex,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_audio_input,flex,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cache_storage_hour,flex,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,input,priority,0.9,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,audio_input,priority,1.8,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,output,priority,5.4,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_input,priority,0.09,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cached_audio_input,priority,0.18,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,cache_storage_hour,priority,1.8,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,free_tier,free,0,USD,per 1M tokens,input/output/caching free of charge; Batch/Flex not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3-flash-preview,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3-flash-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input,standard,2.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input_over_200k,standard,4.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output,standard,12.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output_over_200k,standard,18.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input,standard,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input_over_200k,standard,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cache_storage_hour,standard,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input,batch,1.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input_over_200k,batch,2.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output,batch,6.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output_over_200k,batch,9.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input,batch,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input_over_200k,batch,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cache_storage_hour,batch,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input,flex,1.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input_over_200k,flex,2.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output,flex,6.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output_over_200k,flex,9.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input,flex,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input_over_200k,flex,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cache_storage_hour,flex,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input,priority,3.6,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,input_over_200k,priority,7.2,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output,priority,21.6,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,output_over_200k,priority,32.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input,priority,0.36,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cached_input_over_200k,priority,0.72,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,cache_storage_hour,priority,8.1,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,free_tier,free,0,USD,per 1M tokens,Not available (paid tier only),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-3.1-pro-preview,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview,2026-09-18
gemini,gemini-2.5-pro,input,standard,1.25,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input_over_200k,standard,2.5,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output,standard,10.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output_over_200k,standard,15.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input,standard,0.125,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input_over_200k,standard,0.25,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cache_storage_hour,standard,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input,batch,0.625,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input_over_200k,batch,1.25,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output,batch,5.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output_over_200k,batch,7.5,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input,batch,0.125,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input_over_200k,batch,0.25,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cache_storage_hour,batch,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input,flex,0.625,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input_over_200k,flex,1.25,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output,flex,5.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output_over_200k,flex,7.5,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input,flex,0.125,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input_over_200k,flex,0.25,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cache_storage_hour,flex,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input,priority,2.25,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,input_over_200k,priority,4.5,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output,priority,18.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,output_over_200k,priority,27.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input,priority,0.225,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cached_input_over_200k,priority,0.45,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,cache_storage_hour,priority,8.1,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,free_tier,free,0,USD,per 1M tokens,"input/output free of charge (standard/priority rows); caching, Batch, Flex not available",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,grounding_google_search,standard,35.0,USD,per 1K grounded prompts,"1,500 RPD free, then $35 per 1,000 grounded prompts",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-pro,grounding_google_maps,standard,25.0,USD,per 1K grounded prompts,"10,000 RPD free, then $25 per 1,000 grounded prompts",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro,2026-09-18
gemini,gemini-2.5-flash,input,standard,0.3,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,audio_input,standard,1.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,output,standard,2.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_input,standard,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_audio_input,standard,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,input,batch,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,audio_input,batch,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,output,batch,1.25,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_input,batch,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_audio_input,batch,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cache_storage_hour,batch,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,input,flex,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,audio_input,flex,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,output,flex,1.25,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_input,flex,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_audio_input,flex,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cache_storage_hour,flex,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,input,priority,0.54,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,audio_input,priority,1.8,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,output,priority,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_input,priority,0.054,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cached_audio_input,priority,0.18,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,cache_storage_hour,priority,1.8,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,free_tier,free,0,USD,per 1M tokens,input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash-Lite),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,grounding_google_search,standard,35.0,USD,per 1K grounded prompts,"1,500 RPD free (limit shared Flash/Flash-Lite), then $35 per 1,000 grounded prompts; free tier: 500 RPD",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash,grounding_google_maps,standard,25.0,USD,per 1K grounded prompts,"1,500 RPD free, then $25 per 1,000 grounded prompts; free tier 500 RPD",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash,2026-09-18
gemini,gemini-2.5-flash-lite,input,standard,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,audio_input,standard,0.3,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,output,standard,0.4,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_input,standard,0.01,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_audio_input,standard,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cache_storage_hour,standard,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,input,batch,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,audio_input,batch,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,output,batch,0.2,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_input,batch,0.01,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_audio_input,batch,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cache_storage_hour,batch,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,input,flex,0.05,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,audio_input,flex,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,output,flex,0.2,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_input,flex,0.01,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_audio_input,flex,0.03,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cache_storage_hour,flex,1.0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,input,priority,0.18,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,audio_input,priority,0.54,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,output,priority,0.72,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_input,priority,0.018,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cached_audio_input,priority,0.054,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,cache_storage_hour,priority,1.8,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,free_tier,free,0,USD,per 1M tokens,input/output free of charge; caching not available; Google Search grounding free up to 500 RPD (shared with Flash),https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,grounding_google_search,standard,35.0,USD,per 1K grounded prompts,"1,500 RPD free (limit shared Flash/Flash-Lite), then $35 per 1,000 grounded prompts; free tier: 500 RPD",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-2.5-flash-lite,grounding_google_maps,standard,25.0,USD,per 1K grounded prompts,"1,500 RPD free, then $25 per 1,000 grounded prompts; free tier 500 RPD",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-lite,2026-09-18
gemini,gemini-robotics-er-2-preview,input,standard,1.0,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $2.0; text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,output,standard,5.0,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $10.0; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,cached_input,standard,0.1,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.2,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,cache_storage_hour,standard,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,input,batch,0.5,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $1.0; text / image / video / audio same price,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,output,batch,2.5,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $5.0; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,cached_input,batch,0.05,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.1,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,cache_storage_hour,batch,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,free_tier,free,0,USD,per 1M tokens,input/output free of charge; caching not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-robotics-er-2-preview,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2-preview,2026-09-18
gemini,gemini-2.5-computer-use-preview-10-2025,input,standard,1.0,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $2.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-computer-use-preview-10-2025,2026-09-18
gemini,gemini-2.5-computer-use-preview-10-2025,output,standard,5.0,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $10.0; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-computer-use-preview-10-2025,2026-09-18
gemini,gemini-2.5-computer-use-preview-10-2025,free_tier,free,0,USD,per 1M tokens,input/output free of charge,https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-computer-use-preview-10-2025,2026-09-18
gemini,gemini-2.5-computer-use-preview-10-2025,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-computer-use-preview-10-2025,2026-09-18
gemini,gemini-2.5-computer-use-preview-10-2025,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-computer-use-preview-10-2025,2026-09-18
