{ "azure/gpt-realtime-2.1-2026-07-07": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "cache_read_input_image_token_cost": 5e-07, "supports_prompt_caching": true, "supports_reasoning": true }, "azure/gpt-realtime-2.1-mini-2026-07-07": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "cache_read_input_image_token_cost": 8e-08, "supports_prompt_caching": true, "supports_reasoning": true }, "azure/gpt-realtime-translate-2026-05-06": { "input_cost_per_second": 0.0005666666666666667, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/a-new-chapter-for-realtime-ai-reasoning-translation-and-real-time-transcription/4517124", "supported_modalities": [ "audio" ], "supported_output_modalities": [ "audio", "text" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true }, "azure/gpt-realtime-translate-2026-05-07": { "input_cost_per_second": 0.0005666666666666667, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://ai.azure.com/catalog/models/gpt-realtime-translate", "supported_modalities": [ "audio" ], "supported_output_modalities": [ "audio", "text" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true }, "azure/gpt-realtime-whisper-2026-05-06": { "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", "mode": "audio_transcription", "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "max_input_tokens": 32000, "max_output_tokens": 4096 }, "azure/gpt-realtime-whisper-2026-05-07": { "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", "mode": "audio_transcription", "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "max_input_tokens": 32000, "max_output_tokens": 4096 }, "sample_spec": { "code_interpreter_cost_per_session": 0.0, "computer_use_input_cost_per_1k_tokens": 0.0, "computer_use_output_cost_per_1k_tokens": 0.0, "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD", "file_search_cost_per_1k_calls": 0.0, "file_search_cost_per_gb_per_day": 0.0, "input_cost_per_audio_token": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", "max_input_tokens": "max input tokens, if the provider specifies it", "max_output_tokens": "max output tokens, if the provider specifies it", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank, search", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, "search_context_cost_per_query": { "search_context_size_high": 0.0, "search_context_size_low": 0.0, "search_context_size_medium": 0.0 }, "supported_regions": [ "global", "us-west-2", "eu-west-1", "ap-southeast-1", "ap-northeast-1" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "vector_store_cost_per_gb_per_day": 0.0 }, "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06 }, "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, "abliteration/abliterated-model": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "abliteration", "max_input_tokens": 262144, "max_output_tokens": 262134, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://abliteration.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ] }, "abliteration/abliterated-model-large": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "abliteration", "max_input_tokens": 1000000, "max_output_tokens": 999990, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://abliteration.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ] }, "abliteration/abliterated-model-large-v2": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "abliteration", "max_input_tokens": 1000000, "max_output_tokens": 999990, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://abliteration.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_none_reasoning_effort": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ] }, "abliteration/abliterated-model-large-flash": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "abliteration", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://abliteration.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ] }, "ai21.j2-mid-v1": { "input_cost_per_token": 1.25e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.j2-ultra-v1": { "input_cost_per_token": 1.88e-05, "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.88e-05, "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-1-5-large-v1:0": { "deprecation_date": "2026-11-26", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" }, "ai21.jamba-1-5-mini-v1:0": { "deprecation_date": "2026-11-26", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" }, "ai21.jamba-instruct-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_system_messages": true }, "aiml/dall-e-2": { "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" }, "mode": "image_generation", "output_cost_per_image": 0.026, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/dall-e-3": { "litellm_provider": "aiml", "metadata": { "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" }, "mode": "image_generation", "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-pro": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", "output_cost_per_image": 0.065, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-pro/v1.1": { "litellm_provider": "aiml", "mode": "image_generation", "output_cost_per_image": 0.052, "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-pro/v1.1-ultra": { "litellm_provider": "aiml", "mode": "image_generation", "output_cost_per_image": 0.063, "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux-realism": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro - Professional-grade image generation model" }, "mode": "image_generation", "output_cost_per_image": 0.046, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux/dev": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", "output_cost_per_image": 0.033, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux/kontext-max/text-to-image": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", "output_cost_per_image": 0.104, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux/kontext-pro/text-to-image": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/flux/schnell": { "litellm_provider": "aiml", "metadata": { "notes": "Flux Schnell - Fast generation model optimized for speed" }, "mode": "image_generation", "output_cost_per_image": 0.004, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/google/imagen-4.0-ultra-generate-001": { "litellm_provider": "aiml", "metadata": { "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" }, "mode": "image_generation", "output_cost_per_image": 0.078, "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/google/nano-banana-pro": { "litellm_provider": "aiml", "metadata": { "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" }, "mode": "image_generation", "output_cost_per_image": 0.195, "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", "supported_endpoints": [ "/v1/images/generations" ] }, "aiml/openai/gpt-image-2": { "litellm_provider": "aiml", "metadata": { "notes": "OpenAI gpt-image-2 via AI/ML API - flagship multimodal image generation and editing model with reasoning and 2K output. output_cost_per_image is AI/ML's published medium-quality rate; like the other aiml image entries it is billed as a flat per-image price" }, "mode": "image_generation", "output_cost_per_image": 0.054, "source": "https://docs.aimlapi.com/api-references/image-models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06, "supports_nova_canvas_image_edit": true }, "us.amazon.nova-canvas-v1:0": { "deprecation_date": "2026-09-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", "output_cost_per_image": 0.06, "supports_nova_canvas_image_edit": true }, "us.writer.palmyra-x4-v1:0": { "deprecation_date": "2027-03-09", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { "deprecation_date": "2027-03-21", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { "deprecation_date": "2027-03-09", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { "deprecation_date": "2027-03-21", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-vision-7b": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_vision": true }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "output_cost_per_token_batches": 1.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_priority": 4.375e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 3.125e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_image_token": 1.25e-06, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.75e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "apac.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 9.9e-08, "input_cost_per_token": 3.96e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.311e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "apac.amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 3.4375e-07, "input_cost_per_token": 1.375e-06, "input_cost_per_image_token": 1.375e-06, "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "eu.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 1.0725e-07, "input_cost_per_token": 4.29e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.597e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "eu.amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 3.4375e-07, "input_cost_per_token": 1.375e-06, "input_cost_per_image_token": 1.375e-06, "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_flex": 4.125e-08, "cache_read_input_token_cost_priority": 1.44375e-07, "input_cost_per_token": 3.3e-07, "input_cost_per_token_batches": 1.65e-07, "input_cost_per_token_flex": 1.65e-07, "input_cost_per_token_priority": 5.775e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-06, "output_cost_per_token_batches": 1.375e-06, "output_cost_per_token_flex": 1.375e-06, "output_cost_per_token_priority": 4.8125e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "us.amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 3.4375e-07, "input_cost_per_token": 1.375e-06, "input_cost_per_image_token": 1.375e-06, "input_cost_per_audio_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.40625e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 1.925e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-07, "input_cost_per_image": 6e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "output_cost_per_token": 0.0, "output_vector_size": 3072, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, "supports_audio_input": true }, "amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "output_cost_per_token_batches": 7e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "amazon.nova-premier-v1:0": { "cache_read_input_token_cost": 6.25e-07, "cache_read_input_token_cost_priority": 1.09375e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_priority": 4.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "output_cost_per_token_batches": 6.25e-06, "output_cost_per_token_priority": 2.1875e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "input_cost_per_token_flex": 4e-07, "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, "output_cost_per_token_priority": 5.6e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "amazon.nova-2-sonic-v1:0": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-sonic.md", "supports_audio_input": true, "supports_audio_output": true }, "amazon.rerank-v1:0": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, "amazon.titan-embed-image-v1": { "input_cost_per_image": 6e-05, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", "supports_embedding_image_input": true, "supports_image_input": true }, "amazon.titan-embed-text-v1": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "amazon.titan-embed-g1-text-02": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "amazon.titan-embed-text-v2:0": { "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "provider_specific_entry": { "bedrock_invocation_schema": "titan_v2" } }, "amazon.titan-image-generator-v1": { "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", "mode": "image_generation" }, "amazon.titan-image-generator-v2": { "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", "mode": "image_generation", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "amazon.titan-image-generator-v2:0": { "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", "mode": "image_generation", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true }, "us.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true }, "eu.twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true }, "twelvelabs.marengo-embed-3-0-v1:0": { "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, "supports_embedding_image_input": true, "supports_image_input": true }, "us.twelvelabs.marengo-embed-3-0-v1:0": { "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, "supports_embedding_image_input": true, "supports_image_input": true }, "eu.twelvelabs.marengo-embed-3-0-v1:0": { "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, "supports_embedding_image_input": true, "supports_image_input": true }, "twelvelabs.pegasus-1-2-v1:0": { "deprecation_date": "2027-03-22", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { "deprecation_date": "2027-03-22", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { "deprecation_date": "2027-03-22", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "global.twelvelabs.pegasus-1-2-v1:0": { "deprecation_date": "2027-03-22", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md" }, "amazon.titan-text-express-v1": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07 }, "amazon.titan-text-lite-v1": { "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-07 }, "amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, "anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 2048 }, "anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, "output_cost_per_token_batches": 2.5e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, "anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true }, "anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "token_count_model": { "model": "anthropic.claude-opus-4-1-20250805-v1:0", "litellm_provider": "bedrock" } }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-5-20251101-v1:0", "litellm_provider": "bedrock" } }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-6-v1", "litellm_provider": "bedrock" } }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-6-v1", "litellm_provider": "bedrock" } }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-6-v1", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-6-v1", "litellm_provider": "bedrock" } }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-6-v1", "litellm_provider": "bedrock" } }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "anthropic.claude-mythos-preview": { "cache_creation_input_token_cost": 3.4375e-05, "cache_creation_input_token_cost_above_1hr": 5.5e-05, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 2.75e-05, "output_cost_per_token": 0.0001375, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "global.anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "eu-west-1" } }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-fable-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "global.anthropic.claude-fable-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/claude-fable-latest": { "alias_of": "global.anthropic.claude-fable-5-2" }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "cache_read_input_token_cost": 1.1e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-fable-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "cache_read_input_token_cost": 1.1e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, "anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_token_batches": 1.25e-05 }, "anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "thinking_always_on": true, "supports_forced_tool_use": false, "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", "token_count_model": { "model": "global.anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_token_batches": 1.25e-05 }, "global.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, "supports_forced_tool_use": false, "token_count_model": { "model": "global.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "bedrock/claude-opus-latest": { "alias_of": "global.anthropic.claude-opus-5-5" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-east-1/index.json", "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.375e-05 }, "us.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 4.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, "supports_forced_tool_use": false, "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/eu-west-1/index.json", "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "eu-west-1" }, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.375e-05 }, "eu.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 4.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-southeast-2/index.json", "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" }, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.375e-05 }, "au.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 4.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "jp.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.375e-05 }, "jp.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 4.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "global.anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "eu-west-1" } }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "ap-northeast-1" } }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "ap-northeast-1" } }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "global.anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "eu-west-1" } }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-20250514-v1:0", "litellm_provider": "bedrock" } }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, "anthropic.claude-v2:1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "anyscale/HuggingFaceH4/zephyr-7b-beta": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07 }, "anyscale/codellama/CodeLlama-34b-Instruct-hf": { "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, "anyscale/codellama/CodeLlama-70b-Instruct-hf": { "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" }, "anyscale/google/gemma-7b-it": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" }, "anyscale/meta-llama/Llama-2-13b-chat-hf": { "input_cost_per_token": 2.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07 }, "anyscale/meta-llama/Llama-2-70b-chat-hf": { "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, "anyscale/meta-llama/Llama-2-7b-chat-hf": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07 }, "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" }, "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" }, "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", "supports_function_calling": true }, "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { "input_cost_per_token": 9e-07, "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", "supports_function_calling": true }, "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { "input_cost_per_token": 1.5e-07, "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", "supports_function_calling": true }, "apac.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.575e-08, "input_cost_per_token": 6.3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "apac.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 9.25e-09, "input_cost_per_token": 3.7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-07, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "apac.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.1e-07, "cache_read_input_token_cost_flex": 1.05e-07, "input_cost_per_token": 8.4e-07, "input_cost_per_token_flex": 4.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.36e-06, "output_cost_per_token_flex": 1.68e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "apac.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-20250514-v1:0", "litellm_provider": "bedrock" } }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, "litellm_provider": "assemblyai", "mode": "audio_transcription", "output_cost_per_second": 0.0 }, "assemblyai/nano": { "input_cost_per_second": 0.00010278, "litellm_provider": "assemblyai", "mode": "audio_transcription", "output_cost_per_second": 0.0 }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "au.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "azure/ada": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/claude-haiku-4-5": { "deprecation_date": "2026-11-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 4096, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "supports_web_search": true, "prompt_cache_min_tokens": 4096, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { "deprecation_date": "2027-02-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 4096 }, "azure_ai/claude-opus-4-7": { "deprecation_date": "2027-04-06", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 2048 }, "azure_ai/claude-fable-5": { "deprecation_date": "2027-12-05", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 1e-06, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": false, "supports_web_search": true, "prompt_cache_min_tokens": 512 }, "azure_ai/claude-fable-5-1": { "supports_mid_conversation_system": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 2.5e-07, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": false, "supports_web_search": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-12-05", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" }, "azure_ai/claude-fable-latest": { "alias_of": "azure_ai/claude-fable-5-2" }, "azure_ai/claude-mythos-5-1": { "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 2.5e-07, "deprecation_date": "2027-09-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": false, "supports_web_search": true, "prompt_cache_min_tokens": 512, "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement" }, "azure_ai/claude-opus-5": { "deprecation_date": "2027-07-08", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 512 }, "azure_ai/claude-opus-5-5": { "supports_mid_conversation_system": true, "input_cost_per_token": 4e-06, "output_cost_per_token": 2e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-09-18", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 512, "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, "azure_ai/claude-opus-latest": { "alias_of": "azure_ai/claude-opus-5-5" }, "azure_ai/claude-opus-4-8": { "deprecation_date": "2027-09-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { "deprecation_date": "2026-11-30", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { "deprecation_date": "2027-06-30", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-6": { "deprecation_date": "2027-02-10", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, "azure/computer-use-preview": { "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/container": { "code_interpreter_cost_per_session": 0.033, "litellm_provider": "azure", "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { "deprecation_date": "2027-09-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true }, "azure_ai/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://ai.azure.com/catalog/models/gpt-6-astra", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure_ai/gpt-astra-latest": { "alias_of": "azure_ai/gpt-6-astra" }, "azure_ai/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure_ai/gpt-luna-latest": { "alias_of": "azure_ai/gpt-6-luna" }, "azure_ai/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure_ai/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure_ai/gpt-sol-latest": { "alias_of": "azure_ai/gpt-6.1-sol" }, "azure_ai/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_above_272k_tokens": 1e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure_ai/gpt-terra-latest": { "alias_of": "azure_ai/gpt-6.1-terra" }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 6e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure_ai/gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true }, "azure_ai/codex-mini": { "cache_read_input_token_cost": 3.75e-07, "deprecation_date": "2026-11-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/whisper": { "deprecation_date": "2026-12-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_second": 0.0001, "litellm_provider": "azure_ai", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 6e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 6e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 3e-05, "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-2026-03-05": { "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 3e-05, "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-pro": { "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-pro-2026-03-05": { "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-mini-latest": { "alias_of": "azure_ai/gpt-5.4-mini" }, "azure_ai/gpt-5.4-mini-2026-03-17": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_priority": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4-nano-2026-03-17": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_priority": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/model_router": { "deprecation_date": "2027-05-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" }, "azure_ai/model-router": { "deprecation_date": "2027-05-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-4o": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-4o-mini": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3.3e-07, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_audio_token": 1.1e-05, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/gpt-4o-realtime-preview-2024-12-17": { "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "successor_model": "azure/eu/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "successor_model": "azure/eu/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, "azure/eu/o1-mini-2024-09-12": { "cache_read_input_token_cost": 6.05e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false }, "azure/eu/o3-mini": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/global-standard/gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/global-standard/gpt-4o-mini": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/global/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/global/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/global/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/global/gpt-5.1": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/global/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-3.5-turbo": { "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo": { "input_cost_per_token": 5e-07, "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-35-turbo-instruct": { "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo-instruct-0914": { "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-4-0125-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-1106-preview": { "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo": { "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4.1": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/gpt-4.1-nano": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o-2024-05-13": { "deprecation_date": "2027-01-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-audio": { "deprecation_date": "2027-03-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" }, "azure/gpt-audio-2025-08-28": { "deprecation_date": "2027-03-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-audio-mini": { "deprecation_date": "2027-06-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-audio-mini-2025-10-06": { "deprecation_date": "2027-04-06", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-4o-audio-preview-2024-12-17": { "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-4o-mini": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime": { "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-2025-08-28": { "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-03-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-1.5": { "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-1.5-2026-02-23": { "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-realtime-2.1-2026-07-07", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-2.1-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-mini": { "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "cache_read_input_image_token_cost": 8e-08, "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-06-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-04-06", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "provider_specific_entry": { "realtime_ga_only": 1 }, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { "deprecation_date": "2027-06-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-mini-tts": { "deprecation_date": "2027-06-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "azure/gpt-4o-realtime-preview-2024-12-17": { "cache_read_input_audio_token_cost": 2.5e-06, "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { "deprecation_date": "2026-10-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-realtime-whisper": { "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "audio_transcription", "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.2", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.2-codex", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.1-codex-mini-2025-11-13": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.5e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-03-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.1-codex", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-mini": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-mini", "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-mini", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_priority": 