gemini,gemini-3.7-flash,input,standard,0.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $1.5,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,output,standard,3.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $7.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cached_input,standard,0.075,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.15,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cache_storage_hour,standard,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,input,batch,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,output,batch,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cached_input,batch,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cache_storage_hour,batch,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,input,flex,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,output,flex,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cached_input,flex,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cache_storage_hour,flex,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,input,priority,1.35,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $2.7,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,output,priority,6.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $13.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cached_input,priority,0.135,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.27,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,cache_storage_hour,priority,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,free_tier,free,0,USD,per 1M tokens,input/output/caching free of charge (standard & priority rows); Batch/Flex not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.7-flash,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash,2026-09-18
gemini,gemini-3.6-flash,input,standard,0.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $1.5,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,output,standard,3.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $7.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cached_input,standard,0.075,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.15,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cache_storage_hour,standard,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,input,batch,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,output,batch,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cached_input,batch,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cache_storage_hour,batch,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,input,flex,0.375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.75,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,output,flex,1.875,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $3.75; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cached_input,flex,0.0375,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.075,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cache_storage_hour,flex,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,input,priority,1.35,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $2.7,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,output,priority,6.75,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $13.5; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cached_input,priority,0.135,USD,per 1M tokens,Introductory price through 2026-12-31; from 2027-01-01: $0.27,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,cache_storage_hour,priority,0.5,USD,per 1M tokens per hour,Introductory price through 2026-12-31; from 2027-01-01: $1.0,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,free_tier,free,0,USD,per 1M tokens,input/output/caching free of charge (standard & priority rows); Batch/Flex not available,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.6-flash,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input,standard,2.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input_over_200k,standard,4.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output,standard,12.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output_over_200k,standard,18.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input,standard,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input_over_200k,standard,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cache_storage_hour,standard,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input,batch,1.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input_over_200k,batch,2.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output,batch,6.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output_over_200k,batch,9.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input,batch,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input_over_200k,batch,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cache_storage_hour,batch,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input,flex,1.0,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input_over_200k,flex,2.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output,flex,6.0,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output_over_200k,flex,9.0,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input,flex,0.2,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input_over_200k,flex,0.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cache_storage_hour,flex,4.5,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input,priority,3.6,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,input_over_200k,priority,7.2,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output,priority,21.6,USD,per 1M tokens,prompts <= 200k tokens; includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,output_over_200k,priority,32.4,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input,priority,0.36,USD,per 1M tokens,prompts <= 200k tokens,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cached_input_over_200k,priority,0.72,USD,per 1M tokens,prompts > 200k tokens (long-context tier),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,cache_storage_hour,priority,8.1,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,free_tier,free,0,USD,per 1M tokens,Not available (paid tier only),https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests; billed per search query executed (a prompt may trigger several)",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.1-pro-preview-customtools,grounding_google_maps,standard,14.0,USD,per 1K search queries,"5,000 prompts per month free (shared across Gemini 3), then $14 per 1,000 search queries",https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview-customtools,2026-09-18
gemini,gemini-3.8-live,input_text,standard,0.75,USD,per 1M tokens,Live API,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live,audio_input,standard,3.0,USD,per 1M tokens,= $0.005 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live,image_video_input,standard,1.0,USD,per 1M tokens,= $0.002 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live,output_text,standard,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live,audio_output,standard,12.0,USD,per 1M tokens,= $0.018 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live,free_tier,free,0,USD,per 1M tokens,free of charge; Google Search grounding supported on free tier for these models,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,input_text,standard,0.75,USD,per 1M tokens,Live API,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,audio_input,standard,3.0,USD,per 1M tokens,= $0.005 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,image_video_input,standard,1.0,USD,per 1M tokens,= $0.002 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,output_text,standard,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,audio_output,standard,12.0,USD,per 1M tokens,= $0.018 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.8-live-extended-thinking,free_tier,free,0,USD,per 1M tokens,free of charge; Google Search grounding supported on free tier for these models,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,input_text,standard,0.75,USD,per 1M tokens,Live API,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,audio_input,standard,3.0,USD,per 1M tokens,= $0.005 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,image_video_input,standard,1.0,USD,per 1M tokens,= $0.002 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,output_text,standard,4.5,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,audio_output,standard,12.0,USD,per 1M tokens,= $0.018 per minute,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.1-flash-live-preview,free_tier,free,0,USD,per 1M tokens,free of charge; Google Search grounding supported on free tier for these models,https://ai.google.dev/gemini-api/docs/pricing#live-api-models,2026-09-18
gemini,gemini-3.5-live-translate-preview,audio_input,standard,3.5,USD,per 1M tokens,= $0.0053/min; 25 tokens per second of audio; effective ~$0.0368/min in+out,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-live-translate-preview,audio_output,standard,21.0,USD,per 1M tokens,= $0.0315/min,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe-live,audio_input,standard,3.5,USD,per 1M tokens,= $0.005/min (25 audio tokens/s),https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe-live,output_text,standard,21.0,USD,per 1M tokens,= $0.004/min (175 text tokens/min); blended ~$0.009/min,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe,audio_input,standard,2.0,USD,per 1M tokens,= $0.003/min,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe,output_text,standard,12.0,USD,per 1M tokens,= $0.002/min; blended ~$0.005/min,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-live-translate-preview,free_tier,free,0,USD,per 1M tokens,free of charge,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe-live,free_tier,free,0,USD,per 1M tokens,free of charge,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.5-transcribe,free_tier,free,0,USD,per 1M tokens,free of charge,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-native-audio-preview-12-2025,input_text,standard,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-native-audio-preview-12-2025,audio_video_input,standard,3.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-native-audio-preview-12-2025,output_text,standard,2.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-native-audio-preview-12-2025,audio_output,standard,12.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-1.1-flash,input,standard,1.5,USD,per 1M tokens,text / image / video / audio,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-1.1-flash,output_text,standard,9.0,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-1.1-flash,video_output,standard,17.5,USD,per 1M tokens,"5,792 tokens per second of 720p video => ~$0.10 per second",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-1.1-flash,video_output_per_second,standard,0.1,USD,per second,"effective, 720p, standard",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-flash-preview,input,standard,1.5,USD,per 1M tokens,text / image / video / audio,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-flash-preview,output_text,standard,9.0,USD,per 1M tokens,includes thinking tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-flash-preview,video_output,standard,17.5,USD,per 1M tokens,"5,792 tokens per second of 720p video => ~$0.10 per second",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-omni-flash-preview,video_output_per_second,standard,0.1,USD,per second,"effective, 720p, standard",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,input,standard,0.5,USD,per 1M tokens,text/image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,output_text,standard,3.0,USD,per 1M tokens,text and thinking,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output,standard,60.0,USD,per 1M tokens,per 1M image tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_0.5K,standard,0.045,USD,per image,747 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_1K,standard,0.067,USD,per image,1120 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_2K,standard,0.101,USD,per image,1680 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_4K,standard,0.151,USD,per image,2520 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,input,batch,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,output_text,batch,1.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output,batch,30.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_0.5K,batch,0.022,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_1K,batch,0.034,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_2K,batch,0.05,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,image_output_4K,batch,0.076,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free/month shared across Gemini 3.x; text and image search grounding; retrieved context not charged as input",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,input,standard,0.5,USD,per 1M tokens,text/image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,output_text,standard,3.0,USD,per 1M tokens,text and thinking,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output,standard,60.0,USD,per 1M tokens,per 1M image tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_0.5K,standard,0.045,USD,per image,747 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_1K,standard,0.067,USD,per image,1120 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_2K,standard,0.101,USD,per image,1680 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_4K,standard,0.151,USD,per image,2520 tokens per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,input,batch,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,output_text,batch,1.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output,batch,30.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_0.5K,batch,0.022,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_1K,batch,0.034,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_2K,batch,0.05,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,image_output_4K,batch,0.076,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-image-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free/month shared across Gemini 3.x; text and image search grounding; retrieved context not charged as input",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,input,standard,0.25,USD,per 1M tokens,text/image/video,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,output_text,standard,1.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,image_output,standard,30.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,image_output_1K,standard,0.0336,USD,per image,1120 tokens; only 1K supported,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,input,batch,0.125,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,output_text,batch,0.75,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,image_output,batch,15.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-lite-image,image_output_1K,batch,0.0168,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,input,standard,2.0,USD,per 1M tokens,text/image; image input = 560 tokens = $0.0011 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_input,standard,0.0011,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,output_text,standard,12.0,USD,per 1M tokens,text and thinking,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output,standard,120.0,USD,per 1M tokens,per 1M image tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_1K_2K,standard,0.134,USD,per image,1120 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_4K,standard,0.24,USD,per image,2000 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,input,batch,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_input,batch,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,output_text,batch,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_1K_2K,batch,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_4K,batch,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,input,flex,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_input,flex,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,output_text,flex,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_1K_2K,flex,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output_4K,flex,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,input,priority,3.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,output_text,priority,21.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,image_output,priority,216.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free/month shared across Gemini 3.x",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,input,standard,2.0,USD,per 1M tokens,text/image; image input = 560 tokens = $0.0011 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_input,standard,0.0011,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,output_text,standard,12.0,USD,per 1M tokens,text and thinking,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output,standard,120.0,USD,per 1M tokens,per 1M image tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_1K_2K,standard,0.134,USD,per image,1120 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_4K,standard,0.24,USD,per image,2000 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,input,batch,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_input,batch,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,output_text,batch,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_1K_2K,batch,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_4K,batch,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,input,flex,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_input,flex,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,output_text,flex,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_1K_2K,flex,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output_4K,flex,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,input,priority,3.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,output_text,priority,21.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,image_output,priority,216.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3-pro-image-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free/month shared across Gemini 3.x",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,input,standard,2.0,USD,per 1M tokens,text/image; image input = 560 tokens = $0.0011 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_input,standard,0.0011,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,output_text,standard,12.0,USD,per 1M tokens,text and thinking,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output,standard,120.0,USD,per 1M tokens,per 1M image tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_1K_2K,standard,0.134,USD,per image,1120 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_4K,standard,0.24,USD,per image,2000 tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,input,batch,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_input,batch,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,output_text,batch,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_1K_2K,batch,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_4K,batch,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,input,flex,1.0,USD,per 1M tokens,text,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_input,flex,0.0006,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,output_text,flex,6.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_1K_2K,flex,0.067,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output_4K,flex,0.12,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,input,priority,3.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,output_text,priority,21.6,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,image_output,priority,216.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,nano-banana-pro-preview,grounding_google_search,standard,14.0,USD,per 1K requests,"5,000 free/month shared across Gemini 3.x",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,input,standard,0.3,USD,per 1M tokens,text/image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,image_output,standard,0.039,USD,per image,"$30 per 1M image tokens; 1290 tokens per image up to 1024x1024; deprecated, shutdown 2026-10-02",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,input,batch,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,image_output,batch,0.0195,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,input,flex,0.15,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,image_output,flex,0.0195,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,input,priority,0.54,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-image,image_output,priority,0.0702,USD,per image,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-tts-preview,input_text,standard,1.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-tts-preview,audio_output,standard,20.0,USD,per 1M tokens,25 audio tokens per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-tts-preview,input_text,batch,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-3.1-flash-tts-preview,audio_output,batch,10.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-preview-tts,input_text,standard,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-preview-tts,audio_output,standard,10.0,USD,per 1M tokens,25 audio tokens per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-preview-tts,input_text,batch,0.25,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-flash-preview-tts,audio_output,batch,5.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-pro-preview-tts,input_text,standard,1.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-pro-preview-tts,audio_output,standard,20.0,USD,per 1M tokens,25 audio tokens per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-pro-preview-tts,input_text,batch,0.5,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-2.5-pro-preview-tts,audio_output,batch,10.0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-generate-preview,video_output_720p,standard,0.4,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-generate-preview,video_output_1080p,standard,0.4,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-generate-preview,video_output_4k,standard,0.6,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-fast-generate-preview,video_output_720p,standard,0.1,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-fast-generate-preview,video_output_1080p,standard,0.12,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-fast-generate-preview,video_output_4k,standard,0.3,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-lite-generate-preview,video_output_720p,standard,0.05,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-lite-generate-preview,video_output_1080p,standard,0.08,USD,per second,video with audio (default); charged only when the video is successfully generated,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,veo-3.1-lite-generate-preview,video_output_4k,standard,,USD,per second,4K output not supported,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,lyria-3.5,per_song,standard,0.08,USD,per request,full song,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,lyria-3-clip-preview,per_song,standard,0.04,USD,per request,30 s clip,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,lyria-3-pro-preview,per_song,standard,0.08,USD,per request,full song; legacy,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,input_text,standard,0.2,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,image_input,standard,0.45,USD,per 1M tokens,= $0.00012 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,audio_input,standard,6.5,USD,per 1M tokens,= $0.00016 per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,video_input,standard,12.0,USD,per 1M tokens,= $0.00079 per frame,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,input_text,batch,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,image_input,batch,0.225,USD,per 1M tokens,= $0.00006 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,audio_input,batch,3.25,USD,per 1M tokens,= $0.00008 per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,video_input,batch,6.0,USD,per 1M tokens,= $0.000395 per frame,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2,free_tier,free,0,USD,per 1M tokens,standard free of charge; batch not available on free tier,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,input_text,standard,0.2,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,image_input,standard,0.45,USD,per 1M tokens,= $0.00012 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,audio_input,standard,6.5,USD,per 1M tokens,= $0.00016 per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,video_input,standard,12.0,USD,per 1M tokens,= $0.00079 per frame,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,input_text,batch,0.1,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,image_input,batch,0.225,USD,per 1M tokens,= $0.00006 per image,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,audio_input,batch,3.25,USD,per 1M tokens,= $0.00008 per second,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,video_input,batch,6.0,USD,per 1M tokens,= $0.000395 per frame,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-2-preview,free_tier,free,0,USD,per 1M tokens,standard free of charge; batch not available on free tier,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemini-embedding-001,input,standard,,USD,per 1M tokens,not listed on pricing.md as of 2026-09-18; File Search indexing embeddings billed at $0.15 per 1M tokens (file-search tool row),https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-26b-a4b-it,input,free,0,USD,per 1M tokens,Gemma 4: free tier free of charge; paid tier 'Not available',https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-26b-a4b-it,output,free,0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-26b-a4b-it,cached_input,free,0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-26b-a4b-it,cache_storage_hour,free,0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-31b-it,input,free,0,USD,per 1M tokens,Gemma 4: free tier free of charge; paid tier 'Not available',https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-31b-it,output,free,0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-31b-it,cached_input,free,0,USD,per 1M tokens,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,gemma-4-31b-it,cache_storage_hour,free,0,USD,per 1M tokens per hour,,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:google_search,grounding_google_search,standard,14.0,USD,per 1K requests,"Gemini 3.x: 5,000 free search requests per month shared across all Gemini 3 models; billed per executed search query; retrieved context not charged as input",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:google_search,grounding_google_search,standard,35.0,USD,per 1K grounded prompts,"Gemini 2.5 models: 1,500 RPD free (shared Flash/Flash-Lite); billed per grounded prompt",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:google_search,grounding_google_search,free,0,USD,per 1K grounded prompts,Free tier: 500 RPD free (shared Flash/Flash-Lite); not available for