3.6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-nano", "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4-nano", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.2-pro", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.1": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.2", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_vision": true }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/gpt-5.3-chat": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/us/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/us/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/eu/gpt-5.2-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/eu/gpt-5.3-chat": { "cache_read_input_token_cost": 1.925e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-chat-latest", "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.2-codex", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.2": { "deprecation_date": "2027-06-08", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4", "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.4", "input_cost_per_token": 1.75e-06, "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.3-codex", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/gpt-5.4": { "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.5", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "cache_read_input_token_cost_batches": 1.3e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 3e-05, "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_flex": 1.25e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, "cache_read_input_token_cost_batches": 1.43e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens": 5.5e-06, "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.5", "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, "cache_read_input_token_cost_batches": 1.43e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens": 5.5e-06, "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.5", "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 3e-05, "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_flex": 1.25e-06, "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_batches": 1.3e-07, "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens": 5.5e-06, "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, "cache_read_input_token_cost_batches": 1.43e-07, "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.5", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_above_272k_tokens": 5.5e-06, "input_cost_per_token_batches": 1.375e-06, "output_cost_per_token_above_272k_tokens": 2.475e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, "cache_read_input_token_cost_batches": 1.43e-07, "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.5-pro", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "input_cost_per_token_above_272k_tokens_flex": 3e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/gpt-5.4-pro-2026-03-05": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.5-pro", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_above_272k_tokens_flex": 3e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "cache_read_input_token_cost_priority": 8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_priority": 8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_flex": 2.5e-06, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, "cache_read_input_token_cost_priority": 8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, "input_cost_per_token_priority": 8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol-2026-07-09": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_flex": 2.5e-06, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, "cache_read_input_token_cost_priority": 8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6-sol", "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, "input_cost_per_token_priority": 8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, "output_cost_per_token_priority": 4e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_flex": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-terra-2026-07-09": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6.1-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-luna-2026-07-09": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "input_cost_per_token_above_272k_tokens_flex": 1e-05, "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "input_cost_per_token_flex": 5e-06, "output_cost_per_token_flex": 2.5e-05, "cache_read_input_token_cost_flex": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-06 }, "azure/gpt-astra-latest": { "alias_of": "azure/gpt-6-astra" }, "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "input_cost_per_token_above_272k_tokens_flex": 1e-05, "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "input_cost_per_token_flex": 5e-06, "output_cost_per_token_flex": 2.5e-05, "cache_read_input_token_cost_flex": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-06 }, "azure/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "deprecation_date": "2028-03-11", "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_flex": 5e-09, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_flex": 2.5e-07 }, "azure/gpt-luna-latest": { "alias_of": "azure/gpt-6-luna" }, "azure/gpt-6-luna-2026-09-22": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "deprecation_date": "2028-03-11", "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_flex": 5e-09, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_flex": 2.5e-07 }, "azure/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 5e-06, "cache_read_input_token_cost_flex": 1e-07, "cache_creation_input_token_cost_flex": 1.25e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, "azure/gpt-6-sol-2026-09-22": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_priority": 2e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 5e-06, "cache_read_input_token_cost_flex": 1e-07, "cache_creation_input_token_cost_flex": 1.25e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, "azure/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_above_272k_tokens": 1e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/gpt-terra-latest": { "alias_of": "azure/gpt-6.1-terra" }, "azure/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 5e-06, "cache_read_input_token_cost_flex": 5e-08, "cache_creation_input_token_cost_flex": 1.25e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, "azure/gpt-sol-latest": { "alias_of": "azure/gpt-6.1-sol" }, "azure/gpt-6.1-sol-2026-09-29": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 5e-06, "cache_read_input_token_cost_flex": 5e-08, "cache_creation_input_token_cost_flex": 1.25e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06 }, "azure/us/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, "cache_read_input_token_cost": 5.5e-08, "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_above_272k_tokens": 2.2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-06, "output_cost_per_token_above_272k_tokens": 8.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/us/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 3e-06, "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, "input_cost_per_token": 1.2e-06, "input_cost_per_token_above_272k_tokens": 2.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_272k_tokens": 9e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2.4e-06, "input_cost_per_token_above_272k_tokens": 4.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/apac/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 3e-06, "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_above_272k_tokens": 1.2e-07, "input_cost_per_token": 1.2e-06, "input_cost_per_token_above_272k_tokens": 2.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_272k_tokens": 9e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/gpt-6-1-terra-now-generally-available-in-microsoft-foundry-build-agents-that-see/4567769", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/apac/gpt-6.1-sol": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2.4e-06, "input_cost_per_token_above_272k_tokens": 4.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ "medium" ], "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ "medium" ], "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/us/gpt-5.6": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, "cache_creation_input_token_cost_priority": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, "cache_creation_input_token_cost_priority": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-6-sol", "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-6.1-terra", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.75e-07, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-6-luna", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/us/gpt-6-astra": { "deprecation_date": "2028-01-11", "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/us/gpt-6-luna": { "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, "cache_read_input_token_cost": 1.1e-08, "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/us/gpt-6-sol": { "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": {"search_context_size_high":0.014,"search_context_size_low":0.014,"search_context_size_medium":0.014}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/us/gpt-chat-latest": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, "reasoning_effort_levels": [ "medium" ], "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/eu/gpt-5.6": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, "cache_creation_input_token_cost_priority": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, "cache_creation_input_token_cost_priority": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-6-sol", "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-6.1-terra", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.75e-07, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-6-luna", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.5": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_batches": 2.5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.5": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.5": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_batches": 2.5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_batches": 1.5e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token_above_272k_tokens_batches": 5e-06, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6", "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-24": { "deprecation_date": "2027-10-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, "cache_read_input_token_cost_batches": 2.75e-07, "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false }, "azure/gpt-5.5-pro-2026-04-23": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-mini-latest": { "alias_of": "azure/gpt-5.4-mini" }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-image-1.5", "input_cost_per_image_token": 1e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/low/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/low/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/low/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/gpt-image-1-mini": { "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-image-2", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, "output_cost_per_token": 1e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-image-2", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, "output_cost_per_token": 1e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "azure/low/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/low/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/low/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 2.0345052083e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/medium/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 7.9752604167e-09, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_pixel": 3.1575520833e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "azure/mistral-large-2402": { "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/mistral-large-latest": { "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true }, "azure/o1": { "deprecation_date": "2026-11-19", "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o1-mini": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, "azure/o3": { "deprecation_date": "2026-11-19", "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o3-2025-04-16": { "deprecation_date": "2026-11-19", "successor_model": "azure/gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure/o3-mini": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/o3-pro": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o3-pro-2025-06-10": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o4-mini": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-terra", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/standard/1024-x-1024/dall-e-2": { "input_cost_per_pixel": 0.0, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "azure/speech/azure-tts-hd": { "input_cost_per_character": 3e-05, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" }, "azure/speech/azure-stt": { "audio_transcription_config": "azure_speech", "input_cost_per_second": 0.0002777778, "litellm_provider": "azure", "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/tts-1": { "deprecation_date": "2026-12-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/tts-1-hd": { "deprecation_date": "2026-12-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_character": 3.3e-05, "litellm_provider": "azure", "mode": "audio_speech", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_creation_input_token_cost": 1.38e-06, "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o-mini": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.65e-07, "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3.3e-07, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_audio_token": 1.1e-05, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/us/gpt-4o-realtime-preview-2024-12-17": { "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-mini", "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-nano", "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.2", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.2-codex", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o1": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "successor_model": "azure/us/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "successor_model": "azure/us/gpt-5.6-sol", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, "output_cost_per_token_batches": 3.3e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o1-mini-2024-09-12": { "cache_read_input_token_cost": 6.05e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false }, "azure/us/o3": { "deprecation_date": "2026-11-19", "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o3-2025-04-16": { "deprecation_date": "2026-11-19", "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o3-mini": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6-terra", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure/whisper-1": { "deprecation_date": "2027-02-26", "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" }, "azure_ai/Cohere-embed-v3-english": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, "azure_ai/Codestral-2501": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": false }, "azure_ai/FLUX-1.1-pro": { "deprecation_date": "2027-01-05", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/FLUX.1-Kontext-pro": { "deprecation_date": "2027-01-05", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/flux.2-pro": { "deprecation_date": "2027-01-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/FLUX.2-flex": { "deprecation_date": "2027-01-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "azure_ai/FW-DeepSeek-V3.2": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 3.1e-07, "input_cost_per_token": 6.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-DeepSeek-V4-Pro": { "cache_read_input_token_cost": 1.65e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5": { "deprecation_date": "2027-07-01", "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.1": { "deprecation_date": "2027-07-01", "successor_model": "azure_ai/FW-GLM-5.2", "cache_read_input_token_cost": 2.86e-07, "input_cost_per_token": 1.54e-06, "litellm_provider": "azure_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.54e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { "cache_read_input_token_cost": 2.31e-07, "input_cost_per_token": 2.31e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Kimi-K2.5": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/FW-Kimi-K2.6": { "cache_read_input_token_cost": 1.76e-07, "input_cost_per_token": 1.045e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/FW-Kimi-K2.7-Code": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 1.05e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/FW-Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/kimi-latest": { "alias_of": "azure_ai/FW-Kimi-K3" }, "azure_ai/FW-MiniMax-M2.5": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 3.3e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-MiniMax-M3": { "cache_read_input_token_cost": 6.6e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/minimax-latest": { "alias_of": "azure_ai/FW-MiniMax-M3" }, "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 6e-08, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/MAI-Image-2.5": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image": 0.048, "output_cost_per_image_token": 4.7e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "deprecation_date": "2026-10-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/MAI-Image-2.6", "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { "input_cost_per_image_token": 1.75e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "deprecation_date": "2026-10-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/MAI-Image-2.6-Flash", "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Pro": { "deprecation_date": "2026-10-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.1085, "output_cost_per_image_token": 0.000106, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-mai-image-2-5-pro-and-mai-voice-2-flash-in-microsoft-foundry/4539446", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure_ai/MAI-Thinking-1": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { "deprecation_date": "2027-01-31", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Llama-4-Scout-17B-16E-Instruct": { "deprecation_date": "2027-01-31", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/Phi-4": { "deprecation_date": "2027-01-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-4-mini-instruct": { "deprecation_date": "2027-01-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false }, "azure_ai/Phi-4-multimodal-instruct": { "deprecation_date": "2027-01-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "microsoft--phi-4", "input_cost_per_audio_token": 4e-06, "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": false, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { "deprecation_date": "2027-01-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "microsoft--phi-4", "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false }, "azure_ai/Phi-4-reasoning": { "deprecation_date": "2027-01-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "microsoft--phi-4", "input_cost_per_token": 1.25e-07, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true }, "azure_ai/mistral-document-ai-2512": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/mistral-ocr-4-0" }, "azure_ai/mistral-ocr-4-0": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.004, "annotation_cost_per_page": 0.005, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/" }, "azure_ai/Cohere-parse-v5": { "deprecation_date": "2026-12-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "litellm_provider": "azure_ai", "mode": "ocr", "ocr_cost_per_page": 0.0015, "source": "https://cohere.com/blog/parse", "supported_endpoints": [ "/v1/ocr" ] }, "azure_ai/cohere-command-a": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/doc-intelligence/prebuilt-layout": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.01, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/doc-intelligence/prebuilt-document": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.01, "mode": "ocr", "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { "deprecation_date": "2026-02-27", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/cohere-rerank-v4.0-pro": { "deprecation_date": "2027-09-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/cohere-rerank-v5-pro", "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/cohere-rerank-v4.0-fast": { "deprecation_date": "2027-09-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/cohere-rerank-v5-fast", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" }, "azure_ai/deepseek-v3.2": { "deprecation_date": "2027-11-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/deepseek-v4.1-flash", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/deepseek-v3.2-speciale": { "deprecation_date": "2027-11-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/deepseek-v4-pro": { "deprecation_date": "2028-02-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.74e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 1.45e-07, "supports_prompt_caching": true }, "azure_ai/deepseek-pro-latest": { "alias_of": "azure_ai/deepseek-v4-pro" }, "azure_ai/deepseek-v4-flash": { "deprecation_date": "2028-02-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/DeepSeek-V4-Flash-0731", "input_cost_per_token": 1.9e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 2.8e-08, "supports_prompt_caching": true }, "azure_ai/deepseek-flash-latest": { "alias_of": "azure_ai/deepseek-v4-flash" }, "azure_ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 1.4e-08, "deprecation_date": "2026-12-03", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 4.4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { "deprecation_date": "2027-06-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/Cohere-Embed-V5-Fast", "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true, "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { "deprecation_date": "2027-01-31", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/grok-4.3", "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure_ai/grok-4.6": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure_ai/grok-4-20-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_reasoning": true }, "azure_ai/grok-4-20-non-reasoning": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-06", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { "deprecation_date": "2027-05-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-1-fast-reasoning": { "deprecation_date": "2027-05-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "token_count_framing": 149, "token_count_tool_framing": 302, "token_count_responses_framing": 145, "token_count_responses_tool_framing": 100, "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-code-fast-1": { "deprecation_date": "2027-01-31", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_pdf_input": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { "deprecation_date": "2026-01-30", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "input_cost_per_token": 3.2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.71e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_pdf_input": false }, "azure_ai/kimi-k2.5": { "deprecation_date": "2027-01-26", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true }, "azure_ai/kimi-k2.6": { "deprecation_date": "2027-04-16", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1.6e-07, "supports_prompt_caching": true }, "azure_ai/ministral-3b": { "deprecation_date": "2026-12-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "ministral-ministral-4b-instruct", "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-latest": { "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-large-3": { "input_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/mistral-medium-2505": { "deprecation_date": "2026-12-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/mistral-medium-3-5", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "azure_ai/mistral-nemo": { "deprecation_date": "2026-01-30", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "successor_model": "azure_ai/mistral-small-2503", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_pdf_input": false }, "azure_ai/mistral-small-2503": { "deprecation_date": "2027-02-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "mistralai-mistral-small-4-119b-2603", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_vision": true }, "babbage-002": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { "cost_per_second": 0.001902, "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { "cost_per_second": 0.0011416, "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { "cost_per_second": 0.0066027, "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, "bedrock/guardrails": { "guardrail_cost_per_unit": { "automatedReasoningPolicyUnits": 0.00017, "contentPolicyImageUnits": 0.00075, "contentPolicyUnits": 0.00015, "contextualGroundingPolicyUnits": 0.0001, "sensitiveInformationPolicyFreeUnits": 0.0, "sensitiveInformationPolicyUnits": 0.0001, "topicPolicyUnits": 0.00015, "wordPolicyUnits": 0.0 }, "litellm_provider": "bedrock", "mode": "guardrail", "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.01475, "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.008194, "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { "input_cost_per_token": 2.23e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-v2:1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/ap-northeast-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, "output_cost_per_token_flex": 1.52e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.1e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.94e-06, "output_cost_per_token_flex": 1.47e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-south-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { "input_cost_per_token": 3.1e-07, "input_cost_per_token_batches": 1.55e-07, "input_cost_per_token_flex": 1.55e-07, "input_cost_per_token_priority": 5.425e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.24e-06, "output_cost_per_token_batches": 6.2e-07, "output_cost_per_token_flex": 6.2e-07, "output_cost_per_token_priority": 2.17e-06 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_flex": 1.11e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", "supports_audio_input": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_flex": 1.8e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.03e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.9e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-north-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.01635, "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.009083, "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { "input_cost_per_token": 2.48e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, "bedrock/eu-central-1/anthropic.claude-v2:1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/eu-central-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.78e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.55e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4.7e-07, "input_cost_per_token_batches": 2.35e-07, "input_cost_per_token_flex": 2.35e-07, "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, "output_cost_per_token_batches": 9.3e-07, "output_cost_per_token_flex": 9.3e-07, "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 4.7e-07, "input_cost_per_token_batches": 2.35e-07, "input_cost_per_token_flex": 2.35e-07, "input_cost_per_token_priority": 8.225e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.86e-06, "output_cost_per_token_batches": 9.3e-07, "output_cost_per_token_flex": 9.3e-07, "output_cost_per_token_priority": 3.255e-06 }, "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 2.3e-07, "input_cost_per_token_batches": 1.15e-07, "input_cost_per_token_flex": 1.15e-07, "input_cost_per_token_priority": 4.025e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.01e-06, "output_cost_per_token_batches": 5.05e-07, "output_cost_per_token_flex": 5.05e-07, "output_cost_per_token_priority": 1.7675e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "input_cost_per_token_batches": 3.9e-07, "input_cost_per_token_flex": 3.9e-07, "input_cost_per_token_priority": 1.365e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, "output_cost_per_token_batches": 9.3e-07, "output_cost_per_token_flex": 9.3e-07, "output_cost_per_token_priority": 3.255e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 5.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-south-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/eu-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.88e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.01e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_batches": 3.7e-07, "input_cost_per_token_flex": 3.7e-07, "input_cost_per_token_priority": 1.295e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_batches": 1.11e-06, "output_cost_per_token_flex": 1.11e-06, "output_cost_per_token_priority": 3.885e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, "input_cost_per_token_batches": 1.8e-07, "input_cost_per_token_flex": 1.8e-07, "input_cost_per_token_priority": 6.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.44e-06, "output_cost_per_token_batches": 7.2e-07, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.52e-06 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 7.3e-07, "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, "output_cost_per_token_flex": 1.52e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/sa-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "input_cost_per_token_flex": 3.6e-07, "input_cost_per_token_priority": 1.26e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, "output_cost_per_token_batches": 1.8e-06, "output_cost_per_token_flex": 1.8e-06, "output_cost_per_token_priority": 6.3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-v2:1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-1/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token_batches": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-east-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { "input_cost_per_token": 3e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { "input_cost_per_token": 1.3e-06, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.7e-06 }, "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "deprecation_date": "2027-04-27", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "deprecation_date": "2027-04-27", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true }, "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true }, "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.62e-07, "input_cost_per_image": 7.2e-05, "input_cost_per_video_per_second": 0.00084, "input_cost_per_audio_per_second": 0.000168, "input_cost_per_token_batches": 8.1e-08, "output_cost_per_token": 0.0, "output_vector_size": 3072, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, "supports_audio_input": true }, "bedrock/us-gov-west-1/amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.8e-08, "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.88e-07, "output_cost_per_token_batches": 1.44e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 1.05e-08, "input_cost_per_token": 4.2e-08, "input_cost_per_token_batches": 2.1e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.68e-07, "output_cost_per_token_batches": 8.4e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, "cache_read_input_token_cost_flex": 1.2e-07, "cache_read_input_token_cost_priority": 4.2e-07, "input_cost_per_token": 9.6e-07, "input_cost_per_token_batches": 4.8e-07, "input_cost_per_token_flex": 4.8e-07, "input_cost_per_token_priority": 1.68e-06, "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "output_cost_per_token_batches": 1.92e-06, "output_cost_per_token_flex": 1.92e-06, "output_cost_per_token_priority": 6.72e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.6e-06 }, "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "deprecation_date": "2027-04-27", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "deprecation_date": "2027-04-27", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-05-09", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "supports_pdf_input": true }, "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-05-09", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-v1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-v2:1": { "input_cost_per_token": 8e-06, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md" }, "bedrock/us-west-2/minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token_batches": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "input_cost_per_token": 6e-07, "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-west-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 2048 }, "black_forest_labs/flux-kontext-pro": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.04, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ] }, "black_forest_labs/flux-kontext-max": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.08, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ] }, "black_forest_labs/flux-pro-1.0-fill": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits" ] }, "black_forest_labs/flux-pro-1.0-expand": { "litellm_provider": "black_forest_labs", "mode": "image_edit", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/edits" ] }, "black_forest_labs/flux-pro-1.1": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "black_forest_labs/flux-pro-1.1-ultra": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "black_forest_labs/flux-dev": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "black_forest_labs/flux-pro": { "litellm_provider": "black_forest_labs", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://bfl.ai/pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "cerebras/llama-3.1-70b": { "input_cost_per_token": 6e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama-3.1-8b": { "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama-3.3-70b": { "deprecation_date": "2026-02-16", "input_cost_per_token": 8.5e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-8b": { "deprecation_date": "2026-05-27", "input_cost_per_token": 1e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/gpt-oss-120b": { "input_cost_per_token": 3.5e-07, "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "cerebras/qwen-3-32b": { "deprecation_date": "2026-02-16", "input_cost_per_token": 4e-07, "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "cerebras/qwen-3.8-27b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "chatdolphin": { "input_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07 }, "gpt-4o-transcribe-diarize": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { "supports_web_search": true, "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 4096 }, "claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_batches": 1.5e-07, "deprecation_date": "2026-11-30", "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_batches": 1.5e-07, "deprecation_date": "2026-11-30", "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "successor_model": "claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-5-5": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_web_search": true }, "claude-sonnet-latest": { "alias_of": "claude-sonnet-5-5" }, "claude-sonnet-4-6": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "provider_specific_entry": { "us": 1.1 }, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": {"model":"anthropic.claude-sonnet-4-5-20250929-v1:0","litellm_provider":"bedrock"} }, "claude-opus-4-5-20251101": { "supports_web_search": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096 }, "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_speed": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6-20260205": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "provider_specific_entry": { "us": 1.1 }, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 2048, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-7-20260416": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-latest": { "alias_of": "claude-fable-5-2" }, "claude-opus-5-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": {"us":1.1,"fast":2}, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-latest": { "alias_of": "claude-opus-5-5" }, "claude-opus-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1, "fast": 2.0 }, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-8": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1, "fast": 2.0 }, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "cloudflare/clef-omni": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 64000, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", "supports_audio_input": true, "supports_video_input": true, "supports_vision": true }, "cloudflare/@cf/cloudflare/clef-omni": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 64000, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", "supports_audio_input": true, "supports_video_input": true, "supports_vision": true }, "cloudflare/clef": { "input_cost_per_token": 2.4e-07, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", "supports_vision": true }, "cloudflare/clef-flash": { "input_cost_per_token": 9e-08, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", "supports_vision": true }, "cloudflare/@cf/cloudflare/clef": { "input_cost_per_token": 2.4e-07, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", "supports_vision": true }, "cloudflare/@cf/cloudflare/clef-flash": { "input_cost_per_token": 9e-08, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", "supports_vision": true }, "cloudflare/clairic": { "input_cost_per_token": 1e-07, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "extraction", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", "supports_vision": true }, "cloudflare/@cf/cloudflare/clairic": { "input_cost_per_token": 1e-07, "litellm_provider": "cloudflare", "max_input_tokens": 65536, "mode": "extraction", "output_cost_per_token": 0.0, "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", "supports_vision": true }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 }, "cloudflare/@cf/meta/llama-2-7b-chat-int8": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 }, "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 }, "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 }, "cloudflare/@cf/openai/gpt-oss-120b": { "input_cost_per_token": 3.5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/google/gemma-2b-it-lora": { "input_cost_per_token": 0.0, "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 }, "cloudflare/@cf/meta/llama-3.2-3b-instruct": { "input_cost_per_token": 5.09e-08, "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300 }, "cloudflare/@cf/meta/llama-guard-3-8b": { "input_cost_per_token": 4.84e-07, "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "rpm": 300 }, "cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": { "input_cost_per_token": 0.0, "litellm_provider": "cloudflare", "max_input_tokens": 15000, "max_output_tokens": 15000, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 }, "cloudflare/@cf/moonshotai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b": { "input_cost_per_token": 4.97e-07, "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, "rpm": 300, "supports_reasoning": true }, "cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": { "input_cost_per_token": 1.52e-07, "litellm_provider": "cloudflare", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.87e-07, "rpm": 300 }, "cloudflare/@cf/meta/llama-3.2-1b-instruct": { "input_cost_per_token": 2.7e-08, "litellm_provider": "cloudflare", "max_input_tokens": 60000, "max_output_tokens": 60000, "mode": "chat", "output_cost_per_token": 2.01e-07, "rpm": 300 }, "cloudflare/@cf/moonshotai/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/zai-org/glm-4.7-flash": { "input_cost_per_token": 6.05e-08, "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora": { "input_cost_per_token": 0.0, "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 }, "cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": { "input_cost_per_token": 2.93e-07, "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/ibm-granite/granite-4.0-h-micro": { "input_cost_per_token": 1.7e-08, "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": { "input_cost_per_token": 6.6e-07, "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300 }, "cloudflare/@cf/zai-org/glm-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/nvidia/nemotron-3-120b-a12b": { "input_cost_per_token": 5e-07, "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "input_cost_per_token": 3.51e-07, "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300 }, "cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": { "input_cost_per_token": 5.09e-08, "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/google/gemma-7b-it-lora": { "input_cost_per_token": 0.0, "litellm_provider": "cloudflare", "max_input_tokens": 3500, "max_output_tokens": 3500, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 }, "cloudflare/@cf/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1e-07, "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct": { "input_cost_per_token": 3.51e-07, "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": { "input_cost_per_token": 4.85e-08, "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, "rpm": 300, "supports_vision": true }, "cloudflare/@cf/openai/gpt-oss-20b": { "input_cost_per_token": 2e-07, "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, "cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 2.7e-07, "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/qwen/qwq-32b": { "input_cost_per_token": 6.6e-07, "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300, "supports_reasoning": true }, "codestral/codestral-2405": { "deprecation_date": "2025-06-16", "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "codestral/codestral-latest": { "input_cost_per_token": 0.0, "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "cohere.command-light-text-v14": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "cohere.command-text-v14": { "input_cost_per_token": 1e-06, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "cohere.embed-english-v3": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, "cohere.embed-multilingual-v3": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, "cohere.embed-v4:0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, "us.cohere.embed-v4:0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "supports_embedding_image_input": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.cohere.embed-v4:0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "supports_embedding_image_input": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "cohere/embed-v4.0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "supports_embedding_image_input": true, "input_cost_per_image_token": 4.7e-07, "source": "https://cohere.com/pricing" }, "cohere/embed-v5.0-pro": { "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048, "supports_embedding_image_input": true, "source": "https://cohere.com/pricing" }, "cohere/embed-v5.0-fast": { "input_cost_per_token": 8e-08, "litellm_provider": "cohere", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048, "supports_embedding_image_input": true, "source": "https://cohere.com/pricing" }, "cohere/parse-v5.0": { "litellm_provider": "cohere", "mode": "ocr", "ocr_cost_per_page": 0.0015, "source": "https://cohere.com/blog/parse", "supported_endpoints": [ "/v1/ocr" ] }, "cohere.rerank-v3-5:0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_tool_choice": true }, "c4ai-aya-expanse-32b": { "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "source": "https://docs.cohere.com/docs/models" }, "command-a-plus-05-2026": { "input_cost_per_token": 0.0, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.cohere.com/docs/command-a-plus", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "command-nightly": { "input_cost_per_token": 1e-06, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06 }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_tool_choice": true }, "command-r7b-12-2024": { "input_cost_per_token": 3.75e-08, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.cohere.com/v2/docs/command-r7b", "supports_function_calling": true, "supports_tool_choice": true }, "coralbricks/glm-5.3-fast": { "cache_creation_input_token_cost": 1.68e-06, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "coralbricks/glm-5.3-fp4": { "cache_creation_input_token_cost": 1.68e-06, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "coralbricks/glm-5.3": { "cache_creation_input_token_cost": 1.68e-06, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "coralbricks/deepseek-v4.1-flash-fast": { "cache_creation_input_token_cost": 9e-08, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "coralbricks/deepseek-v4.1-flash-fast-fp4": { "cache_creation_input_token_cost": 9e-08, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "coralbricks/deepseek-v4.1-flash": { "cache_creation_input_token_cost": 9e-08, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "computer-use-preview": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, "computer-use-preview-2025-03-11": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://developers.openai.com/api/docs/models/computer-use-preview" }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false }, "dashscope/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/deepseek-v4-pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/glm-5.1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "dashscope", "max_input_tokens": 202745, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/glm-5.2": { "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "dashscope", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 229376, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen-coder": { "input_cost_per_token": 3e-07, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-flash": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen-flash-2025-07-28": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen-max": { "input_cost_per_token": 1.6e-06, "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-plus": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-plus-2025-01-25": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-plus-2025-04-28": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-plus-2025-07-14": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-plus-2025-07-28": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen-plus-2025-09-11": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen-plus-latest": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen-turbo": { "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-turbo-2024-11-01": { "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-turbo-2025-04-28": { "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-turbo-latest": { "input_cost_per_token": 5e-08, "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen3-30b-a3b": { "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen3-coder-flash": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 4e-07, "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3-coder-flash-2025-07-28": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3-coder-plus": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3-coder-plus-2025-07-22": { "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3-max-preview": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "dashscope/qwen3-max": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "dashscope/qwen3-max-2026-01-23": { "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "dashscope/qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true }, "dashscope/qwen3-next-80b-a3b-thinking": { "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen3-vl-235b-a22b-thinking": { "input_cost_per_token": 4e-07, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen3-vl-32b-instruct": { "input_cost_per_token": 1.6e-07, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen3-vl-32b-thinking": { "input_cost_per_token": 1.6e-07, "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen3-vl-plus": { "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.4e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 6e-07, "output_cost_per_token": 4.8e-06, "range": [ 128000.0, 256000.0 ] } ] }, "dashscope/qwen3.5-plus": { "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_token": 2.4e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3.7-max": { "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "dashscope/qwen3.7-plus": { "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 256000.0 ] }, { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.8e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "dashscope/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "dashscope/qwen-max-latest": { "alias_of": "dashscope/qwen3.8-max" }, "dashscope/qwen3.8-flash": { "cache_creation_input_token_cost": 2e-07, "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "dashscope/qwen-flash-latest": { "alias_of": "dashscope/qwen3.8-flash" }, "dashscope/qwen3.8-omni-flash": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "dashscope/qwen-image-2.0": { "litellm_provider": "dashscope", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "dashscope/qwen-image-2.0-pro": { "litellm_provider": "dashscope", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "dashscope/qwen-image-3.0": { "litellm_provider": "dashscope", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "dashscope/qwen-image-3.0-pro": { "litellm_provider": "dashscope", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "dashscope/qwen3-tts-flash": { "input_cost_per_character": 1e-05, "litellm_provider": "dashscope", "mode": "audio_speech", "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "dashscope/qwen-audio-3.1-tts-flash": { "input_cost_per_token": 2.3e-07, "output_cost_per_token": 1.87e-06, "litellm_provider": "dashscope", "mode": "audio_speech", "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "dashscope/qwen-audio-3.1-tts-plus": { "input_cost_per_character": 3e-05, "litellm_provider": "dashscope", "mode": "audio_speech", "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "dashscope/qwen-audio-3.0-tts-plus": { "input_cost_per_character": 2e-05, "litellm_provider": "dashscope", "mode": "audio_speech", "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "dashscope/qwen-audio-3.0-tts-flash": { "input_cost_per_character": 1.5e-05, "litellm_provider": "dashscope", "mode": "audio_speech", "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "dashscope/wan3.0-video": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", "output_cost_per_second": 0.165025, "output_cost_per_second_480p": 0.041256, "output_cost_per_second_720p": 0.082513, "output_cost_per_second_1080p": 0.165025, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/wan3.0-video-prime": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", "output_cost_per_second": 0.254399, "output_cost_per_second_480p": 0.0636, "output_cost_per_second_720p": 0.127199, "output_cost_per_second_1080p": 0.254399, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.1-t2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.1-i2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.1-r2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.0-t2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.0-i2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/happyhorse-1.0-r2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/wan2.7-t2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/wan2.7-i2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "dashscope/wan2.7-r2v": { "litellm_provider": "dashscope", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/deepseek-v4-pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/glm-5.1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "qwencloud", "max_input_tokens": 202745, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/glm-5.2": { "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "qwencloud", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "qwencloud", "max_input_tokens": 229376, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwen-coder": { "input_cost_per_token": 3e-07, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-flash": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen-flash-2025-07-28": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen-max": { "input_cost_per_token": 1.6e-06, "litellm_provider": "qwencloud", "max_input_tokens": 30720, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-plus": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-plus-2025-01-25": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-plus-2025-04-28": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-plus-2025-07-14": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-plus-2025-07-28": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen-plus-2025-09-11": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen-plus-latest": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen-turbo": { "input_cost_per_token": 5e-08, "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-turbo-2024-11-01": { "input_cost_per_token": 5e-08, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-turbo-2025-04-28": { "input_cost_per_token": 5e-08, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-turbo-latest": { "input_cost_per_token": 5e-08, "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen3-30b-a3b": { "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen3-coder-flash": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 4e-07, "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3-coder-flash-2025-07-28": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3-coder-plus": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3-coder-plus-2025-07-22": { "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3-max-preview": { "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwencloud/qwen3-max": { "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwencloud/qwen3-max-2026-01-23": { "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwencloud/qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_tool_choice": true }, "qwencloud/qwen3-next-80b-a3b-thinking": { "input_cost_per_token": 1.5e-07, "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwen3-vl-235b-a22b-thinking": { "input_cost_per_token": 4e-07, "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwen3-vl-32b-instruct": { "input_cost_per_token": 1.6e-07, "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwen3-vl-32b-thinking": { "input_cost_per_token": 1.6e-07, "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwen3-vl-plus": { "litellm_provider": "qwencloud", "max_input_tokens": 260096, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.4e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 6e-07, "output_cost_per_token": 4.8e-06, "range": [ 128000.0, 256000.0 ] } ] }, "qwencloud/qwen3.5-plus": { "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_token": 2.4e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3.7-max": { "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwencloud/qwen3.7-plus": { "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 256000.0 ] }, { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.8e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwencloud/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "qwencloud/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "qwencloud", "max_input_tokens": 98304, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.qwencloud.com/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwencloud/qwen-image-2.0": { "litellm_provider": "qwencloud", "mode": "image_generation", "source": "https://www.qwencloud.com/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwencloud/qwen-image-2.0-pro": { "litellm_provider": "qwencloud", "mode": "image_generation", "source": "https://www.qwencloud.com/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwencloud/qwen-image-3.0": { "litellm_provider": "qwencloud", "mode": "image_generation", "source": "https://www.qwencloud.com/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwencloud/qwen-image-3.0-pro": { "litellm_provider": "qwencloud", "mode": "image_generation", "source": "https://www.qwencloud.com/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwencloud/wan3.0-video": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", "output_cost_per_second": 0.2, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "output_cost_per_second_1080p": 0.2, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/wan3.0-video-prime": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", "output_cost_per_second": 0.28, "output_cost_per_second_480p": 0.068, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.28, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.1-t2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", "output_cost_per_second": 0.18, "output_cost_per_second_480p": 0.07, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.18, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.1-i2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", "output_cost_per_second": 0.18, "output_cost_per_second_480p": 0.07, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.18, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.1-r2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", "output_cost_per_second": 0.18, "output_cost_per_second_480p": 0.07, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.18, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.0-t2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", "output_cost_per_second": 0.24, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.24, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.0-i2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", "output_cost_per_second": 0.24, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.24, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/happyhorse-1.0-r2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", "output_cost_per_second": 0.24, "output_cost_per_second_720p": 0.14, "output_cost_per_second_1080p": 0.24, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/wan2.7-t2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", "output_cost_per_second": 0.15, "output_cost_per_second_720p": 0.1, "output_cost_per_second_1080p": 0.15, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/wan2.7-i2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", "output_cost_per_second": 0.15, "output_cost_per_second_720p": 0.1, "output_cost_per_second_1080p": 0.15, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwencloud/wan2.7-r2v": { "litellm_provider": "qwencloud", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", "output_cost_per_second": 0.15, "output_cost_per_second_720p": 0.1, "output_cost_per_second_1080p": 0.15, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/deepseek-v4-pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/glm-5.1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 202745, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/glm-5.2": { "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 229376, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen-coder": { "input_cost_per_token": 3e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-flash": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen-flash-2025-07-28": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen-max": { "input_cost_per_token": 1.6e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 30720, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-plus": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-plus-2025-01-25": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-plus-2025-04-28": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-plus-2025-07-14": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-plus-2025-07-28": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen-plus-2025-09-11": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen-plus-latest": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 1.2e-05, "output_cost_per_token": 3.