Pro,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:google_maps,grounding_google_maps,standard,14.0,USD,per 1K search queries,"Gemini 3.x: 5,000 prompts/month free shared across Gemini 3",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:google_maps,grounding_google_maps,standard,25.0,USD,per 1K grounded prompts,"Gemini 2.5: 1,500 RPD free (Flash/Flash-Lite), 10,000 RPD free for Pro; free tier 500 RPD, not for Pro",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:code_execution,tool_usage,standard,0,USD,per call,no per-call fee; generated code + results billed as output tokens when created and as input tokens when re-consumed; no charge for session runtime; free tier: free,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:url_context,tool_usage,standard,0,USD,per call,retrieved page content charged as input tokens at model rates,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:computer_use,tool_usage,standard,0,USD,per call,charged as regular tokens per model pricing; not available on free tier,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:file_search,indexing_embeddings,standard,0.15,USD,per 1M tokens,charged once at indexing; storage and query-time embeddings free; retrieved document tokens billed as input tokens,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,tool:custom_tools_endpoint,tokens,standard,,USD,per 1M tokens,gemini-3.1-pro-preview-customtools: same as Gemini 3.1 Pro Preview,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,agent:deep-research,tokens,standard,,USD,per 1M tokens,all model inference at standard Gemini list rates incl. intermediate/reasoning tokens; tool fees per tool pricing (search retrieved tokens excluded; url_context/file search retrieved tokens included),https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,agent:managed-agents,environment_compute,standard,0,USD,per hour,sandbox CPU/memory/execution not billed during preview; inference at list rates,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,agent:antigravity,environment_compute,standard,0,USD,per hour,same as managed agents; inference at list rates,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:batch_api,discount,batch,0.5,USD,multiplier,50% of standard interactive price; target turnaround 24h,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:flex_inference,discount,flex,0.5,USD,multiplier,"50% discount; best-effort, sheddable; 1-15 min target latency",https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:priority_inference,premium,priority,1.8x,USD,multiplier,75-100% more than standard (tables show 1.8x); graceful downgrade to standard when limits exceeded,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:context_cache_storage,cache_storage_hour,standard,0.50-8.10,USD,per 1M tokens per hour,model dependent: $0.50 (3.6-3.8 Flash intro) / $1.00 (most Flash) / $1.80 (Flash priority) / $4.50 (Pro) / $8.10 (Pro priority),https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:document_tokens,pdf_page,standard,,USD,per page,DOCUMENT modality (PDF) billed at the image token rate; appears under promptTokensDetails modality DOCUMENT,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
gemini,service:google_ai_studio,usage,free,0,USD,per call,AI Studio usage is free of charge in all available regions,https://ai.google.dev/gemini-api/docs/pricing,2026-09-18
openai,gpt-6-astra,input,standard,20.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cached_input,standard,2.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cache_write,standard,25.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,output,standard,75.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,input,standard,8.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cached_input,standard,0.8,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cache_write,standard,10.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,output,standard,30.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,input,standard,4.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cached_input,standard,0.4,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cache_write,standard,5.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,output,standard,18.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,input,standard,0.4,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cached_input,standard,0.04,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cache_write,standard,0.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,output,standard,1.8,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,input,standard,10.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,cached_input,standard,1.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,output,standard,45.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,input,standard,60.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,output,standard,270.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,input,standard,5.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,cached_input,standard,0.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,output,standard,22.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,input,standard,0.75,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,cached_input,standard,0.075,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,output,standard,4.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,input,standard,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,cached_input,standard,0.02,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,output,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,input,standard,60.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,output,standard,270.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,input,standard,1.75,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,cached_input,standard,0.175,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,output,standard,14.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2-pro,input,standard,21.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2-pro,output,standard,168.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,input,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,cached_input,standard,0.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,output,standard,10.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,input,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,cached_input,standard,0.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,output,standard,10.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,input,standard,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,cached_input,standard,0.025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,output,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,input,standard,0.05,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,cached_input,standard,0.005,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,output,standard,0.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-pro,input,standard,15.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-pro,output,standard,120.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,input,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,cached_input,standard,0.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,output,standard,8.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,input,standard,0.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,cached_input,standard,0.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,output,standard,1.6,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,input,standard,0.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,cached_input,standard,0.025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,output,standard,0.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,input,standard,2.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,cached_input,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,output,standard,10.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,input,standard,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,output,standard,15.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,input,standard,0.15,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,cached_input,standard,0.075,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,output,standard,0.6,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1,input,standard,15.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1,cached_input,standard,7.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1,output,standard,60.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1-pro,input,standard,150.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1-pro,output,standard,600.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-pro,input,standard,20.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-pro,output,standard,80.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,input,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,cached_input,standard,0.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,output,standard,8.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,input,standard,1.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,cached_input,standard,0.275,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,output,standard,4.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-mini,input,standard,1.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-mini,cached_input,standard,0.55,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-mini,output,standard,4.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-turbo-2024-04-09,input,standard,10.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-turbo-2024-04-09,output,standard,30.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-0613,input,standard,30.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-0613,output,standard,60.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,input,standard,0.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,output,standard,1.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-0125,input,standard,0.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-0125,output,standard,1.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-1106,input,standard,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-1106,output,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-instruct,input,standard,1.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-instruct,output,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,input,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,output,standard,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,input,standard,0.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,output,standard,0.4,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,input,batch,10.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cached_input,batch,1.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cache_write,batch,12.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,output,batch,37.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,input,batch,4.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cached_input,batch,0.4,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cache_write,batch,5.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,output,batch,15.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,input,batch,2.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cached_input,batch,0.2,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cache_write,batch,2.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,output,batch,9.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,input,batch,0.2,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cached_input,batch,0.02,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cache_write,batch,0.25,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,output,batch,0.9,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,input,batch,5.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,cached_input,batch,0.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,output,batch,22.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,input,batch,15.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,output,batch,90.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,input,batch,2.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,cached_input,batch,0.25,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,output,batch,11.25,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,input,batch,0.375,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,cached_input,batch,0.0375,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,output,batch,2.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,input,batch,0.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,cached_input,batch,0.01,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,output,batch,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,input,batch,30.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,output,batch,135.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,input,batch,0.875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,cached_input,batch,0.0875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,output,batch,7.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2-pro,input,batch,10.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2-pro,output,batch,84.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,input,batch,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,cached_input,batch,0.0625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,output,batch,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,input,batch,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,cached_input,batch,0.0625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,output,batch,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,input,batch,0.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,cached_input,batch,0.0125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,output,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,input,batch,0.025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,cached_input,batch,0.0025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,output,batch,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-pro,input,batch,7.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-pro,output,batch,60.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,input,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,output,batch,4.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,input,batch,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,output,batch,0.8,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,input,batch,0.05,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,output,batch,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,input,batch,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,output,batch,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,input,batch,2.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,output,batch,7.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,input,batch,0.075,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,output,batch,0.3,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1,input,batch,7.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1,output,batch,30.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1-pro,input,batch,75.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o1-pro,output,batch,300.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-pro,input,batch,10.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-pro,output,batch,40.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,input,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,output,batch,4.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,input,batch,0.55,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,output,batch,2.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-mini,input,batch,0.55,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3-mini,output,batch,2.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-turbo-2024-04-09,input,batch,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-turbo-2024-04-09,output,batch,15.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-0613,input,batch,15.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4-0613,output,batch,30.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-0125,input,batch,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-0125,output,batch,0.75,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-1106,input,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo-1106,output,batch,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,input,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,output,batch,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,input,batch,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,output,batch,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,input,flex,10.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cached_input,flex,1.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cache_write,flex,12.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,output,flex,37.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,input,flex,4.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cached_input,flex,0.4,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cache_write,flex,5.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,output,flex,15.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,input,flex,2.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cached_input,flex,0.2,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cache_write,flex,2.5,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,output,flex,9.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,input,flex,0.2,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cached_input,flex,0.02,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cache_write,flex,0.25,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,output,flex,0.9,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,input,flex,5.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,cached_input,flex,0.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,output,flex,22.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,input,flex,15.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-pro,output,flex,90.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,input,flex,2.5,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,cached_input,flex,0.25,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,output,flex,11.25,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,input,flex,0.375,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,cached_input,flex,0.0375,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,output,flex,2.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,input,flex,0.1,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,cached_input,flex,0.01,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-nano,output,flex,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,input,flex,30.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-pro,output,flex,135.0,USD,per 1M tokens,<272K context length; long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,input,flex,0.875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,cached_input,flex,0.0875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,output,flex,7.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,input,flex,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,cached_input,flex,0.0625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,output,flex,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,input,flex,0.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,cached_input,flex,0.0625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,output,flex,5.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,input,flex,0.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,cached_input,flex,0.0125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,output,flex,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,input,flex,0.025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,cached_input,flex,0.0025,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-nano,output,flex,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,input,flex,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,cached_input,flex,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,output,flex,4.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,input,flex,0.55,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,cached_input,flex,0.138,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,output,flex,2.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,input,fast,40.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cached_input,fast,4.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,cache_write,fast,50.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-6-astra,output,fast,150.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,input,fast,16.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cached_input,fast,1.6,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,cache_write,fast,20.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,output,fast,60.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,input,fast,8.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cached_input,fast,0.8,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,cache_write,fast,10.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-terra,output,fast,36.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,input,fast,0.8,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cached_input,fast,0.08,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,cache_write,fast,1.0,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-luna,output,fast,3.6,USD,per 1M tokens,long context (>272K input tokens) rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,input,fast,12.5,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,cached_input,fast,1.25,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5,output,fast,75.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,input,fast,5.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,cached_input,fast,0.5,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4,output,fast,30.0,USD,per 1M tokens,<272K context length; short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,input,fast,1.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,cached_input,fast,0.15,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.4-mini,output,fast,9.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,input,fast,3.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,cached_input,fast,0.35,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.2,output,fast,28.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,input,fast,2.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,cached_input,fast,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.1,output,fast,20.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,input,fast,2.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,cached_input,fast,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5,output,fast,20.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,input,fast,0.45,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,cached_input,fast,0.045,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-mini,output,fast,3.6,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,input,fast,3.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,cached_input,fast,0.875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1,output,fast,14.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,input,fast,0.7,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,cached_input,fast,0.175,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini,output,fast,2.8,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,input,fast,0.2,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,cached_input,fast,0.05,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano,output,fast,0.8,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,input,fast,4.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,cached_input,fast,2.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o,output,fast,17.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,input,fast,8.75,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-05-13,output,fast,26.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,input,fast,0.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,cached_input,fast,0.125,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini,output,fast,1.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,input,fast,3.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,cached_input,fast,0.875,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o3,output,fast,14.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,input,fast,2.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,cached_input,fast,0.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini,output,fast,8.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-cyber,input,standard,12.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-cyber,cached_input,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-cyber,cache_write,standard,15.625,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-cyber,output,standard,75.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-cyber,input,standard,12.5,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-cyber,cached_input,standard,1.25,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.5-cyber,output,standard,75.0,USD,per 1M tokens,short context rate,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-live-1,session_duration,standard,0.05,USD,per minute (billed per second),,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,audio_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,text_input,standard,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,text_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,text_output,standard,24.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,image_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1,image_cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,audio_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,audio_cached_input,standard,0.3,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,audio_output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,text_input,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,text_cached_input,standard,0.06,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,text_output,standard,2.