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen-turbo": { "input_cost_per_token": 5e-08, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-turbo-2024-11-01": { "input_cost_per_token": 5e-08, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-turbo-2025-04-28": { "input_cost_per_token": 5e-08, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-turbo-latest": { "input_cost_per_token": 5e-08, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen3-30b-a3b": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen3-coder-flash": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 4e-07, "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3-coder-flash-2025-07-28": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3-coder-plus": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3-coder-plus-2025-07-22": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 256000.0 ] }, { "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3-max-preview": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwen_ai_platform/qwen3-max": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwen_ai_platform/qwen3-max-2026-01-23": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "range": [ 128000.0, 252000.0 ] } ] }, "qwen_ai_platform/qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen3-next-80b-a3b-thinking": { "input_cost_per_token": 1.5e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen3-vl-235b-a22b-thinking": { "input_cost_per_token": 4e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen3-vl-32b-instruct": { "input_cost_per_token": 1.6e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen3-vl-32b-thinking": { "input_cost_per_token": 1.6e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen3-vl-plus": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 260096, "max_output_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.4e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 6e-07, "output_cost_per_token": 4.8e-06, "range": [ 128000.0, 256000.0 ] } ] }, "qwen_ai_platform/qwen3.5-plus": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4e-07, "output_cost_per_token": 2.4e-06, "range": [ 0, 256000.0 ] }, { "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3.7-max": { "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen3.7-plus": { "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "range": [ 0, 256000.0 ] }, { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.8e-06, "range": [ 256000.0, 1000000.0 ] } ] }, "qwen_ai_platform/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "qwen_ai_platform/qwen3.8-flash": { "cache_creation_input_token_cost": 2e-07, "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "qwen_ai_platform/qwen3.8-omni-flash": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "qwen_ai_platform/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 98304, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "qwen_ai_platform/qwen-image-2.0": { "litellm_provider": "qwen_ai_platform", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwen_ai_platform/qwen-image-2.0-pro": { "litellm_provider": "qwen_ai_platform", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwen_ai_platform/qwen-image-3.0": { "litellm_provider": "qwen_ai_platform", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwen_ai_platform/qwen-image-3.0-pro": { "litellm_provider": "qwen_ai_platform", "mode": "image_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supported_endpoints": [ "/v1/images/generations" ] }, "qwen_ai_platform/wan3.0-video": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", "output_cost_per_second": 0.165025, "output_cost_per_second_480p": 0.041256, "output_cost_per_second_720p": 0.082513, "output_cost_per_second_1080p": 0.165025, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/wan3.0-video-prime": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", "output_cost_per_second": 0.254399, "output_cost_per_second_480p": 0.0636, "output_cost_per_second_720p": 0.127199, "output_cost_per_second_1080p": 0.254399, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.1-t2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.1-i2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.1-r2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", "output_cost_per_second": 0.165026, "output_cost_per_second_480p": 0.0618845, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.165026, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.0-t2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.0-i2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/happyhorse-1.0-r2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", "output_cost_per_second": 0.220034, "output_cost_per_second_720p": 0.123769, "output_cost_per_second_1080p": 0.220034, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/wan2.7-t2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/wan2.7-i2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "first_frame" }, "metadata": { "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "qwen_ai_platform/wan2.7-r2v": { "litellm_provider": "qwen_ai_platform", "mode": "video_generation", "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", "output_cost_per_second": 0.143353, "output_cost_per_second_720p": 0.086012, "output_cost_per_second_1080p": 0.143353, "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "provider_specific_entry": { "dashscope_video_reference_input": "reference_image" }, "metadata": { "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." } }, "databricks/databricks-bge-large-en": { "cache_creation_input_token_cost": 1.0003e-07, "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.0003e-07, "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "embedding", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-claude-fable-5": { "cache_creation_input_token_cost": 1.249997e-05, "cache_creation_input_token_cost_above_1hr": 1.999998e-05, "cache_read_input_token_cost": 1.00002e-06, "input_cost_per_token": 9.99999e-06, "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": false, "thinking_always_on": true }, "databricks/databricks-claude-fable-5-1": { "cache_creation_input_token_cost": 1.249997e-05, "cache_creation_input_token_cost_above_1hr": 1.999998e-05, "cache_read_input_token_cost": 2.4997e-07, "input_cost_per_token": 9.99999e-06, "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, "output_dbu_cost_per_token": 0.00071429, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true }, "databricks/claude-fable-latest": { "alias_of": "databricks/databricks-claude-fable-5-2" }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_creation_input_token_cost_above_1hr": 1.99997e-06, "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 5.00003e-06, "output_dbu_cost_per_token": 7.1429e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096 }, "databricks/databricks-claude-opus-4": { "cache_creation_input_token_cost": 1.874999e-05, "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, "input_cost_per_token": 1.500002e-05, "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 7.50001e-05, "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-opus-4-1": { "cache_creation_input_token_cost": 1.874999e-05, "cache_creation_input_token_cost_above_1hr": 2.999997e-05, "cache_read_input_token_cost": 1.50003e-06, "input_cost_per_token": 1.500002e-05, "input_dbu_cost_per_token": 0.00021429, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 7.50001e-05, "output_dbu_cost_per_token": 0.0010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-opus-4-5": { "cache_creation_input_token_cost": 6.25002e-06, "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096 }, "databricks/databricks-claude-opus-4-6": { "cache_creation_input_token_cost": 6.25002e-06, "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, "output_dbu_cost_per_token": 0.00035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096 }, "databricks/databricks-claude-opus-4-7": { "cache_creation_input_token_cost": 6.25002e-06, "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 2048, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-claude-opus-4-8": { "cache_creation_input_token_cost": 6.25002e-06, "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-claude-opus-5": { "cache_creation_input_token_cost": 6.25002e-06, "cache_creation_input_token_cost_above_1hr": 9.99999e-06, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.500001e-05, "output_dbu_cost_per_token": 0.00035714, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-claude-opus-5-5": { "cache_creation_input_token_cost": 5.00003e-06, "cache_creation_input_token_cost_above_1hr": 8.00002e-06, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_token": 4.00001e-06, "input_dbu_cost_per_token": 5.7143e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.999998e-05, "output_dbu_cost_per_token": 0.000285714, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_output_config": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "databricks/claude-opus-latest": { "alias_of": "databricks/databricks-claude-opus-5-5" }, "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "deprecation_date": "2026-10-09", "successor_model": "databricks/databricks-claude-sonnet-5", "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.74997e-06, "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.74997e-06, "cache_creation_input_token_cost_above_1hr": 5.99998e-06, "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.00021429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-sonnet-5": { "cache_creation_input_token_cost": 2.49998e-06, "cache_creation_input_token_cost_above_1hr": 4.00001e-06, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_token": 1.99997e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.00014286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-deepseek-v4-flash-0731": { "cache_creation_input_token_cost": 1.4e-07, "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-11-05", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 2.8e-07, "output_dbu_cost_per_token": 4e-06, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "databricks/system.ai.deepseek-v4-flash-0731": { "deprecation_date": "2026-11-05", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", "litellm_provider": "databricks", "mode": "chat", "source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "token_count_framing": 97 }, "databricks/databricks-deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 1.31999e-06, "cache_read_input_token_cost": 1.3202e-07, "deprecation_date": "2026-10-30", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.31999e-06, "input_dbu_cost_per_token": 1.8857e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "mode": "chat", "output_cost_per_token": 3.95997e-06, "output_dbu_cost_per_token": 5.6571e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "databricks/databricks-gemini-2-5-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, "deprecation_date": "2026-10-02", "successor_model": "databricks/databricks-gemini-3-5-flash", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 2.49998e-06, "output_dbu_cost_per_token": 3.5714e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_anthropic_thinking_payload": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_vision": true, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-2-5-pro": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.24999e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_anthropic_thinking_payload": true, "supports_prompt_caching": true, "supports_tool_choice": true, "deprecation_date": "2026-10-02", "supports_reasoning": true, "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_vision": true, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-3-1-flash-lite": { "cache_creation_input_token_cost": 3.1248e-07, "cache_read_input_audio_token_cost": 6.251e-08, "cache_read_input_token_cost": 3.122e-08, "input_cost_per_audio_token": 6.2503e-07, "input_cost_per_image_token": 3.1248e-07, "input_cost_per_token": 3.1248e-07, "input_dbu_cost_per_token": 4.464e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.87502e-06, "output_dbu_cost_per_token": 2.6786e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_vision": true, "supports_audio_input": true, "supports_video_input": true, "input_cost_per_token_priority": 5.6252e-07, "output_cost_per_token_priority": 3.37498e-06, "cache_read_input_token_cost_priority": 5.628e-08, "cache_creation_input_token_cost_priority": 5.6252e-07, "input_cost_per_audio_token_priority": 1.12497e-06, "cache_read_input_audio_token_cost_priority": 1.1249e-07 }, "databricks/databricks-gemini-3-1-flash-image": { "cache_creation_input_token_cost": 6.2503e-07, "cache_read_input_token_cost": 6.2503e-07, "input_cost_per_image_token": 6.2503e-07, "input_cost_per_token": 6.2503e-07, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 32768, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_image_token": 7.50001e-05, "output_cost_per_token": 3.74997e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_vision": true }, "databricks/databricks-gemini-3-pro-image": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.49998e-06, "input_cost_per_image_token": 2.49998e-06, "input_cost_per_token": 2.49998e-06, "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 32768, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_image_token": 0.0001500002, "output_cost_per_token": 1.500002e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_vision": true }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, "cache_read_input_token_cost_above_200k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, "input_cost_per_token_above_200k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_200k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "input_cost_per_token_priority": 4.50002e-06, "output_cost_per_token_priority": 2.699998e-05, "cache_read_input_token_cost_priority": 4.5003e-07, "cache_creation_input_token_cost_priority": 4.50002e-06, "input_cost_per_token_above_200k_tokens_priority": 8.99997e-06, "output_cost_per_token_above_200k_tokens_priority": 4.049997e-05, "cache_read_input_token_cost_above_200k_tokens_priority": 8.9999e-07 }, "databricks/databricks-gemini-3-flash": { "cache_creation_input_token_cost": 6.2503e-07, "cache_read_input_audio_token_cost": 1.2502e-07, "cache_read_input_token_cost": 6.251e-08, "input_cost_per_audio_token": 1.24999e-06, "input_cost_per_image_token": 6.2503e-07, "input_cost_per_token": 6.2503e-07, "input_dbu_cost_per_token": 8.929e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 3.74997e-06, "output_dbu_cost_per_token": 5.3571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_vision": true, "supports_audio_input": true, "supports_video_input": true, "input_cost_per_token_priority": 1.12497e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.1249e-07, "cache_creation_input_token_cost_priority": 1.12497e-06, "input_cost_per_audio_token_priority": 2.25001e-06, "cache_read_input_audio_token_cost_priority": 2.2498e-07 }, "databricks/databricks-gemini-3-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "databricks/databricks-gemini-3-8-flash": { "cache_creation_input_token_cost": 7.4998e-07, "cache_read_input_token_cost": 7.497e-08, "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.74997e-06, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, "cache_creation_input_token_cost_priority": 1.35002e-06, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-3-7-flash": { "cache_creation_input_token_cost": 7.4998e-07, "cache_read_input_token_cost": 7.497e-08, "input_cost_per_token": 7.4998e-07, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.74997e-06, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, "cache_creation_input_token_cost_priority": 1.35002e-06, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-3-6-flash": { "cache_creation_input_token_cost": 7.4998e-07, "cache_read_input_token_cost": 7.497e-08, "input_cost_per_token": 7.4998e-07, "input_dbu_cost_per_token": 1.0714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.74997e-06, "output_dbu_cost_per_token": 5.3571e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, "cache_creation_input_token_cost_priority": 1.35002e-06, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 1.87502e-06, "cache_read_input_token_cost": 1.8753e-07, "input_cost_per_token": 1.87502e-06, "input_dbu_cost_per_token": 2.6786e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.124998e-05, "output_dbu_cost_per_token": 0.000160714, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 3.37498e-06, "output_cost_per_token_priority": 2.025002e-05, "cache_read_input_token_cost_priority": 3.3747e-07, "cache_creation_input_token_cost_priority": 3.37498e-06, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash-lite": { "cache_creation_input_token_cost": 3.7499e-07, "cache_read_input_token_cost": 3.752e-08, "input_cost_per_token": 3.7499e-07, "input_dbu_cost_per_token": 5.357e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 3.12501e-06, "output_dbu_cost_per_token": 4.4643e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 6.7501e-07, "output_cost_per_token_priority": 5.62499e-06, "cache_read_input_token_cost_priority": 6.748e-08, "cache_creation_input_token_cost_priority": 6.7501e-07, "supports_audio_input": true, "supports_video_input": true }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 5.0001e-07, "output_dbu_cost_per_token": 7.143e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-glm-5-2": { "cache_creation_input_token_cost": 1.4e-06, "cache_read_input_token_cost": 2.5998e-07, "input_cost_per_token": 1.4e-06, "input_dbu_cost_per_token": 2e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, "mode": "chat", "output_cost_per_token": 4.39999e-06, "output_dbu_cost_per_token": 6.2857e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "input_cost_per_token_priority": 2.45e-06, "output_cost_per_token_priority": 7.7e-06, "cache_read_input_token_cost_priority": 4.55e-07, "cache_creation_input_token_cost_priority": 2.45e-06, "deprecation_date": "2027-02-04", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "successor_model": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3": { "cache_creation_input_token_cost": 1.4e-06, "cache_read_input_token_cost": 2.5998e-07, "input_cost_per_token": 1.4e-06, "input_dbu_cost_per_token": 2e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 4.39999e-06, "output_dbu_cost_per_token": 6.2857e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "thinking_always_on": true, "input_cost_per_token_priority": 2.45e-06, "output_cost_per_token_priority": 7.7e-06, "cache_read_input_token_cost_priority": 4.55e-07, "cache_creation_input_token_cost_priority": 2.45e-06 }, "databricks/glm-latest": { "alias_of": "databricks/databricks-glm-5-3" }, "databricks/databricks-glm-5-3-flash": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 3.003e-08, "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.0001e-07, "output_dbu_cost_per_token": 7.143e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true, "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token_priority": 8.75e-07, "cache_read_input_token_cost_priority": 5.25e-08, "cache_creation_input_token_cost_priority": 2.625e-07 }, "databricks/glm-flash-latest": { "alias_of": "databricks/databricks-glm-5-3-flash" }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.2502e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_priority": 2.49998e-06, "output_cost_per_token_priority": 1.999998e-05, "cache_read_input_token_cost_priority": 2.4997e-07, "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.2502e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_priority": 2.49998e-06, "output_cost_per_token_priority": 1.999998e-05, "cache_read_input_token_cost_priority": 2.4997e-07, "cache_creation_input_token_cost_priority": 2.49998e-06 }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "input_dbu_cost_per_token": 2.5e-05, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_priority": 3.5e-06, "output_cost_per_token_priority": 2.8e-05, "cache_read_input_token_cost_priority": 3.5e-07, "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-3-codex": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "input_dbu_cost_per_token": 2.5e-05, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_priority": 3.5e-06, "output_cost_per_token_priority": 2.8e-05, "cache_read_input_token_cost_priority": 3.5e-07, "cache_creation_input_token_cost_priority": 3.5e-06 }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, "cache_read_input_token_cost_above_272k_tokens": 5.0001e-07, "input_cost_per_token": 2.49998e-06, "input_cost_per_token_above_272k_tokens": 5.00003e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 5.00003e-06, "output_cost_per_token_priority": 2.999997e-05, "cache_read_input_token_cost_priority": 5.0001e-07, "cache_creation_input_token_cost_priority": 5.00003e-06, "input_cost_per_token_above_272k_tokens_priority": 5.00003e-06, "output_cost_per_token_above_272k_tokens_priority": 2.999997e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 5.0001e-07 }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, "cache_read_input_token_cost": 7.497e-08, "input_cost_per_token": 7.4998e-07, "input_dbu_cost_per_token": 1.0714e-05, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 4.50002e-06, "output_dbu_cost_per_token": 6.4286e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.50003e-06, "output_cost_per_token_priority": 8.99997e-06, "cache_read_input_token_cost_priority": 1.5001e-07, "cache_creation_input_token_cost_priority": 1.50003e-06 }, "databricks/gpt-mini-latest": { "alias_of": "databricks/databricks-gpt-5-4-mini" }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, "cache_read_input_token_cost": 2.002e-08, "input_cost_per_token": 1.9999e-07, "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.24999e-06, "output_dbu_cost_per_token": 1.7857e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-gpt-5-6-sol": { "cache_creation_input_token_cost": 5.00003e-06, "cache_creation_input_token_cost_above_272k_tokens": 9.99999e-06, "cache_read_input_token_cost": 3.9998e-07, "cache_read_input_token_cost_above_272k_tokens": 8.0003e-07, "input_cost_per_token": 4.00001e-06, "input_cost_per_token_above_272k_tokens": 8.00002e-06, "input_dbu_cost_per_token": 5.7143e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, "mode": "chat", "output_cost_per_token": 1.999998e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_dbu_cost_per_token": 0.000285714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 8.00002e-06, "output_cost_per_token_priority": 4.000003e-05, "cache_read_input_token_cost_priority": 8.0003e-07, "cache_creation_input_token_cost_priority": 9.99999e-06, "input_cost_per_token_above_272k_tokens_priority": 1.599997e-05, "output_cost_per_token_above_272k_tokens_priority": 6.000001e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 1.59999e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.999998e-05 }, "databricks/databricks-gpt-5-6-terra": { "cache_creation_input_token_cost": 2.49998e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, "cache_read_input_token_cost": 1.9999e-07, "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, "input_cost_per_token": 1.99997e-06, "input_cost_per_token_above_272k_tokens": 4.00001e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.200003e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "output_dbu_cost_per_token": 0.000171429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 4.00001e-06, "output_cost_per_token_priority": 2.399999e-05, "cache_read_input_token_cost_priority": 3.9998e-07, "cache_creation_input_token_cost_priority": 5.00003e-06, "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, "output_cost_per_token_above_272k_tokens_priority": 3.600002e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, "databricks/databricks-gpt-5-6-luna": { "cache_creation_input_token_cost": 2.4997e-07, "cache_creation_input_token_cost_above_272k_tokens": 5.0001e-07, "cache_read_input_token_cost": 2.002e-08, "cache_read_input_token_cost_above_272k_tokens": 3.997e-08, "input_cost_per_token": 1.9999e-07, "input_cost_per_token_above_272k_tokens": 3.9998e-07, "input_dbu_cost_per_token": 2.857e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.20001e-06, "output_cost_per_token_above_272k_tokens": 1.79998e-06, "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 3.9998e-07, "output_cost_per_token_priority": 2.40002e-06, "cache_read_input_token_cost_priority": 3.997e-08, "cache_creation_input_token_cost_priority": 5.0001e-07, "input_cost_per_token_above_272k_tokens_priority": 8.0003e-07, "output_cost_per_token_above_272k_tokens_priority": 3.60003e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 8.001e-08, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.00002e-06 }, "databricks/databricks-gpt-5-5": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 5.0001e-07, "cache_read_input_token_cost_above_272k_tokens": 1.00002e-06, "input_cost_per_token": 5.00003e-06, "input_cost_per_token_above_272k_tokens": 9.99999e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 2.999997e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_dbu_cost_per_token": 0.000428571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.249997e-05, "output_cost_per_token_priority": 7.50001e-05, "cache_read_input_token_cost_priority": 1.24999e-06, "cache_creation_input_token_cost_priority": 1.249997e-05, "input_cost_per_token_above_272k_tokens_priority": 1.249997e-05, "output_cost_per_token_above_272k_tokens_priority": 7.50001e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 1.24999e-06 }, "databricks/databricks-gpt-5-5-pro": { "cache_creation_input_token_cost": 2.999997e-05, "cache_read_input_token_cost": 2.999997e-05, "input_cost_per_token": 2.999997e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_dbu_cost_per_token": 0.00042857, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 0.0001800001, "output_cost_per_token_above_272k_tokens": 0.00027, "output_dbu_cost_per_token": 0.0025714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.99997e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_priority": 4.5003e-07, "output_cost_per_token_priority": 3.60003e-06, "cache_read_input_token_cost_priority": 4.501e-08, "cache_creation_input_token_cost_priority": 4.5003e-07 }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, "cache_read_input_token_cost": 4.97e-09, "input_cost_per_token": 4.998e-08, "input_dbu_cost_per_token": 7.14e-07, "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 3.9998e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 5.9997e-07, "output_dbu_cost_per_token": 8.571e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-gpt-oss-20b": { "cache_creation_input_token_cost": 7e-08, "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 7e-08, "input_dbu_cost_per_token": 1e-06, "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 3.0002e-07, "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-grok-4-6": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 6.2503e-07, "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 500000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 7.50001e-06, "output_dbu_cost_per_token": 0.000107143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, "input_cost_per_token": 1.2999e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "embedding", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-inkling": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.7003e-07, "deprecation_date": "2026-10-30", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 4.04999e-06, "output_dbu_cost_per_token": 5.7857e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "successor_model": "databricks/databricks-glm-5-3", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true }, "databricks/databricks-kimi-k3": { "cache_creation_input_token_cost": 2.99999e-06, "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, "mode": "chat", "output_cost_per_token": 1.500002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 5.25e-06, "output_cost_per_token_priority": 2.625e-05, "cache_read_input_token_cost_priority": 5.25e-07, "cache_creation_input_token_cost_priority": 5.25e-06 }, "databricks/kimi-latest": { "alias_of": "databricks/databricks-kimi-k3" }, "databricks/system.ai.kimi-k3": { "litellm_provider": "databricks", "mode": "chat", "token_count_framing": 100 }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "mode": "chat", "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 4.5003e-07, "output_dbu_cost_per_token": 6.429000000000001e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-meta-llama-3-3-70b-instruct": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "mode": "chat", "output_cost_per_token": 1.50003e-06, "output_dbu_cost_per_token": 2.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, "databricks/databricks-qwen35-122b-a10b": { "cache_creation_input_token_cost": 2.2001e-07, "cache_read_input_token_cost": 2.2001e-07, "input_cost_per_token": 2.2001e-07, "input_dbu_cost_per_token": 3.143e-06, "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 25000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 2.20003e-06, "output_dbu_cost_per_token": 3.