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,image_input,standard,0.8,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2.1-mini,image_cached_input,standard,0.08,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,audio_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,text_input,standard,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,text_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,text_output,standard,24.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,image_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-2,image_cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,audio_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,text_input,standard,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,text_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,text_output,standard,16.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,image_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-1.5,image_cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,audio_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,audio_cached_input,standard,0.3,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,audio_output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,text_input,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,text_cached_input,standard,0.06,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,text_output,standard,2.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,image_input,standard,0.8,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-mini,image_cached_input,standard,0.08,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,audio_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,text_input,standard,4.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,text_cached_input,standard,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,text_output,standard,16.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,image_input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime,image_cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-1.5,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-1.5,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-1.5,text_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-1.5,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-mini,audio_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-mini,audio_output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-mini,text_input,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio-mini,text_output,standard,2.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio,audio_input,standard,32.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio,audio_output,standard,64.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio,text_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-audio,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-tts,audio_output,standard,12.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-tts,text_input,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tts-1,text_input,standard,15.0,USD,per 1M characters,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tts-1-hd,text_input,standard,30.0,USD,per 1M characters,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,image_cached_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-sunburst,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,image_cached_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2.5-flare,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_cached_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_cached_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_cached_input,standard,0.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,text_cached_input,standard,0.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_cached_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_cached_input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_cached_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,image_cached_input,batch,1.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-2,text_cached_input,batch,0.625,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,image_cached_input,batch,1.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1.5,text_cached_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,image_cached_input,batch,0.13,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1-mini,text_cached_input,batch,0.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,image_cached_input,batch,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-image-1,text_cached_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,image_cached_input,batch,1.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-image-latest,text_cached_input,batch,0.63,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2,video_output,standard,0.1,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output,standard,0.7,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2,video_output,batch,0.05,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,sora-2-pro,video_output,batch,0.35,USD,per second,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-translate,audio_duration,standard,0.034,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-live-transcribe,audio_duration,standard,0.017,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-realtime-whisper,audio_duration,standard,0.017,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-transcribe,audio_duration,standard,0.0045,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe,audio_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe,audio_duration,standard,0.006,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-transcribe,audio_input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-transcribe,text_output,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-transcribe,audio_duration,standard,0.003,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe-diarize,audio_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe-diarize,text_output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-transcribe-diarize,audio_duration,standard,0.006,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,whisper-1,audio_duration,standard,0.006,USD,per minute,estimated cost per minute of audio,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Web search,Web search (all models),standard,10.0,USD,per 1k calls,$10.00 / 1k calls + Search content tokens billed at model rates.,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Web search,Image Web search (all models),standard,10.0,USD,per 1k calls,$10.00 / 1k calls + Search content tokens billed at model rates.,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Web search,"Web search preview (reasoning models, including `gpt-5`, `o-series`)",standard,10.0,USD,per 1k calls,$10.00 / 1k calls + Search content tokens billed at model rates.,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Web search,Web search preview (non-reasoning models),standard,25.0,USD,per 1k calls,$25.00 / 1k calls + Search content tokens are free.,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Containers,Hosted Shell and Code Interpreter,standard,0.03,USD,per 20-minute session per container (by size),"1 GB $0.03, 4 GB $0.12, 16 GB $0.48, 64 GB $1.92 per 20-minute session per container.",https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:File search,Storage,standard,0.1,USD,per GB per day,$0.10 / GB per day (1 GB free),https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:File search,Tool call,standard,2.5,USD,per 1k calls,$2.50 / 1k calls,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,tool:Agent Kit,ChatKit file and image upload storage,standard,0.1,USD,per GB per day,$0.10 / GB-day after 1 GB free per account per month,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chat-latest,input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chat-latest,cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chat-latest,output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,input,standard,1.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,cached_input,standard,0.175,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,output,standard,14.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-rosalind-research,input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-rosalind-research,cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-rosalind-research,output,standard,25.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-search-api,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-search-api,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5-search-api,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,omni-moderation-latest,input,standard,0.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,input,fast,3.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,cached_input,fast,0.35,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.3-codex,output,fast,28.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuning_training,standard,100.0,USD,per hour,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_input,standard,2.0,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_cached_input,standard,0.5,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_output,standard,8.0,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuning_training,standard,25.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_input,standard,3.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_cached_input,standard,0.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_output,standard,12.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuning_training,standard,5.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_input,standard,0.8,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_cached_input,standard,0.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_output,standard,3.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuning_training,standard,1.5,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_input,standard,0.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_cached_input,standard,0.05,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_output,standard,0.8,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuning_training,standard,25.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_input,standard,3.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_cached_input,standard,1.875,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_output,standard,15.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuning_training,standard,3.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_input,standard,0.3,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_cached_input,standard,0.15,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_output,standard,1.2,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuning_training,standard,8.0,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuned_input,standard,3.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuned_output,standard,6.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuning_training,standard,6.0,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuned_input,standard,12.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuned_output,standard,12.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuning_training,standard,0.4,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuned_input,standard,1.6,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuned_output,standard,1.6,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuning_training,batch,100.0,USD,per hour,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_input,batch,1.0,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_cached_input,batch,0.25,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,o4-mini-2025-04-16,fine_tuned_output,batch,4.0,USD,per 1M tokens,data sharing,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuning_training,batch,25.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_input,batch,1.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_cached_input,batch,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-2025-04-14,fine_tuned_output,batch,6.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuning_training,batch,5.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_input,batch,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_cached_input,batch,0.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-mini-2025-04-14,fine_tuned_output,batch,1.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuning_training,batch,1.5,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_input,batch,0.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_cached_input,batch,0.025,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4.1-nano-2025-04-14,fine_tuned_output,batch,0.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuning_training,batch,25.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_input,batch,2.225,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_cached_input,batch,0.9,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-2024-08-06,fine_tuned_output,batch,12.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuning_training,batch,3.0,USD,per 1M training tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_input,batch,0.15,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_cached_input,batch,0.075,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-4o-mini-2024-07-18,fine_tuned_output,batch,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuning_training,batch,8.0,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuned_input,batch,1.5,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-3.5-turbo,fine_tuned_output,batch,3.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuning_training,batch,6.0,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuned_input,batch,6.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,davinci-002,fine_tuned_output,batch,6.0,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuning_training,batch,0.4,USD,per 1M training tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuned_input,batch,0.8,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,babbage-002,fine_tuned_output,batch,0.9,USD,per 1M tokens,legacy,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,chatgpt-4o-latest,input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/chatgpt-4o-latest,2026-09-18
openai,chatgpt-4o-latest,output,standard,15.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/chatgpt-4o-latest,2026-09-18
openai,codex-mini-latest,input,standard,1.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/codex-mini-latest,2026-09-18
openai,codex-mini-latest,cached_input,standard,0.375,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/codex-mini-latest,2026-09-18
openai,codex-mini-latest,output,standard,6.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/codex-mini-latest,2026-09-18
openai,computer-use-preview,input,standard,3.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/computer-use-preview,2026-09-18
openai,computer-use-preview,output,standard,12.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/computer-use-preview,2026-09-18
openai,gpt-4-turbo-preview,input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4-turbo-preview,2026-09-18
openai,gpt-4-turbo-preview,output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4-turbo-preview,2026-09-18
openai,gpt-4-turbo,input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4-turbo,2026-09-18
openai,gpt-4-turbo,output,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4-turbo,2026-09-18
openai,gpt-4.5-preview,input,standard,75.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4.5-preview,2026-09-18
openai,gpt-4.5-preview,cached_input,standard,37.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4.5-preview,2026-09-18
openai,gpt-4.5-preview,output,standard,150.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4.5-preview,2026-09-18
openai,gpt-4,input,standard,30.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4,2026-09-18
openai,gpt-4,output,standard,60.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4,2026-09-18
openai,gpt-4o-audio-preview,input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-audio-preview,2026-09-18
openai,gpt-4o-audio-preview,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-audio-preview,2026-09-18
openai,gpt-4o-audio-preview,audio_input,standard,40.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-audio-preview,2026-09-18
openai,gpt-4o-audio-preview,audio_output,standard,80.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-audio-preview,2026-09-18
openai,gpt-4o-mini-audio-preview,input,standard,0.15,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview,2026-09-18
openai,gpt-4o-mini-audio-preview,output,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview,2026-09-18
openai,gpt-4o-mini-audio-preview,audio_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview,2026-09-18
openai,gpt-4o-mini-audio-preview,audio_output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-audio-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,input,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,cached_input,standard,0.3,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,output,standard,2.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,audio_input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,audio_cached_input,standard,0.3,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-realtime-preview,audio_output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-realtime-preview,2026-09-18
openai,gpt-4o-mini-search-preview,input,standard,0.15,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview,2026-09-18
openai,gpt-4o-mini-search-preview,output,standard,0.6,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview,2026-09-18
openai,gpt-4o-realtime-preview,input,standard,5.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-realtime-preview,cached_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-realtime-preview,output,standard,20.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-realtime-preview,audio_input,standard,40.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-realtime-preview,audio_cached_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-realtime-preview,audio_output,standard,80.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-realtime-preview,2026-09-18
openai,gpt-4o-search-preview,input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-search-preview,2026-09-18
openai,gpt-4o-search-preview,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-4o-search-preview,2026-09-18
openai,gpt-5-chat-latest,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-chat-latest,2026-09-18
openai,gpt-5-chat-latest,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-chat-latest,2026-09-18
openai,gpt-5-chat-latest,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-chat-latest,2026-09-18
openai,gpt-5-codex,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-codex,2026-09-18
openai,gpt-5-codex,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-codex,2026-09-18
openai,gpt-5-codex,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5-codex,2026-09-18
openai,gpt-5.1-chat-latest,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest,2026-09-18
openai,gpt-5.1-chat-latest,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest,2026-09-18
openai,gpt-5.1-chat-latest,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest,2026-09-18
openai,gpt-5.1-codex-max,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-max,2026-09-18
openai,gpt-5.1-codex-max,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-max,2026-09-18
openai,gpt-5.1-codex-max,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-max,2026-09-18
openai,gpt-5.1-codex-mini,input,standard,0.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini,2026-09-18
openai,gpt-5.1-codex-mini,cached_input,standard,0.025,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini,2026-09-18
openai,gpt-5.1-codex-mini,output,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini,2026-09-18
openai,gpt-5.1-codex,input,standard,1.25,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex,2026-09-18
openai,gpt-5.1-codex,cached_input,standard,0.125,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex,2026-09-18
openai,gpt-5.1-codex,output,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.1-codex,2026-09-18
openai,gpt-5.2-chat-latest,input,standard,1.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest,2026-09-18
openai,gpt-5.2-chat-latest,cached_input,standard,0.175,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest,2026-09-18
openai,gpt-5.2-chat-latest,output,standard,14.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest,2026-09-18
openai,gpt-5.2-codex,input,standard,1.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-codex,2026-09-18
openai,gpt-5.2-codex,cached_input,standard,0.175,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-codex,2026-09-18
openai,gpt-5.2-codex,output,standard,14.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.2-codex,2026-09-18
openai,gpt-5.3-chat-latest,input,standard,1.75,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest,2026-09-18
openai,gpt-5.3-chat-latest,cached_input,standard,0.175,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest,2026-09-18
openai,gpt-5.3-chat-latest,output,standard,14.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest,2026-09-18
openai,o1-mini,input,standard,1.1,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-mini,2026-09-18
openai,o1-mini,cached_input,standard,0.55,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-mini,2026-09-18
openai,o1-mini,output,standard,4.4,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-mini,2026-09-18
openai,o1-preview,input,standard,15.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-preview,2026-09-18
openai,o1-preview,cached_input,standard,7.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-preview,2026-09-18
openai,o1-preview,output,standard,60.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o1-preview,2026-09-18
openai,o3-deep-research,input,standard,10.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o3-deep-research,2026-09-18
openai,o3-deep-research,cached_input,standard,2.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o3-deep-research,2026-09-18
openai,o3-deep-research,output,standard,40.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o3-deep-research,2026-09-18
openai,o4-mini-deep-research,input,standard,2.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o4-mini-deep-research,2026-09-18
openai,o4-mini-deep-research,cached_input,standard,0.5,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o4-mini-deep-research,2026-09-18
openai,o4-mini-deep-research,output,standard,8.0,USD,per 1M tokens,,https://developers.openai.com/api/docs/models/o4-mini-deep-research,2026-09-18
openai,rule:batch,discount,batch,-50,USD,percent vs standard,"Batch API: 50% lower cost, 24h completion window; per-model batch tables on the pricing page",https://developers.openai.com/api/docs/guides/batch,2026-09-18
openai,rule:flex,discount,flex,-50,USD,percent vs standard,"Flex processing (beta): tokens priced at Batch API rates; slower, may return 429 resource_unavailable",https://developers.openai.com/api/docs/guides/flex-processing,2026-09-18
openai,rule:fast,premium,fast,100,USD,percent vs standard,"Fast mode (ex-Priority processing, renamed 2026-07-30): 2x standard token rates for GPT-5.6 Sol / GPT-6 Astra; service_tier 'fast' or 'priority'",https://developers.openai.com/api/docs/guides/fast-mode,2026-09-18
openai,rule:cache_write,cache_write,standard,125,USD,percent of uncached input rate,GPT-5.6 and later: cache writes billed at 1.25x uncached input; earlier models: no cache-write charge,https://developers.openai.com/api/docs/guides/prompt-caching,2026-09-18
openai,rule:cache_read_gpt-5.6+,cached_input,standard,10,USD,percent of uncached input rate,GPT-5.6 and later: cache reads at 0.1x uncached input rate,https://developers.openai.com/api/docs/guides/prompt-caching,2026-09-18
openai,rule:long_context,multiplier,standard,,USD,x standard,"Prompts >272K input tokens: 2x input (and cache) rates, 1.5x output rate for the full request (GPT-5.4 / 5.5 / 5.6 / 6 Astra)",https://developers.openai.com/api/docs/pricing,2026-09-18
openai,rule:data_residency,uplift,standard,10,USD,percent,Regional processing endpoints (us./eu./ae. …api.openai.com): 10% uplift for models released on or after 2026-03-05 that are eligible for data residency,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,rule:container_billing,session,standard,,USD,"per minute, 5-minute minimum",Since 2026-06-02 eligible container sessions (Code Interpreter / Hosted Shell) are billed per minute with a 5-minute minimum instead of the full 20-minute rate,https://developers.openai.com/api/docs/changelog,2026-09-18
openai,rule:web_search_content_tokens_mini,input,standard,,USD,"8,000 input tokens per call","gpt-4o-mini and gpt-4.1-mini with the non-preview web search tool: search content tokens billed as a fixed block of 8,000 input tokens per call",https://developers.openai.com/api/docs/pricing,2026-09-18
openai,rule:pro_mode,output,standard,,USD,standard token rates,reasoning.mode: pro (GPT-5.6) aggregates all model work and bills it at the model's standard token rates (more tokens than standard mode),https://developers.openai.com/api/docs/guides/reasoning,2026-09-18
openai,gpt-rosalind-research,billing_start,standard,,USD,date,Billing begins 2026-10-05; cache-write pricing does not apply,https://developers.openai.com/api/docs/pricing,2026-09-18
openai,gpt-5.6-sol,promotion,standard,,USD,note,Promotional pricing ($4 in / $20 out) available at least through 2026-11-21,https://developers.openai.com/api/docs/pricing,2026-09-18
xai,grok-4.6,input,standard,2.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,cached_input,standard,0.5,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,image_input,standard,2.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,output,standard,6.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,input,long_context,4.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,cached_input,long_context,1.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,output,long_context,12.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,batch,batch,,USD,per 1M tokens,Batch API not supported for this model (model page),https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.6,input,priority,4.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.6,cached_input,priority,1.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.6,output,priority,12.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.6 @ https://us.api.x.ai/v1,input,us_regional,2.2,USD,per 1M tokens,US regional endpoint = 1.1x global token rates (live catalogue on us.api.x.ai shows 22000/5500/66000 ticks); long-context rates also x1.1,https://docs.x.ai/developers/advanced-api-usage/regions,2026-09-19