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false, "thinking_always_on": true, "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token_priority": 3.85e-06, "cache_read_input_token_cost_priority": 3.85e-07, "cache_creation_input_token_cost_priority": 3.85e-07 }, "databricks/databricks-qwen3-next-80b-a3b-instruct": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5001e-07, "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.20001e-06, "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false }, "databricks/databricks-qwen3-embedding-0-6b": { "cache_creation_input_token_cost": 2.002e-08, "cache_read_input_token_cost": 2.002e-08, "input_cost_per_token": 2.002e-08, "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", "max_input_tokens": 32768, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "embedding", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-openjev-qwen35-4b": { "cache_creation_input_token_cost": 4.2e-08, "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 4.2e-08, "input_dbu_cost_per_token": 6e-07, "litellm_provider": "databricks", "metadata": { "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate." }, "mode": "evaluation", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models" }, "databricks/databricks-typesafeai-jev-1-14-0": { "cache_creation_input_token_cost": 4.2e-08, "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 4.2e-08, "input_dbu_cost_per_token": 6e-07, "litellm_provider": "databricks", "metadata": { "notes": "TypeSafe AI Jev 1.14.0, provider-hosted by TypeSafe AI and served through Unity Gateway, queried through the System One API. The proprietary pricing page lists 'Jev 1.14' at 0.600 DBU per 1M input tokens; input_cost_per_token is that times $0.070 per DBU. Output is free. No cache rates are published, so cache tokens bill at the input rate." }, "mode": "evaluation", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supports_vision": true }, "databricks/ai_decide": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "databricks", "metadata": { "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it." }, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide" }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", "mode": "search" }, "davinci-002": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "source": "https://developers.openai.com/api/docs/pricing" }, "deepgram/aura": { "input_cost_per_character": 1.5e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0150/1000 characters = $0.000015 per character", "note": "Aura-1 text-to-speech voices (aura--), pay as you go" }, "source": "https://deepgram.com/pricing" }, "deepgram/aura-2": { "input_cost_per_character": 3e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.030/1000 characters = $0.00003 per character", "note": "Aura-2 text-to-speech voices (aura-2--), pay as you go" }, "source": "https://deepgram.com/pricing" }, "deepgram/base": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-conversationalai": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-finance": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-general": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-meeting": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-phonecall": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-video": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/base-voicemail": { "input_cost_per_second": 0.00020833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0125/60 seconds = $0.00020833 per second", "original_pricing_per_minute": 0.0125 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/enhanced": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/enhanced-finance": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/enhanced-general": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/enhanced-meeting": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/enhanced-phonecall": { "input_cost_per_second": 0.00024167, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0145/60 seconds = $0.00024167 per second", "original_pricing_per_minute": 0.0145 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-atc": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-automotive": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-conversationalai": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-drivethru": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-finance": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-general": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-meeting": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-phonecall": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-video": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-2-voicemail": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-3": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-3-general": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-3-medical": { "input_cost_per_second": 8.667e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", "original_pricing_per_minute": 0.0052 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-general": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/nova-phonecall": { "input_cost_per_second": 7.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0043/60 seconds = $0.00007167 per second", "original_pricing_per_minute": 0.0043 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/streaming/nova-3": { "input_cost_per_second": 0.00012833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0077/60 seconds = $0.00012833 per second", "note": "Nova-3 monolingual streaming, pay as you go", "original_pricing_per_minute": 0.0077 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/nova-3-medical": { "input_cost_per_second": 0.00012833, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0077/60 seconds = $0.00012833 per second", "note": "Nova-3 Medical streaming, launch price from Deepgram's 2025-03-03 announcement. deepgram.com/pricing does not list Nova-3 Medical, and this matches its current Nova-3 monolingual streaming pay as you go rate", "original_pricing_per_minute": 0.0077 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://www.businesswire.com/news/home/20250303470439/en", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/nova-3-multilingual": { "input_cost_per_second": 0.00015333, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0092/60 seconds = $0.00015333 per second", "note": "Nova-3 multilingual (language=multi) streaming, pay as you go", "original_pricing_per_minute": 0.0092 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/redact": { "input_cost_per_second": 3.333e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0020/60 seconds = $0.00003333 per second", "note": "Redaction add-on (redact query param), streaming, pay as you go", "original_pricing_per_minute": 0.002 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/keyterm": { "input_cost_per_second": 2.167e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0013/60 seconds = $0.00002167 per second", "note": "Keyterm Prompting add-on (keyterm query param), streaming, pay as you go", "original_pricing_per_minute": 0.0013 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/detect_entities": { "input_cost_per_second": 2.833e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0017/60 seconds = $0.00002833 per second", "note": "Entity Detection add-on (detect_entities query param), streaming, pay as you go", "original_pricing_per_minute": 0.0017 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/streaming/diarize": { "input_cost_per_second": 3.333e-05, "litellm_provider": "deepgram", "metadata": { "calculation": "$0.0020/60 seconds = $0.00003333 per second", "note": "Speaker Diarization add-on (diarize / diarize_model query params), streaming, pay as you go", "original_pricing_per_minute": 0.002 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/listen" ] }, "deepgram/whisper": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/whisper-base": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/whisper-large": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/whisper-medium": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/whisper-small": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepgram/whisper-tiny": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", "metadata": { "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://deepgram.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7e-07, "output_cost_per_token": 7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3.6e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_vision": true, "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-07, "output_cost_per_token": 5.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 5.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, "output_cost_per_token": 2.9e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-08, "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1.4e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, "output_cost_per_token": 5e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8.5e-07, "output_cost_per_token": 8.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 7.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, "output_cost_per_token": 1.65e-05, "cache_read_input_token_cost": 3.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 1.65e-05, "output_cost_per_token": 8.25e-05, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, "output_cost_per_token": 1.65e-05, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-07, "output_cost_per_token": 2.4e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, "cache_read_input_token_cost": 3.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.4e-07, "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "cache_read_input_token_cost": 1.35e-07, "supports_prompt_caching": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.5e-07, "cache_read_input_token_cost": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_reasoning": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1e-06, "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-07, "output_cost_per_token": 2.5e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "supports_image_size": false, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-08, "output_cost_per_token": 4.9e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 2e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-08, "output_cost_per_token": 5.5e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-07, "output_cost_per_token": 1.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, "output_cost_per_token": 6e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 5e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.9e-08, "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, "output_cost_per_token": 8e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-08, "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { "max_input_tokens": 262144, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "source": "https://deepinfra.com/pricing", "supports_tool_choice": true, "supports_function_calling": true, "supports_reasoning": true, "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.7e-08, "output_cost_per_token": 1.7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "deepseek/deepseek-coder": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 1.4e-07, "input_cost_per_token_cache_hit": 1.4e-08, "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "deepseek/deepseek-r1": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 5.5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-07-24", "deprecation_source": "https://api-docs.deepseek.com/updates", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false }, "deepseek/deepseek-v3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.7e-07, "input_cost_per_token_cache_hit": 7e-08, "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true }, "deepseek/deepseek-v3.2": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "deepseek.v3-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true }, "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 156000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.md", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "dolphin": { "input_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-07 }, "deepseek-v3-2-251201": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "glm-4-7-251222": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "kimi-k2-thinking-251104": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "doubao-embedding": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 }, "doubao-embedding-large": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 }, "doubao-embedding-large-text-240915": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 4096 }, "doubao-embedding-large-text-250515": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 }, "doubao-embedding-text-240715": { "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 }, "exa_ai/search": { "litellm_provider": "exa_ai", "mode": "search", "tiered_pricing": [ { "input_cost_per_query": 0.005, "max_results_range": [ 0, 25 ] }, { "input_cost_per_query": 0.025, "max_results_range": [ 26, 100 ] } ] }, "firecrawl/search": { "litellm_provider": "firecrawl", "mode": "search", "tiered_pricing": [ { "input_cost_per_query": 0.00166, "max_results_range": [ 1, 10 ] }, { "input_cost_per_query": 0.00332, "max_results_range": [ 11, 20 ] }, { "input_cost_per_query": 0.00498, "max_results_range": [ 21, 30 ] }, { "input_cost_per_query": 0.00664, "max_results_range": [ 31, 40 ] }, { "input_cost_per_query": 0.0083, "max_results_range": [ 41, 50 ] }, { "input_cost_per_query": 0.00996, "max_results_range": [ 51, 60 ] }, { "input_cost_per_query": 0.01162, "max_results_range": [ 61, 70 ] }, { "input_cost_per_query": 0.01328, "max_results_range": [ 71, 80 ] }, { "input_cost_per_query": 0.01494, "max_results_range": [ 81, 90 ] }, { "input_cost_per_query": 0.0166, "max_results_range": [ 91, 100 ] } ], "metadata": { "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" } }, "webiq/search": { "input_cost_per_query": 0.007, "litellm_provider": "webiq", "mode": "search" }, "perplexity/search": { "input_cost_per_query": 0.005, "litellm_provider": "perplexity", "mode": "search" }, "sail/moonshotai/Kimi-K3": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.25e-05, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token_balanced": 2e-06, "output_cost_per_token_balanced": 1e-05, "cache_read_input_token_cost_balanced": 2e-07, "input_cost_per_token_flex": 1.25e-06, "output_cost_per_token_flex": 6.25e-06, "cache_read_input_token_cost_flex": 1.5e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.8e-07, "output_cost_per_token": 3.08e-06, "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token_balanced": 5e-07, "output_cost_per_token_balanced": 2.5e-06, "cache_read_input_token_cost_balanced": 1.2e-07, "input_cost_per_token_flex": 4e-07, "output_cost_per_token_flex": 1.8e-06, "cache_read_input_token_cost_flex": 8e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/zai-org/GLM-5.3-Flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.1e-07, "output_cost_per_token": 3.5e-07, "cache_read_input_token_cost": 2e-08, "input_cost_per_token_balanced": 8e-08, "output_cost_per_token_balanced": 2.8e-07, "cache_read_input_token_cost_balanced": 2e-08, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_flex": 1.8e-07, "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9.2e-07, "output_cost_per_token": 2.77e-06, "cache_read_input_token_cost": 4e-08, "input_cost_per_token_balanced": 7.4e-07, "output_cost_per_token_balanced": 2.22e-06, "cache_read_input_token_cost_balanced": 3e-08, "input_cost_per_token_flex": 4.6e-07, "output_cost_per_token_flex": 1.39e-06, "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 2e-08, "input_cost_per_token_balanced": 7e-08, "output_cost_per_token_balanced": 1.4e-07, "cache_read_input_token_cost_balanced": 2e-08, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_flex": 9e-08, "cache_read_input_token_cost_flex": 1e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/deepseek-ai/DeepSeek-V4.1-Flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 3e-07, "cache_read_input_token_cost": 6e-09, "input_cost_per_token_balanced": 7e-08, "output_cost_per_token_balanced": 2.2e-07, "cache_read_input_token_cost_balanced": 5e-09, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_flex": 1.5e-07, "cache_read_input_token_cost_flex": 4e-09, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/moonshotai/Kimi-K2.6": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-06, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_balanced": 4.5e-07, "output_cost_per_token_balanced": 3e-06, "cache_read_input_token_cost_balanced": 2e-07, "input_cost_per_token_flex": 3.5e-07, "output_cost_per_token_flex": 2e-06, "cache_read_input_token_cost_flex": 1e-07, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-31B-it": { "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 4e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_balanced": 1.2e-07, "output_cost_per_token_balanced": 6e-07, "cache_read_input_token_cost_balanced": 8e-08, "input_cost_per_token_flex": 6e-08, "output_cost_per_token_flex": 3e-07, "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://docs.sailresearch.com/models" }, "sail/nvidia/Gemma-4-31B-IT-NVFP4": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 7e-08, "input_cost_per_token_balanced": 1.1e-07, "output_cost_per_token_balanced": 3.2e-07, "cache_read_input_token_cost_balanced": 6e-08, "input_cost_per_token_flex": 7e-08, "output_cost_per_token_flex": 2e-07, "cache_read_input_token_cost_flex": 4e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://docs.sailresearch.com/models" }, "sail/google/gemma-4-12B-it": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token_balanced": 1e-07, "output_cost_per_token_balanced": 2e-06, "cache_read_input_token_cost_balanced": 7e-08, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_flex": 1e-06, "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/openai/gpt-oss-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 3e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "source": "https://docs.sailresearch.com/models" }, "sail/Qwen/Qwen3.6-35B-A3B": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 2e-08, "input_cost_per_token_flex": 5e-08, "output_cost_per_token_flex": 4e-07, "cache_read_input_token_cost_flex": 2e-08, "litellm_provider": "sail", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://docs.sailresearch.com/models" }, "searxng/search": { "litellm_provider": "searxng", "mode": "search", "input_cost_per_query": 0.0, "metadata": { "notes": "SearXNG is an open-source metasearch engine. Free to use when self-hosted or using public instances." } }, "serper/search": { "input_cost_per_query": 0.001, "litellm_provider": "serper", "mode": "search", "metadata": { "notes": "Serper Google Search API. Pricing: $1.00/1k queries (Starter), $0.75/1k (Standard), $0.50/1k (Scale), $0.30/1k (Ultimate)." } }, "apiserpent/search": { "input_cost_per_query": 0.0006, "litellm_provider": "apiserpent", "mode": "search", "metadata": { "notes": "APISerpent quick search (/api/search/quick), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } }, "apiserpent/deep_search": { "input_cost_per_query": 0.0006, "litellm_provider": "apiserpent", "mode": "search", "metadata": { "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } }, "agentcore/search": { "input_cost_per_query": 0.007, "litellm_provider": "agentcore", "mode": "search", "metadata": { "notes": "Web Search on Amazon Bedrock AgentCore, billed by AWS on the gateway" } }, "bing_grounding/search": { "input_cost_per_query": 0.014, "litellm_provider": "bing_grounding", "mode": "search", "metadata": { "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, "deepseek/search": { "input_cost_per_query": 0.00075, "litellm_provider": "deepseek", "mode": "search" }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", "mode": "search", "metadata": { "notes": "TinyFish Search API" } }, "nimble/search": { "input_cost_per_query": 0.005, "litellm_provider": "nimble", "mode": "search", "metadata": { "notes": "Nimble Search API pay-as-you-go list price: $5 per 1,000 searches, up to 100 results per search. Volume plans price differently." } }, "elevenlabs/scribe_v1": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", "original_pricing_per_hour": 0.22 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "elevenlabs/scribe_v1_experimental": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", "original_pricing_per_hour": 0.22 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://elevenlabs.io/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "elevenlabs/eleven_v3": { "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v3 - most expressive TTS model with 70+ languages and audio tags support" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_multilingual_v2": { "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Multilingual v2 - default TTS model with 29 languages support" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_v4": { "input_cost_per_character": 8e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.08/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v4 - most emotive TTS model with audio tags and 90+ languages" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_v4_turbo": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v4 Turbo - low-latency v4 tuned for real-time and agents" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_v3_conversational": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven v3 Conversational - low-latency v3 tuned for realtime conversation" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_flash_v2_5": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Flash v2.5 - low-latency multilingual TTS model" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_flash_v2": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Flash v2 - low-latency English-only TTS model" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_turbo_v2_5": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Turbo v2.5 - multilingual TTS model" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "elevenlabs/eleven_turbo_v2": { "input_cost_per_character": 4e-05, "litellm_provider": "elevenlabs", "metadata": { "calculation": "$0.04/1000 characters (API usage pricing, billed in USD per character)", "notes": "ElevenLabs Eleven Turbo v2 - English-only TTS model" }, "mode": "audio_speech", "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/speech" ] }, "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, "embed-english-v3.0": { "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true, "supports_image_input": true }, "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true }, "embed-multilingual-light-v3.0": { "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true }, "eu.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.95e-08, "input_cost_per_token": 7.8e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-07, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "eu.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 1.15e-08, "input_cost_per_token": 4.6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-07, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "eu.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.625e-07, "cache_read_input_token_cost_flex": 1.3125e-07, "input_cost_per_token": 1.05e-06, "input_cost_per_token_flex": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 4.2e-06, "output_cost_per_token_flex": 2.1e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "cache_read_input_token_cost": 8e-08, "cache_creation_input_token_cost": 1e-06, "prompt_cache_min_tokens": 2048 }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "deprecation_date": "2026-10-15", "successor_model": "eu.anthropic.claude-haiku-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "deprecation_date": "2027-01-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "token_count_model": { "model": "anthropic.claude-opus-4-1-20250805-v1:0", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "eu.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-20250514-v1:0", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "eu.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "eu.meta.llama3-2-1b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.mistral.pixtral-large-2502-v1:0": { "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, "fal_ai/bria/text-to-image/3.2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/v1.1": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, "output_cost_per_pixel": 3.814697265625e-08, "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/v1.1-ultra": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux/schnell": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.003, "output_cost_per_pixel": 2.86102294921875e-09, "source": "https://fal.ai/models/fal-ai/flux/schnell", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bytedance/seedance-2.5/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-latest/text-to-video": { "alias_of": "fal_ai/bytedance/seedance-2.5/text-to-video" }, "fal_ai/bytedance/seedance-2.5/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-latest/image-to-video": { "alias_of": "fal_ai/bytedance/seedance-2.5/image-to-video" }, "fal_ai/bytedance/seedance-2.5/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-latest/reference-to-video": { "alias_of": "fal_ai/bytedance/seedance-2.5/reference-to-video" }, "fal_ai/minimax/h3/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.06, "output_cost_per_second_2k": 0.13, "output_cost_per_second_4k": 0.16, "source": "https://fal.ai/models/minimax/h3/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.06, "output_cost_per_second_2k": 0.13, "output_cost_per_second_4k": 0.16, "source": "https://fal.ai/models/minimax/h3/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.3034, "output_cost_per_second_480p": 0.1346, "output_cost_per_second_720p": 0.3034, "output_cost_per_second_1080p": 0.682, "output_cost_per_second_4k": 1.5552, "source": "https://fal.ai/models/bytedance/seedance-2.0/text-to-video", "metadata": { "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" }, "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.3034, "output_cost_per_second_480p": 0.1346, "output_cost_per_second_720p": 0.3034, "output_cost_per_second_1080p": 0.682, "output_cost_per_second_4k": 1.5552, "source": "https://fal.ai/models/bytedance/seedance-2.0/image-to-video", "metadata": { "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" }, "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.3034, "output_cost_per_second_480p": 0.1346, "output_cost_per_second_720p": 0.3034, "output_cost_per_second_1080p": 0.682, "output_cost_per_second_4k": 1.5552, "source": "https://fal.ai/models/bytedance/seedance-2.0/reference-to-video", "metadata": { "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" }, "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ideogram/v3": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/imagen4/preview": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/imagen4/preview/fast": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/imagen4/preview/ultra": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v3/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/stable-diffusion-v35-medium": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-medium at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-medium", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/nano-banana": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "source": "https://fal.ai/models/fal-ai/nano-banana", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/gemini-25-flash-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/nano-banana-2": { "litellm_provider": "fal_ai", "metadata": { "comment": "priced by the request's resolution field (0.5K, 1K default, 2K, 4K); the web search and high thinking surcharges are not modeled" }, "mode": "image_generation", "output_cost_per_image": 0.08, "output_cost_per_image_0.5K": 0.06, "output_cost_per_image_1K": 0.08, "output_cost_per_image_2K": 0.12, "output_cost_per_image_4K": 0.16, "source": "https://fal.ai/models/fal-ai/nano-banana-2", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/nano-banana-pro": { "litellm_provider": "fal_ai", "metadata": { "comment": "priced by the request's resolution field (1K default, 2K, 4K); the web search surcharge is not modeled" }, "mode": "image_generation", "output_cost_per_image": 0.15, "output_cost_per_image_1K": 0.15, "output_cost_per_image_2K": 0.15, "output_cost_per_image_4K": 0.3, "source": "https://fal.ai/models/fal-ai/nano-banana-pro", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/google/nano-banana-2.1": { "litellm_provider": "fal_ai", "metadata": { "comment": "fal bills this endpoint by tokens and reports the charge in the x-fal-billable-units response header, priced at output_cost_per_billable_unit dollars per unit. The per-image prices are fal's representative costs by the request's resolution field (1K default, 2K, 4K) for a short prompt, used when the header is absent" }, "mode": "image_generation", "output_cost_per_billable_unit": 1.0, "output_cost_per_image": 0.04, "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.059, "output_cost_per_image_4K": 0.134, "source": "https://fal.ai/models/google/nano-banana-2.1", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/google/nano-banana-2.1/edit": { "litellm_provider": "fal_ai", "metadata": { "comment": "fal bills this endpoint by tokens and reports the charge in the x-fal-billable-units response header, priced at output_cost_per_billable_unit dollars per unit. The per-image prices are fal's representative costs by the request's resolution field (1K default, 2K, 4K) for a short prompt and two 1K input images, used when the header is absent" }, "mode": "image_generation", "output_cost_per_billable_unit": 1.0, "output_cost_per_image": 0.044, "output_cost_per_image_1K": 0.044, "output_cost_per_image_2K": 0.063, "output_cost_per_image_4K": 0.138, "source": "https://fal.ai/models/google/nano-banana-2.1/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/google/nano-banana-latest": { "alias_of": "fal_ai/google/nano-banana-2.1" }, "fal_ai/google/nano-banana-latest/edit": { "alias_of": "fal_ai/google/nano-banana-2.1/edit" }, "fal_ai/openai/gpt-image-2": { "litellm_provider": "fal_ai", "metadata": { "notes": "OpenAI gpt-image-2 served through fal.ai. fal bills by token but publishes deterministic per-image prices per size and quality, mirrored here as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2 that litellm's fal_ai cost calculator picks from the request params. This flat entry is the fallback when no keyed entry matches and carries the default request rate (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" }, "mode": "image_generation", "output_cost_per_image": 0.145, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.006, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.007, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.012, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.037, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.053, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.042, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.056, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.101, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.145, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.211, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.165, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.158, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.222, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.401, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/gpt-image-2": { "litellm_provider": "fal_ai", "metadata": { "notes": "Alias of fal_ai/openai/gpt-image-2, which litellm also accepts without the openai/ prefix. Same rates, including the keyed fal_ai/{quality}/{width}-x-{height}/gpt-image-2 entries; see that entry for details" }, "mode": "image_generation", "output_cost_per_image": 0.145, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.006, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.007, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.012, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.037, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.053, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.042, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.056, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.101, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.145, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.211, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.165, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.158, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.222, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/gpt-image-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.401, "source": "https://fal.ai/models/openai/gpt-image-2", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "metadata": { "notes": "Editing endpoint of gpt-image-2 on fal.ai, reached through the image generation path with fal's image_urls param since /v1/images/edits is not wired for fal_ai. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" }, "mode": "image_generation", "output_cost_per_image": 0.151, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.011, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.015, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.018, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.017, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.019, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.024, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.043, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.061, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.054, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.053, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.068, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.113, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.151, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.219, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.178, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.158, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.234, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.413, "source": "https://fal.ai/models/openai/gpt-image-2/edit", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "metadata": { "notes": "OpenAI gpt-image-2.5 (flare) served through fal.ai. fal publishes deterministic per-image prices per size and quality, mirrored as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/flare/text-to-image that the fal_ai cost calculator picks from the request params. This flat entry is the fallback for the default request (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" }, "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00402, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00588, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00474, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00441, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00615, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01113, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00903, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01317, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01434, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02595, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05268, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04116, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0396, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05529, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.10008, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0642, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09366, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07377, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07041, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09828, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1779, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.14445, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21072, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.16464, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1584, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.2211, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.40026, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "metadata": { "notes": "Editing endpoint of gpt-image-2.5 (flare) on fal.ai, reachable through /v1/images/edits or the image generation path with fal's image_urls param. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/flare/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" }, "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00402, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00588, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00474, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00441, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00615, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01113, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00903, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01317, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01434, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02595, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05268, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04116, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0396, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05529, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.10008, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0642, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09366, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07377, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07041, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09828, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1779, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-768/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.14445, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21072, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.16464, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1584, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.2211, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/flare/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.40026, "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "metadata": { "notes": "OpenAI gpt-image-2.5 (sunburst) served through fal.ai. fal publishes deterministic per-image prices per size and quality, mirrored as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/sunburst/text-to-image that the fal_ai cost calculator picks from the request params. This flat entry is the fallback for the default request (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" }, "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00402, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00588, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00474, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00441, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00615, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01113, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00903, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01317, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01434, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02595, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05268, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04116, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0396, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05529, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.10008, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0642, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09366, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07377, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07041, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09828, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1779, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.14445, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21072, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.16464, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1584, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.2211, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.40026, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true }, "fal_ai/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "metadata": { "notes": "Editing endpoint of gpt-image-2.5 (sunburst) on fal.ai, reachable through /v1/images/edits or the image generation path with fal's image_urls param. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/sunburst/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" }, "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00402, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00588, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00474, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00441, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00615, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01113, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.00903, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01317, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01029, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01434, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02595, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03612, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05268, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04116, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0396, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05529, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.10008, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0642, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09366, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07377, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07041, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09828, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1779, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.14445, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21072, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.16464, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1584, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.2211, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.40026, "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/dev": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/dev", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/trellis": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://fal.ai/models/fal-ai/trellis", "metadata": { "comment": "image-to-3D, returns a GLB mesh; served through the /fal_ai pass-through route" } }, "fal_ai/fal-ai/trellis-2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.3, "output_cost_per_image_512": 0.25, "output_cost_per_image_1024": 0.3, "output_cost_per_image_1536": 0.35, "source": "https://fal.ai/models/fal-ai/trellis-2", "metadata": { "comment": "image-to-3D, returns a GLB mesh; priced by the request's resolution field (default 1024); served through the /fal_ai pass-through route" } }, "fal_ai/fal-ai/flux-lora-depth": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora-depth", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/moondream3-preview/query": { "input_cost_per_token": 4e-07, "litellm_provider": "fal_ai", "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://fal.ai/models/fal-ai/moondream3-preview/query", "supported_endpoints": [ "/v1/chat/completions" ], "supports_reasoning": true, "supports_vision": true }, "featherless_ai/featherless-ai/Qwerky-72B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 2e-07 }, "fireworks-ai-56b-to-176b": { "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "output_cost_per_token": 1.2e-06 }, "fireworks-ai-above-16b": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 9e-07 }, "fireworks-ai-default": { "input_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "output_cost_per_token": 0.0 }, "fireworks-ai-embedding-150m-to-350m": { "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "output_cost_per_token": 0.0 }, "fireworks-ai-embedding-up-to-150m": { "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "output_cost_per_token": 0.0 }, "fireworks-ai-moe-up-to-56b": { "input_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 5e-07 }, "fireworks-ai-up-to-4b": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "output_cost_per_token": 1e-07, "source": "https://docs.fireworks.ai/serverless/pricing" }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 160000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus": { "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p2": { "input_cost_per_token": 5.6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-08-14", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 1.32e-06, "input_cost_per_token_priority": 1.65e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "cache_read_input_token_cost_priority": 5.5e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 1.32e-06, "input_cost_per_token_priority": 1.65e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/firefunction-v2": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p5": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p5", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://artificialanalysis.ai/models/glm-4-5-air", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p6": { "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-4p7": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/glm-5p1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { "cache_read_input_token_cost": 3.5e-08, "input_cost_per_token": 7e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905": { "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking": { "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2p5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, "cache_read_input_token_cost_priority": 2.2e-07, "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, "cache_read_input_token_cost_priority": 2.85e-07, "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, "input_cost_per_token_priority": 1.425e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { "input_cost_per_token": 1.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://fireworks.ai/pricing", "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/minimax-m2p1": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/minimax-latest": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/minimax-latest": { "alias_of": "fireworks_ai/accounts/fireworks/models/minimax-m3" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/accounts/fireworks/models/yi-large": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "fireworks_ai/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-08-14", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "successor_model": "fireworks_ai/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/glm-5p1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-5p1-fast": { "cache_read_input_token_cost": 5.2e-07, "input_cost_per_token": 2.8e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2026-09-25", "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/gpt-oss-20b": { "cache_read_input_token_cost": 3.5e-08, "input_cost_per_token": 7e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/kimi-k2p5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, "cache_read_input_token_cost_priority": 2.2e-07, "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, "cache_read_input_token_cost_priority": 2.85e-07, "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, "input_cost_per_token_priority": 1.425e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/minimax-m2p1": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/nomic-ai/nomic-embed-text-v1": { "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, "fireworks_ai/thenlper/gte-base": { "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, "fireworks_ai/thenlper/gte-large": { "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, "friendliai/zai-org/GLM-5.3-Flash": { "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_image_input": true, "supports_video_input": true, "mode": "chat", "comment": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "source": "https://api.friendli.ai/serverless/v1/models" }, "friendliai/zai-org/GLM-5.3": { "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.26e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 2.34e-07, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "supports_image_input": false, "supports_video_input": false, "mode": "chat", "comment": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "source": "https://api.friendli.ai/serverless/v1/models" }, "friendliai/google/gemma-4-31B-it": { "litellm_provider": "friendliai", "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "supports_prompt_caching": false, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_image_input": true, "supports_video_input": false, "mode": "chat", "comment": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "source": "https://api.friendli.ai/serverless/v1/models" }, "friendliai/zai-org/GLM-5.2": { "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "high", "max" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "supports_image_input": false, "supports_video_input": false, "mode": "chat", "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", "max_input_tokens": 202752, "max_output_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "supports_image_input": false, "supports_video_input": false, "mode": "chat", "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "source": "https://api.friendli.ai/serverless/v1/models", "deprecation_date": "2026-11-20" }, "ft:babbage-002": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.6e-06, "input_cost_per_token_batches": 8e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 9e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "ft:davinci-002": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.2e-05, "input_cost_per_token_batches": 6e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "source": "https://developers.openai.com/api/docs/pricing" }, "ft:gpt-3.5-turbo": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0613": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "ft:gpt-3.5-turbo", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "fedramp_uplift_multiplier": 1.1, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4-0613": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "fedramp_uplift_multiplier": 1.1, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "cache_read_input_token_cost_batches": 9e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.25e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "ft:gpt-4o-2024-11-20": { "cache_creation_input_token_cost": 1.875e-06, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, "cache_read_input_token_cost_batches": 5e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.2e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.6e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-4.1-nano-2025-04-14": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "ft:o4-mini-2025-04-16": { "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 1.6e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, "deprecation_date": "2026-10-20", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_above_200k_tokens": 3e-07, "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true }, "gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "rpm": 100000, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": false, "tpm": 8000000, "supports_image_size": false }, "gemini-3-pro-image": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 6e-05, "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 6e-05, "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_image_token_batches": 3e-05, "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_image_token_batches": 3e-05, "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_audio_token_cost_batches": 2.5e-08, "cache_read_input_audio_token_cost_flex": 2.5e-08, "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, "input_cost_per_audio_token_above_200k_tokens": 5e-07, "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, "input_cost_per_audio_token_batches": 2.5e-07, "input_cost_per_audio_token_flex": 2.5e-07, "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, "deprecation_date": "2026-10-20", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token": 3e-07, "input_cost_per_audio_token_above_200k_tokens": 3e-07, "input_cost_per_audio_token_above_200k_tokens_batches": 5e-08, "input_cost_per_audio_token_above_200k_tokens_flex": 5e-08, "input_cost_per_audio_token_above_200k_tokens_priority": 5.4e-07, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_audio_token_flex": 5e-08, "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, "output_cost_per_token_priority": 7.2e-07, "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, "search_free_requests": {"count":1500,"period":"day","shared_group":"gemini-2-flash"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_image_size": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true }, "gemini-2.5-flash-lite-preview-09-2025": { "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, "gemini-2.5-flash-preview-09-2025": { "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, "gemini-live-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": false, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "input_cost_per_image_token": 3e-06, "input_cost_per_video_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "input_cost_per_image_token": 3e-06 }, "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true }, "gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, "deprecation_date": "2026-10-20", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.25e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, "output_cost_per_token_above_200k_tokens_flex": 7.5e-06, "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 2048.0, "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, "search_free_requests": {"count":10000,"period":"day","shared_group":"gemini-2.5-pro"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, "gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_priority": 9e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_above_200k_tokens": 1e-06, "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, "input_cost_per_audio_token_priority": 2.7e-06, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_token_batches": 4.5e-06, "output_cost_per_token_flex": 4.5e-06, "output_cost_per_token_priority": 1.62e-05, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "vertex_ai/gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2027-01-28", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, "supports_video_input": true, "supports_vision": true, "supports_web_search": false, "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, "input_cost_per_video_token": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "output_cost_per_video_token": 1e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, "gemini-robotics-er-1.5-preview": { "cache_read_input_token_cost": 0, "input_cost_per_token": 3e-07, "input_cost_per_audio_token": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_reasoning_token": 2.5e-06, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true }, "gemini/gemini-robotics-er-2-preview": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gemini-embedding-001": { "deprecation_date": "2028-05-20", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "gemini-embedding-2", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "gemini-embedding-2-preview": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_embedding_image_input": true, "uses_embed_content": true }, "gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, "vertex_ai/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_embedding_image_input": true, "supports_multimodal": true, "uses_embed_content": true }, "gemini-flash-experimental": { "input_cost_per_character": 0, "input_cost_per_token": 0, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true }, "gemini/gemini-embedding-001": { "deprecation_date": "2028-05-14", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-embedding-2", "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "tpm": 10000000, "input_cost_per_token_batches": 7.5e-08 }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 }, "gemini/gemini-3-pro-image-preview": { "deprecation_date": "2026-06-25", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3-pro-image", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, "gemini/gemini-3.1-flash-image-preview": { "deprecation_date": "2026-06-25", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-nano-banana-2.1", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-05-25", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.1-flash-lite", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 }, "gemini/gemini-embedding-2-preview": { "deprecation_date": "2026-11-06", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 6.5e-06, "input_cost_per_audio_token_batches": 3.25e-06, "input_cost_per_image_token": 4.5e-07, "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_video_token": 1.2e-05, "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "successor_model": "gemini/gemini-embedding-2", "supports_audio_input": true, "supports_embedding_image_input": true, "supports_multimodal": true, "supports_vision": true, "tpm": 10000000 }, "gemini/deep-research-preview-04-2026": { "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, "gemini/deep-research-max-preview-04-2026": { "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, "gemini/gemini-2.5-flash": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_audio_token_cost_batches": 1e-07, "cache_read_input_audio_token_cost_flex": 1e-07, "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 3e-08, "cache_read_input_token_cost_flex": 3e-08, "cache_read_input_token_cost_priority": 5.4e-08, "deprecation_date": "2026-12-01", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, "deprecation_date": "2027-03-15", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "gemini", "supports_reasoning": false, "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": false, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_audio_input": false, "supports_image_size": false }, "gemini/gemini-3-pro-image": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 6e-05, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": true }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-image": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, "output_cost_per_image_token_batches": 3e-05, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "rpm": 1000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-nano-banana-2.1", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "rpm": 