xai,grok-4.6 @ https://us.api.x.ai/v1,cached_input,us_regional,0.55,USD,per 1M tokens,US regional endpoint = 1.1x global token rates (live catalogue on us.api.x.ai shows 22000/5500/66000 ticks); long-context rates also x1.1,https://docs.x.ai/developers/advanced-api-usage/regions,2026-09-19
xai,grok-4.6 @ https://us.api.x.ai/v1,image_input,us_regional,2.2,USD,per 1M tokens,US regional endpoint = 1.1x global token rates (live catalogue on us.api.x.ai shows 22000/5500/66000 ticks); long-context rates also x1.1,https://docs.x.ai/developers/advanced-api-usage/regions,2026-09-19
xai,grok-4.6 @ https://us.api.x.ai/v1,output,us_regional,6.6,USD,per 1M tokens,US regional endpoint = 1.1x global token rates (live catalogue on us.api.x.ai shows 22000/5500/66000 ticks); long-context rates also x1.1,https://docs.x.ai/developers/advanced-api-usage/regions,2026-09-19
xai,grok-4.5,input,standard,2.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,cached_input,standard,0.3,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,image_input,standard,2.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,output,standard,6.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,input,long_context,4.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,cached_input,long_context,0.6,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,output,long_context,12.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,batch,batch,,USD,per 1M tokens,Batch API not supported for this model (model page),https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.5,input,priority,4.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.5,cached_input,priority,0.6,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.5,output,priority,12.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.3,input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,cached_input,standard,0.2,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,image_input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,output,standard,2.5,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,input,long_context,2.5,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,cached_input,long_context,0.4,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,output,long_context,5.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,input,batch,1.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,cached_input,batch,0.16,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,output,batch,2.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.3,input,priority,2.5,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.3,cached_input,priority,0.4,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.3,output,priority,5.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-reasoning,input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,cached_input,standard,0.2,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,image_input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,output,standard,2.5,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,input,long_context,2.5,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,cached_input,long_context,0.4,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,output,long_context,5.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,input,batch,1.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,cached_input,batch,0.16,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,output,batch,2.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-reasoning,input,priority,2.5,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-reasoning,cached_input,priority,0.4,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-reasoning,output,priority,5.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-non-reasoning,input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,cached_input,standard,0.2,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,image_input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,output,standard,2.5,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,input,long_context,2.5,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,cached_input,long_context,0.4,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,output,long_context,5.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,input,batch,1.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,cached_input,batch,0.16,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,output,batch,2.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-0309-non-reasoning,input,priority,2.5,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-non-reasoning,cached_input,priority,0.4,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-0309-non-reasoning,output,priority,5.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-4.20-multi-agent-0309,input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,cached_input,standard,0.2,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,image_input,standard,1.25,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,output,standard,2.5,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,input,long_context,2.5,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,cached_input,long_context,0.4,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,output,long_context,5.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,input,batch,1.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,cached_input,batch,0.16,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-4.20-multi-agent-0309,output,batch,2.0,USD,per 1M tokens,"Batch API 20% off standard (< 200,000 prompt tokens); applies to input, output, cached and reasoning tokens",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,input,standard,1.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,cached_input,standard,0.2,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,image_input,standard,1.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output (image tokens priced like text)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,output,standard,2.0,USD,per 1M tokens,"prompt < 200,000 tokens; reasoning tokens billed as output",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,input,long_context,2.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,cached_input,long_context,0.4,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,output,long_context,4.0,USD,per 1M tokens,"prompt >= 200,000 tokens -> higher rate for ALL tokens of the request",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,batch,batch,,USD,per 1M tokens,Batch API not supported for this model (model page),https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-build-0.1,input,priority,2.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-build-0.1,cached_input,priority,0.4,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-build-0.1,output,priority,4.0,USD,per 1M tokens,service_tier=priority -> 2x standard on all token types (caching discount applied before multiplier); billed only when response service_tier == 'priority',https://docs.x.ai/developers/advanced-api-usage/priority-processing,2026-09-19
xai,grok-imagine-image,image_output,standard,0.02,USD,per image,default tier (image_price); Batch API accepted where supported but no discount; also via image_generation tool,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,standard,0.06,USD,per image,default tier (image_price); Batch API accepted where supported but no discount; also via image_generation tool,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=low resolution=1k,0.04,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=low resolution=2k,0.06,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=low resolution=1.5k,0.05,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=medium resolution=1k,0.06,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=medium resolution=2k,0.08,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-2.0,image_output,quality=medium resolution=1.5k,0.07,USD,per image,"quality auto (default) bills at the quality actually served (low for generation, medium for editing)",https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-image-quality,image_output,standard,0.05,USD,per image,default tier (image_price); Batch API accepted where supported but no discount; also via image_generation tool,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-video,video_output,standard,0.05,USD,per second,billed per second of generated video; batch at standard rates,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-imagine-video-1.5,video_output,standard,0.08,USD,per second,billed per second of generated video; batch at standard rates,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-voice-think-fast-2.0 (speech-to-speech),audio_input_output,standard,0.08,USD,per minute,$4.80 / hour of audio sent or received,https://docs.x.ai/developers/pricing,2026-09-19
xai,grok-voice-think-fast-2.0 (speech-to-speech),text_input_message,standard,0.004,USD,per message,per conversation.item.create text item (function_call_output and audio items excluded),https://docs.x.ai/developers/pricing,2026-09-19
xai,speech-to-text (grok-voice-transcribe-*),audio_input,rest,0.1,USD,per hour,POST /v1/stt,https://docs.x.ai/developers/pricing,2026-09-19
xai,speech-to-text (grok-voice-transcribe-*),audio_input,streaming,0.2,USD,per hour,wss://api.x.ai/v1/stt,https://docs.x.ai/developers/pricing,2026-09-19
xai,text-to-speech,text_input,standard,15.0,USD,per 1M characters,POST /v1/tts and streaming,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:web_search,per_call,standard,5.0,USD,per 1K calls,only successful server-side tool executions are billed; includes image search; view_image results token-billed only,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:x_search,per_call,standard,5.0,USD,per 1K calls,only successful server-side tool executions are billed; UNTIL 2026-09-21 12:00 PT: per 1k calls. FROM 2026-09-21: $5 per 1k posts fetched + $10 per 1k user profiles fetched (every post returned incl. parent/quoted counts),https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:code_execution / code_interpreter,per_call,standard,5.0,USD,per 1K calls,only successful server-side tool executions are billed; Python sandbox; code_interpreter alias not supported in gRPC/xai-sdk,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:attachment_search,per_call,standard,10.0,USD,per 1K calls,only successful server-side tool executions are billed; search files attached to messages,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:collections_search / file_search,per_call,standard,2.5,USD,per 1K calls,only successful server-side tool executions are billed; RAG over collections; file_search alias not supported in gRPC/xai-sdk,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:x_search (posts),per_post_fetched,from 2026-09-21,5.0,USD,per 1K posts,replaces per-call billing on 2026-09-21 12:00 PT,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:x_search (profiles),per_profile_fetched,from 2026-09-21,10.0,USD,per 1K profiles,user search results,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:image_generation,per_call,standard,0.0,USD,per call,no invocation fee: image_generation billed at Imagine per-image rates; view_* and MCP billed through tokens only,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:view_image,per_call,standard,0.0,USD,per call,no invocation fee: image_generation billed at Imagine per-image rates; view_* and MCP billed through tokens only,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:view_x_video,per_call,standard,0.0,USD,per call,no invocation fee: image_generation billed at Imagine per-image rates; view_* and MCP billed through tokens only,https://docs.x.ai/developers/pricing,2026-09-19
xai,tool:mcp (remote MCP tools),per_call,standard,0.0,USD,per call,no invocation fee: image_generation billed at Imagine per-image rates; view_* and MCP billed through tokens only,https://docs.x.ai/developers/pricing,2026-09-19
xai,files,storage_gb_day,standard,0.025,USD,per GiB per day,file storage,https://docs.x.ai/developers/pricing,2026-09-19
xai,collections,storage_gb_day,standard,0.1,USD,per GiB per day,collection storage,https://docs.x.ai/developers/pricing,2026-09-19
xai,files,download_gb,standard,0.2,USD,per GiB,downloads,https://docs.x.ai/developers/pricing,2026-09-19
xai,collections,download_gb,standard,0.2,USD,per GiB,downloads,https://docs.x.ai/developers/pricing,2026-09-19
xai,usage-guideline-violation (Responses API),per_request_fee,standard,0.05,USD,per request,charged when a violation is caught before generation; generations that violate are still charged,https://docs.x.ai/developers/pricing,2026-09-19
xai,management-api (https://management-api.x.ai),per_call,standard,0.0,USD,per call,no pricing documented; requires a Management key (not available to this atlas -> ACCOUNT_RESTRICTED),https://docs.x.ai/developers/management-api-guide,2026-09-19
xai,"GET /v1/models, /v1/language-models, /v1/api-key, /v1/me, POST /v1/tokenize-text",per_call,standard,0.0,USD,per call,"no usage returned; free (not documented explicitly, observed: no cost_in_usd_ticks)",https://docs.x.ai/developers/rest-api-reference/inference/models,2026-09-19