1000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": false, "tpm": 4000000 }, "gemini/deep-research-pro-preview-12-2025": { "deprecation_date": "2026-10-23", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/deep-research-preview-04-2026", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "rpm": 1000.0, "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "tpm": 4000000.0 }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, "cache_read_input_audio_token_cost_batches": 3e-08, "cache_read_input_audio_token_cost_flex": 3e-08, "cache_read_input_audio_token_cost_priority": 5.4e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_audio_token_flex": 1.5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, "output_cost_per_token_priority": 7.2e-07, "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query" }, "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 2e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-preview-tts": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "tpm": 4000000, "rpm": 10, "supports_audio_input": false, "supports_function_calling": false, "supports_response_schema": false, "supports_web_search": false }, "gemini/gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_priority": 2.25e-06, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "output_cost_per_token_priority": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "supports_url_context": true, "cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_flex": 2.5e-07, "deprecation_date": "2026-12-01", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash", "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, "input_cost_per_token_above_200k_tokens_flex": 1.25e-06, "output_cost_per_token_above_200k_tokens_batches": 7.5e-06, "output_cost_per_token_above_200k_tokens_flex": 7.5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "deprecation_date": "2026-07-28", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 800000 }, "gemini/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_audio_token_cost_batches": 2.5e-08, "cache_read_input_audio_token_cost_flex": 2.5e-08, "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-05-07", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.5-flash-lite", "input_cost_per_audio_token": 5e-07, "input_cost_per_audio_token_flex": 2.5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07, "input_cost_per_audio_token_priority": 9e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 2e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "supports_computer_use": true }, "gemini/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_audio_token_cost_batches": 1e-07, "cache_read_input_audio_token_cost_flex": 1e-07, "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 9e-07, "input_cost_per_audio_token_priority": 1.8e-06, "output_cost_per_token_priority": 5.4e-06, "cache_read_input_token_cost_priority": 9e-08, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "successor_model": "gemini/gemini-3.6-flash", "supports_audio_input": true, "supports_computer_use": true }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 2.7e-06, "input_cost_per_audio_token_priority": 2.7e-06, "output_cost_per_token_priority": 1.62e-05, "cache_read_input_token_cost_priority": 2.7e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, "cache_read_input_token_cost_flex": 8e-08, "successor_model": "gemini/gemini-3.6-flash" }, "gemini/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "successor_model": "gemini/gemini-3.8-flash" }, "gemini/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "supports_computer_use": true }, "gemini/gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, "tpm": 800000, "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-omni-1.2-flash" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 6e-06, "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_flex": 6e-06, "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_audio_token_cost_priority": 1.8e-07, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_priority": 9e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_above_200k_tokens": 1e-06, "input_cost_per_audio_token_above_200k_tokens_batches": 5e-07, "input_cost_per_audio_token_above_200k_tokens_flex": 5e-07, "input_cost_per_audio_token_above_200k_tokens_priority": 1.8e-06, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_audio_token_flex": 5e-07, "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, "deprecation_date": "2026-11-06" }, "gemini-3.5-flash": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1.5e-06, "input_cost_per_audio_token_priority": 2.7e-06, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_token_batches": 4.5e-06, "output_cost_per_token_flex": 4.5e-06, "output_cost_per_token_priority": 1.62e-05, "prompt_cache_min_tokens": 4096.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "gemini-3.8-flash", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2026-11-19", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, "deprecation_date": "2027-01-28", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "gemini-3.8-flash", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, "supports_video_input": true, "supports_vision": true, "supports_web_search": false, "supports_native_streaming": true }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "supports_web_search": false, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_audio_input": false }, "gemini/gemini-exp-1114": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 4000000 }, "gemini/gemini-exp-1206": { "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 2097152, "max_output_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 4000000 }, "gemini/gemini-gemma-2-27b-it": { "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 250000, "rpm": 10 }, "gemini/gemini-gemma-2-9b-it": { "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "tpm": 250000, "rpm": 10 }, "gemini/gemma-3-27b-it": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_vision": true }, "gemini/gemma-4-26b-a4b-it": { "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://ai.google.dev/gemini-api/docs/pricing" }, "gemini/gemma-4-31b-it": { "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://ai.google.dev/gemini-api/docs/pricing" }, "gemini/imagen-3.0-fast-generate-001": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini/imagen-3.0-generate-001": { "litellm_provider": "gemini", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini/learnlm-1.5-pro-experimental": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gemini/lyria-3-clip-preview": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false }, "gemini/lyria-3-pro-preview": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "output_cost_per_image": 0.08, "successor_model": "gemini/lyria-3.5" }, "gemini/veo-3.1-fast-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "gemini/veo-3.1-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "gemini/veo-3.1-lite-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "gemini/veo-3.1-fast-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "gemini/veo-3.1-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "github_copilot/claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": true }, "github_copilot/claude-fable-5.1": { "cache_creation_input_token_cost": 1.25e-05, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": true }, "github_copilot/claude-fable-latest": { "alias_of": "github_copilot/claude-fable-5.2" }, "github_copilot/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "github_copilot/claude-haiku-5.5": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_above_100k_tokens": 5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": false }, "github_copilot/claude-haiku-latest": { "alias_of": "github_copilot/claude-haiku-5.5" }, "github_copilot/claude-opus-4.8": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-11-16", "input_cost_per_token": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/claude-opus-4.8-fast": { "cache_creation_input_token_cost": 1.25e-05, "cache_read_input_token_cost": 1e-06, "deprecation_date": "2026-11-16", "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/claude-opus-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-11-16", "input_cost_per_token": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/claude-opus-5.5": { "cache_creation_input_token_cost": 5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": true }, "github_copilot/claude-opus-latest": { "alias_of": "github_copilot/claude-opus-5.5" }, "github_copilot/claude-sonnet-5": { "cache_creation_input_token_cost": 2.5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/claude-sonnet-5.5": { "cache_creation_input_token_cost": 2.5e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": true }, "github_copilot/claude-sonnet-latest": { "alias_of": "github_copilot/claude-sonnet-5.5" }, "github_copilot/gemini-3.7-flash": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2026-10-19", "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gemini-3.8-flash": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true }, "github_copilot/gpt-3.5-turbo-0613": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true }, "github_copilot/gpt-4": { "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true }, "github_copilot/gpt-4-0613": { "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true }, "github_copilot/gpt-4-o-preview": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { "deprecation_date": "2026-06-01", "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { "deprecation_date": "2026-06-01", "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-41-copilot": { "litellm_provider": "github_copilot", "mode": "completion" }, "github_copilot/gpt-4o": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/gpt-4o-2024-05-13": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/gpt-4o-2024-08-06": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-4o-2024-11-20": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "github_copilot/gpt-4o-mini": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-4o-mini-2024-07-18": { "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true }, "github_copilot/gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-10-19", "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "deprecation_date": "2026-10-19", "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.4-mini": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2026-10-19", "input_cost_per_token": 7.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 4.5e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "deprecation_date": "2026-10-19", "deprecation_source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_200k_tokens": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_200k_tokens": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_above_200k_tokens": 4e-07, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_200k_tokens": 1.8e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.6-sol": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "deprecation_date": "2026-11-16", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-astra-latest": { "alias_of": "github_copilot/gpt-6-astra" }, "github_copilot/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-luna-latest": { "alias_of": "github_copilot/gpt-6-luna" }, "github_copilot/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-sol-latest": { "alias_of": "github_copilot/gpt-6.1-sol" }, "github_copilot/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 917504, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/kimi-latest": { "alias_of": "github_copilot/kimi-k3" }, "github_copilot/mai-code-1.1-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.2e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, "mode": "embedding" }, "chatgpt/gpt-6-sol": { "litellm_provider": "chatgpt", "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_input_tokens": 922000, "max_output_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-6-luna": { "litellm_provider": "chatgpt", "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_input_tokens": 922000, "max_output_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-6-astra": { "litellm_provider": "chatgpt", "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_input_tokens": 922000, "max_output_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-6.1-sol": { "litellm_provider": "chatgpt", "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_input_tokens": 922000, "max_output_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.5": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.6-luna": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-sol": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-terra": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.4": { "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.4-pro": { "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "chatgpt/gpt-5.3-instant": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "chatgpt/gpt-5.3-chat-latest": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true }, "chatgpt/gpt-5.2": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.1-codex-max": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true }, "chatgpt/gpt-5.1-codex-mini": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true }, "gigachat/GigaChat-2": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, "supports_system_messages": true }, "gigachat/GigaChat-2-Max": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true }, "gigachat/GigaChat-2-Pro": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true }, "gigachat/Embeddings": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "gigachat/Embeddings-2": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 }, "gigachat/EmbeddingsGigaR": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 }, "gigachat/GigaEmbeddings-3B-2025-09": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 }, "gmi/anthropic/claude-opus-4.5": { "input_cost_per_token": 5e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, "supports_vision": true, "supports_output_config": true }, "gmi/anthropic/claude-sonnet-4.5": { "input_cost_per_token": 3e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_vision": true }, "gmi/anthropic/claude-sonnet-4": { "input_cost_per_token": 3e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_vision": true }, "gmi/anthropic/claude-opus-4": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_vision": true }, "gmi/openai/gpt-5.2": { "input_cost_per_token": 1.75e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, "supports_function_calling": true }, "gmi/openai/gpt-5.1": { "input_cost_per_token": 1.25e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true }, "gmi/openai/gpt-5": { "input_cost_per_token": 1.25e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true }, "gmi/openai/gpt-4o": { "input_cost_per_token": 2.5e-06, "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_vision": true }, "gmi/openai/gpt-4o-mini": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_vision": true }, "gmi/deepseek-ai/DeepSeek-V3.2": { "input_cost_per_token": 2.8e-07, "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true }, "gmi/deepseek-ai/DeepSeek-V3-0324": { "input_cost_per_token": 2.8e-07, "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "supports_function_calling": true }, "gmi/google/gemini-3-flash-preview": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_vision": true, "supports_system_messages": true }, "gmi/moonshotai/Kimi-K2-Thinking": { "input_cost_per_token": 8e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, "gmi/MiniMaxAI/MiniMax-M2.1": { "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/MiniMaxAI/MiniMax-M2.5": { "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/nvidia/Nemotron-120B-A12B": { "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-07 }, "baseten/zai-org/GLM-5": { "deprecation_date": "2026-10-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 200000, "max_output_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/zai-org/GLM-4.6": { "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.2e-06 }, "baseten/moonshotai/Kimi-K2.5": { "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3e-06 }, "baseten/moonshotai/Kimi-K2-Thinking": { "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/openai/gpt-oss-120b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, "litellm_provider": "baseten", "max_input_tokens": 128072, "max_output_tokens": 128072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { "deprecation_date": "2026-10-16", "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.5e-06 }, "baseten/deepseek-ai/DeepSeek-V3-0324": { "deprecation_date": "2026-10-16", "input_cost_per_token": 7.7e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.7e-07 }, "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8": { "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06, "supports_vision": true }, "gmi/zai-org/GLM-4.7-FP8": { "input_cost_per_token": 4e-07, "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-06 }, "google.gemma-3-12b-it": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 9e-08, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_flex": 1.5e-07, "output_cost_per_token_priority": 5.1e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "google.gemma-3-27b-it": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.3e-07, "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, "output_cost_per_token_batches": 1.9e-07, "output_cost_per_token_flex": 1.9e-07, "output_cost_per_token_priority": 6.7e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "google.gemma-3-4b-it": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-08, "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, "output_cost_per_token_batches": 4e-08, "output_cost_per_token_flex": 4e-08, "output_cost_per_token_priority": 1.4e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true }, "google_pse/search": { "input_cost_per_query": 0.005, "litellm_provider": "google_pse", "mode": "search" }, "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "global.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "global.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-20250514-v1:0", "litellm_provider": "bedrock" } }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, "output_cost_per_token_batches": 2.5e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_priority": 4.375e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "gpt-3.5-turbo": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-07, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-16k": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "fedramp_uplift_multiplier": 1.1, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-instruct": { "deprecation_date": "2026-09-28", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2e-06 }, "gpt-4": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4-0613": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 3e-05, "input_cost_per_token_batches": 1.5e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4-1106-preview": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4-turbo": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "fedramp_uplift_multiplier": 1.1, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4-turbo-2024-04-09": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.4e-05, "output_cost_per_token_batches": 4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 4e-07, "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-06, "output_cost_per_token_batches": 8e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4.1-nano": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_priority": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 8e-07, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4.1-nano-2025-04-14": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-luna", "input_cost_per_token": 1e-07, "input_cost_per_token_priority": 2e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 8e-07, "output_cost_per_token_batches": 2e-07, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_priority": 4.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.7e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o-2024-05-13": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_priority": 8.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 2.625e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4o-audio-preview-2025-06-03": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 1e-05, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-audio": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gpt-audio-1.5": { "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gpt-audio-2025-08-28": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gpt-audio-mini": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gpt-audio-mini-2025-10-06": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-audio-1.5", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_priority": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, "deprecation_date": "2027-01-14", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 1e-06, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4o-mini-search-preview": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4o-mini-search-preview-2025-03-11": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview" }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-live-transcribe", "input_cost_per_second": 5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { "deprecation_date": "2027-01-06", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "gpt-4o-mini-tts-2025-03-20": { "deprecation_date": "2027-01-06", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-4o-search-preview-2025-03-11": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview" }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-live-transcribe", "input_cost_per_second": 0.0001, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-1.5": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true, "supports_pdf_input": true }, "gpt-image-1.5-2025-12-16": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations" ], "supports_vision": true, "supports_pdf_input": true }, "gpt-image-2": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, "deprecation_date": "2027-02-10", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "source": "https://developers.openai.com/api/docs/pricing", "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "gpt-image-2-2026-04-21": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-02-10", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "successor_model": "gpt-image-2.6-sunburst", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-2.5-flare-2026-09-08": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-2.5-sunburst-2026-09-08": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "source": "https://developers.openai.com/api/docs/pricing" }, "low/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "low/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "low/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "medium/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "medium/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "medium/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "high/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "high/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "high/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "standard/1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "standard/1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "standard/1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "1024-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "1024-x-1536/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "1536-x-1024/gpt-image-1.5": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true }, "low/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "low/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "low/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "medium/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "medium/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "high/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "high/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "standard/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "standard/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst" }, "gpt-5": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "deprecation_date": "2027-04-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-sol" }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-04-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, "cache_read_input_token_cost_flex": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_flex": 8.75e-07, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_flex": 7e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_batches": 8.75e-08, "cache_read_input_token_cost_flex": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_flex": 8.75e-07, "output_cost_per_token_batches": 7e-06, "output_cost_per_token_flex": 7e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 8.4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_12hr": 2.5e-05, "cache_creation_input_token_cost_above_12hr_ultrafast": 0.00015, "cache_creation_input_token_cost_above_12hr_batches": 1.25e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.0001, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 0.0003, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-05, "cache_creation_input_token_cost_above_12hr_priority": 5e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, "cache_creation_input_token_cost_flex": 6.25e-06, "cache_creation_input_token_cost_priority": 2.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-06, "cache_read_input_token_cost_batches": 5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, "cache_creation_input_token_cost_ultrafast": 7.5e-05, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, "cache_read_input_token_cost_flex": 5e-07, "cache_read_input_token_cost_priority": 2e-06, "cache_read_input_token_cost_ultrafast": 6e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "input_cost_per_token_above_272k_tokens_flex": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 4e-05, "input_cost_per_token_batches": 5e-06, "input_cost_per_token_above_272k_tokens_batches": 1e-05, "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, "input_cost_per_token_flex": 5e-06, "input_cost_per_token_priority": 2e-05, "input_cost_per_token_ultrafast": 6e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 2.5e-05, "output_cost_per_token_above_272k_tokens_batches": 3.75e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_flex": 2.5e-05, "output_cost_per_token_priority": 0.0001, "output_cost_per_token_ultrafast": 0.0003, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-astra-latest": { "alias_of": "gpt-6-astra" }, "gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_12hr": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_above_272k_tokens_batches": 2e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 4e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_12hr": 2.5e-07, "cache_creation_input_token_cost_above_12hr_batches": 1.25e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-06, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-07, "cache_creation_input_token_cost_above_12hr_priority": 5e-07, "cache_creation_input_token_cost_decisions": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_decisions": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_creation_input_token_cost_priority": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_decisions": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, "cache_read_input_token_cost_batches": 5e-09, "cache_read_input_token_cost_above_272k_tokens_batches": 1e-08, "cache_creation_input_token_cost_batches": 6.25e-08, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-07, "cache_read_input_token_cost_flex": 5e-09, "cache_read_input_token_cost_priority": 2e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_decisions": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "input_cost_per_token_above_272k_tokens_decisions": 2e-07, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_above_272k_tokens_priority": 4e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_above_272k_tokens_batches": 1e-07, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 2e-07, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_decisions": 0.0, "output_cost_per_token_above_272k_tokens": 7.5e-07, "output_cost_per_token_above_272k_tokens_decisions": 0.0, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_above_272k_tokens_priority": 1.5e-06, "output_cost_per_token_batches": 2.5e-07, "output_cost_per_token_above_272k_tokens_batches": 3.75e-07, "output_cost_per_token_flex": 2.5e-07, "output_cost_per_token_priority": 1e-06, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses", "/v1/decisions" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-luna-latest": { "alias_of": "gpt-6-luna" }, "gpt-5.6": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_12hr": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, "cache_creation_input_token_cost_above_12hr_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06, "cache_read_input_token_cost_flex": 2e-07, "cache_read_input_token_cost_priority": 8e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "input_cost_per_token_batches": 2e-06, "input_cost_per_token_above_272k_tokens_batches": 4e-06, "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 8e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_batches": 1e-05, "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-sol": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_12hr": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 2e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 4e-05, "cache_creation_input_token_cost_above_12hr_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_priority": 2e-05, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06, "cache_read_input_token_cost_flex": 2e-07, "cache_read_input_token_cost_priority": 8e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "input_cost_per_token_above_272k_tokens_flex": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "input_cost_per_token_batches": 2e-06, "input_cost_per_token_above_272k_tokens_batches": 4e-06, "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 8e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, "output_cost_per_token_above_272k_tokens_priority": 6e-05, "output_cost_per_token_batches": 1e-05, "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 4e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_12hr": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_above_272k_tokens_batches": 2e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 4e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_above_272k_tokens_batches": 9e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.4e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_12hr": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-07, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-06, "cache_creation_input_token_cost_above_12hr_batches": 2.5e-07, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-07, "cache_creation_input_token_cost_above_12hr_priority": 1e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, "cache_creation_input_token_cost_flex": 1.25e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-08, "cache_creation_input_token_cost_batches": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_flex": 1e-08, "cache_read_input_token_cost_priority": 4e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_token_above_272k_tokens_batches": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_priority": 4e-07, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_above_272k_tokens_batches": 9e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.4e-06, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-5.6-cyber": { "cache_creation_input_token_cost": 1.5625e-05, "cache_creation_input_token_cost_above_12hr": 3.125e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "supports_parallel_function_calling": true }, "daybreak-red-latest": { "cache_creation_input_token_cost": 1.5625e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "supports_parallel_function_calling": true }, "gpt-daybreak-red-latest": { "cache_creation_input_token_cost": 1.5625e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, "input_cost_per_token": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2.5e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 7.5e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "supports_parallel_function_calling": true }, "daybreak-blue-latest": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "supports_parallel_function_calling": true }, "gpt-daybreak-blue-latest": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_above_272k_tokens": 3e-05, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "supports_parallel_function_calling": true }, "chat-latest": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "fedramp_uplift_multiplier": 1.1, "reasoning_effort_levels": [ "medium" ], "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_batches": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_batches": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens_batches": 5e-06, "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, "output_cost_per_token_priority": 7.5e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-pro": { "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false }, "gpt-5.5-pro-2026-04-23": { "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false }, "gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_batches": 1.3e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_flex": 1.3e-07, "cache_read_input_token_cost_priority": 5e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_flex": 1.25e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "input_cost_per_token_priority": 5e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_batches": 1.3e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_flex": 1.3e-07, "cache_read_input_token_cost_priority": 5e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_flex": 1.25e-06, "input_cost_per_token_batches": 1.25e-06, "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "input_cost_per_token_priority": 5e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro": { "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro-2026-03-05": { "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 3e-05, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-mini": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-mini-latest": { "alias_of": "gpt-5.4-mini" }, "gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_batches": 2.25e-06, "output_cost_per_token_priority": 9e-06, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "deprecation_date": "2027-04-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-04-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-luna", "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 6.25e-07, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5-pro": { "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-pro-2025-10-06": { "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 6e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.2-chat-latest", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_priority": 2.8e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "deprecation_date": "2027-04-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-6-sol" }, "gpt-5.3-chat-latest": { "cache_read_input_token_cost": 1.75e-07, "deprecation_date": "2026-08-10", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-luna", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-image-1": { "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 1e-05, "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 4e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "gpt-image-1-mini": { "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_image_token_cost_batches": 1.3e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 2.5e-06, "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 8e-06, "output_cost_per_image_token_batches": 4e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "gpt-realtime": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-1.5": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-2": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "realtime", "provider_specific_entry": { "realtime_ga_only": 1 }, "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-2.1-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-realtime-2025-08-28": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 131072, "max_output_tokens": 40960 }, "gradient_ai/anthropic-claude-3-opus": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 7.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 4e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "gradient_ai/anthropic-claude-3.5-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "gradient_ai/anthropic-claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 1024 }, "gradient_ai/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 9.9e-07, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 32768, "max_output_tokens": 8000 }, "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 2e-07, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 8192, "max_output_tokens": 512 }, "gradient_ai/llama3.3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 6.5e-07, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 2048 }, "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 3e-07, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 512 }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 16384 }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 128000, "max_output_tokens": 16384 }, "gradient_ai/openai-o3": { "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 100000 }, "gradient_ai/openai-o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supports_tool_choice": false, "max_input_tokens": 200000, "max_output_tokens": 100000 }, "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "lemonade/gpt-oss-20b-mxfp4-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "lemonade/gpt-oss-120b-mxfp-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "lemonade/Gemma-3-4b-it-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "lemonade/Qwen3-4B-Instruct-2507-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "amazon-nova/nova-micro-v1": { "input_cost_per_token": 3.5e-08, "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true }, "amazon-nova/nova-lite-v1": { "input_cost_per_token": 6e-08, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true }, "amazon-nova/nova-premier-v1": { "input_cost_per_token": 2.5e-06, "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_response_schema": true, "supports_vision": true }, "amazon-nova/nova-pro-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-08, "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://console.groq.com/docs/models" }, "groq/meta-llama/llama-prompt-guard-2-86m": { "input_cost_per_token": 4e-08, "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" }, "groq/openai/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "groq/openai/gpt-oss-20b": { "cache_read_input_token_cost": 3.75e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "groq/openai/gpt-oss-safeguard-20b": { "cache_read_input_token_cost": 3.7e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "groq/canopylabs/orpheus-v1-english": { "input_cost_per_character": 2.2e-05, "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, "groq/canopylabs/orpheus-arabic-saudi": { "input_cost_per_character": 4e-05, "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, "groq/whisper-large-v3": { "input_cost_per_second": 3.083e-05, "litellm_provider": "groq", "mode": "audio_transcription", "output_cost_per_second": 0.0 }, "groq/whisper-large-v3-turbo": { "input_cost_per_second": 1.111e-05, "litellm_provider": "groq", "mode": "audio_transcription", "output_cost_per_second": 0.0 }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "heroku/claude-3-5-sonnet-latest": { "litellm_provider": "heroku", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "heroku/claude-4-sonnet": { "litellm_provider": "heroku", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "high/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "high/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "hostinger_router/gpt-5.2": { "cache_read_input_token_cost": 0.00000021, "input_cost_per_token": 0.0000021, "litellm_provider": "hostinger_router", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000168, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": true, "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], "source": "https://router.hostinger.com/v1/models" }, "hostinger_router/claude-sonnet-5": { "cache_creation_input_token_cost": 3.3e-06, "cache_creation_input_token_cost_above_1hr": 5.28e-06, "cache_read_input_token_cost": 2.64e-07, "input_cost_per_token": 2.64e-06, "litellm_provider": "hostinger_router", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_response_schema": true, "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "source": "https://router.hostinger.com/v1/models" }, "hostinger_router/text-embedding-3-large": { "input_cost_per_token": 1.716e-07, "litellm_provider": "hostinger_router", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://router.hostinger.com/v1/models" }, "hostinger_router/text-embedding-3-small": { "input_cost_per_token": 3e-08, "litellm_provider": "hostinger_router", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://router.hostinger.com/v1/models" }, "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/Qwen/QwQ-32B": { "input_cost_per_token": 2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/Qwen/Qwen3-235B-A22B": { "input_cost_per_token": 2e-06, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-R1": { "input_cost_per_token": 4e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 2.5e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { "input_cost_per_token": 4e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "hyperbolic/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 2e-06, "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "j2-light": { "input_cost_per_token": 3e-06, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 3e-06 }, "j2-mid": { "input_cost_per_token": 1e-05, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 1e-05 }, "j2-ultra": { "input_cost_per_token": 1.5e-05, "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 1.5e-05 }, "jamba-1.5": { "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "jamba-1.5-large": { "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "jamba-1.5-large@001": { "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "jamba-1.5-mini": { "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "jamba-1.5-mini@001": { "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "jamba-large-1.6": { "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "jamba-large-1.7": { "input_cost_per_token": 2e-06, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "jamba-mini-1.6": { "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "jamba-mini-1.7": { "input_cost_per_token": 2e-07, "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "jina-reranker-v3.5": { "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 131072, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" }, "jina-reranker-m0": { "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 10240, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" }, "jina-reranker-v2-base-multilingual": { "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "jp.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 7e-06, "supports_function_calling": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false }, "crusoe/deepseek-ai/DeepSeek-V3-0324": { "input_cost_per_token": 1.5e-06, "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "crusoe/google/gemma-3-12b-it": { "input_cost_per_token": 1e-07, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "crusoe/meta-llama/Llama-3.3-70B-Instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "crusoe/moonshotai/Kimi-K2-Thinking": { "input_cost_per_token": 2.5e-06, "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_function_calling": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false }, "crusoe/openai/gpt-oss-120b": { "input_cost_per_token": 8e-07, "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507": { "input_cost_per_token": 3e-06, "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "inception/mercury-2": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "inception", "max_input_tokens": 128000, "max_output_tokens": 50000, "mode": "chat", "output_cost_per_token": 7.5e-07, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "inception/mercury-2.5": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true }, "inferenceapis/deepseek-ai/DeepSeek-V3": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-chat": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-flash": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-reasoner": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-v3": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-v4-pro": { "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/deepseek-v4.1-flash": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/glm-5.3": { "cache_read_input_token_cost": 3.4e-07, "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/glm-5.3-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/gpt-oss-120b": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/gpt-oss-20b": { "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/kimi-k2.7-code": { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/llama-3.1-8b-instant": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/llama-3.3-70b": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/llama-3.3-70b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/llama-3.3-70b-versatile": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/minimax-m3": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/moonshotai/Kimi-K2.7-Code": { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/openai/gpt-oss-120b": { "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/openai/gpt-oss-20b": { "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": { "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": true }, "inferenceapis/Qwen/Qwen3.8-Flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/qwen3-vl": { "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": true }, "inferenceapis/qwen3-vl-235b": { "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_vision": true }, "inferenceapis/qwen3.8-flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/zai-org/GLM-5.3": { "cache_read_input_token_cost": 3.4e-07, "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "inferenceapis/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "text-completion-inception/mercury-edit-2": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "text-completion-inception", "max_input_tokens": 32000, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 7.5e-07 }, "lambda_ai/deepseek-llama3.3-70b": { "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/deepseek-r1-0528": { "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/deepseek-r1-671b": { "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/deepseek-v3-0324": { "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/hermes3-405b": { "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/hermes3-70b": { "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/hermes3-8b": { "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/lfm-40b": { "input_cost_per_token": 1e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/lfm-7b": { "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 16384, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.1-405b-instruct-fp8": { "input_cost_per_token": 8e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.1-70b-instruct-fp8": { "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.1-8b-instruct": { "input_cost_per_token": 2.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.2-11b-vision-instruct": { "input_cost_per_token": 1.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "lambda_ai/llama3.2-3b-instruct": { "input_cost_per_token": 1.5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/llama3.3-70b-instruct-fp8": { "input_cost_per_token": 1.2e-07, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/qwen25-coder-32b-instruct": { "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "lambda_ai/qwen3-32b-fp8": { "input_cost_per_token": 5e-08, "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "low/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.011, "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "low/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "low/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.072 }, "medium/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.042, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "medium/1024-x-1536/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "medium/1536-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, "low/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.005, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "low/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "low/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "medium/1024-x-1024/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.011, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "medium/1024-x-1536/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "medium/1536-x-1024/gpt-image-1-mini": { "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", "supported_endpoints": [ "/v1/images/generations" ] }, "medlm-large": { "input_cost_per_character": 5e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "chat", "output_cost_per_character": 1.5e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "medlm-medium": { "input_cost_per_character": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_character": 1e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "meta.llama2-13b-chat-v1": { "input_cost_per_token": 7.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama2-70b-chat-v1": { "input_cost_per_token": 1.95e-06, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.56e-06, "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama3-1-405b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-1-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.2e-07, "output_cost_per_token_batches": 1.1e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-11b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-2-1b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-3b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "meta.llama3-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "meta.llama4-maverick-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama4-scout-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 10000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false }, "meta/muse-ember-1.0": { "cache_read_input_token_cost": 4e-09, "cache_read_input_token_cost_above_200k_tokens": 1.2e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_above_200k_tokens": 3e-07, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_above_200k_tokens": 1.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://dev.meta.ai/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-spark-1.1": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-spark-1.2": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-spark-1.2-contributor": { "cache_read_input_token_cost": 2e-09, "input_cost_per_token": 1e-07, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-spark-1.3": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-spark-1.3-contributor": { "cache_read_input_token_cost": 2e-09, "input_cost_per_token": 1e-07, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta/muse-voice-transcribe-1.0": { "input_cost_per_second": 0.00005, "litellm_provider": "meta", "mode": "audio_transcription", "source": "https://dev.meta.ai/docs/speech-to-text", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "meta/muse-wonder-1.0": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 4e-06, "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://dev.meta.ai/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "meta_llama/Llama-3.3-8B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_tool_choice": true }, "minimax.minimax-m2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": false }, "minimax.minimax-m2.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "minimax/speech-02-hd": { "input_cost_per_character": 0.0001, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "minimax/speech-02-turbo": { "input_cost_per_character": 6e-05, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "minimax/speech-2.6-hd": { "input_cost_per_character": 0.0001, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "minimax/speech-2.6-turbo": { "input_cost_per_character": 6e-05, "litellm_provider": "minimax", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "minimax/MiniMax-M2.1": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 3e-08, "cache_creation_input_token_cost": 3.75e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "minimax/MiniMax-M2.1-lightning": { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.4e-06, "cache_read_input_token_cost": 3e-08, "cache_creation_input_token_cost": 3.75e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "minimax/MiniMax-M2.5": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 3e-08, "cache_creation_input_token_cost": 3.75e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "minimax/MiniMax-M2.5-lightning": { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.4e-06, "cache_read_input_token_cost": 3e-08, "cache_creation_input_token_cost": 3.75e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 }, "minimax/MiniMax-M2": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 3e-08, "cache_creation_input_token_cost": 3.75e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 200000, "max_output_tokens": 8192 }, "minimax/MiniMax-M3": { "input_cost_per_token": 3e-07, "input_cost_per_token_above_512k_tokens": 6e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_512k_tokens": 2.4e-06, "cache_read_input_token_cost": 6e-08, "cache_read_input_token_cost_above_512k_tokens": 1.2e-07, "litellm_provider": "minimax", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true, "max_input_tokens": 1000000, "max_output_tokens": 128000 }, "minimax/MiniMax-M3.1-Flash": { "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 1.5e-08, "litellm_provider": "minimax", "mode": "chat", "source": "https://platform.minimax.io/docs/guides/pricing-paygo", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "supports_vision": true, "max_input_tokens": 1000000 }, "minimax/minimax-latest": { "alias_of": "minimax/MiniMax-M3" }, "minimax/MiniMax-H3": { "litellm_provider": "minimax", "mode": "video_generation", "source": "https://platform.minimax.io/docs/guides/pricing-paygo", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "output_cost_per_second_2k": 0.13, "input_cost_per_image": 0.04, "provider_specific_entry": { "minimax_free_input_images": 5 }, "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "metadata": { "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." } }, "minimax/MiniMax-H3-Max": { "litellm_provider": "minimax", "mode": "video_generation", "source": "https://platform.minimax.io/docs/guides/pricing-paygo", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "input_cost_per_image": 0.074, "provider_specific_entry": { "minimax_free_input_images": 2 }, "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "video" ], "supported_endpoints": [ "/v1/videos" ], "metadata": { "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." } }, "mistral.devstral-2-123b": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, "input_cost_per_token_flex": 2e-07, "input_cost_per_token_priority": 7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.63e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, "output_cost_per_token_flex": 1e-07, "output_cost_per_token_priority": 3.5e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": true }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, "output_cost_per_token_batches": 5e-08, "output_cost_per_token_flex": 5e-08, "output_cost_per_token_priority": 1.7e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": true }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, "output_cost_per_token_batches": 7e-08, "output_cost_per_token_flex": 7e-08, "output_cost_per_token_priority": 2.6e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": true }, "mistral.mistral-7b-instruct-v0:2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": true }, "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.63e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": true }, "mistral.mistral-small-2402-v1:0": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md", "supports_function_calling": true }, "mistral.mixtral-8x7b-instruct-v0:1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "mistral.voxtral-mini-3b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4e-08, "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, "output_cost_per_token_batches": 2e-08, "output_cost_per_token_flex": 2e-08, "output_cost_per_token_priority": 7e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "mistral.voxtral-small-24b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_flex": 1.5e-07, "output_cost_per_token_priority": 5.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/ap-southeast-2/mistral.voxtral-mini-3b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 4.12e-08, "input_cost_per_token_batches": 2.06e-08, "input_cost_per_token_flex": 2.06e-08, "input_cost_per_token_priority": 7.21e-08, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.12e-08, "output_cost_per_token_batches": 2.06e-08, "output_cost_per_token_flex": 2.06e-08, "output_cost_per_token_priority": 7.21e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/ap-southeast-2/mistral.voxtral-small-24b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.03e-07, "input_cost_per_token_batches": 5.15e-08, "input_cost_per_token_flex": 5.15e-08, "input_cost_per_token_priority": 1.8025e-07, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.09e-07, "output_cost_per_token_batches": 1.545e-07, "output_cost_per_token_flex": 1.545e-07, "output_cost_per_token_priority": 5.4075e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-southeast-2/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/ap-northeast-1/mistral.voxtral-mini-3b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 5e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 9e-08, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-08, "output_cost_per_token_batches": 3e-08, "output_cost_per_token_flex": 3e-08, "output_cost_per_token_priority": 9e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/ap-northeast-1/mistral.voxtral-small-24b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.2e-07, "input_cost_per_token_batches": 6e-08, "input_cost_per_token_flex": 6e-08, "input_cost_per_token_priority": 2.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "output_cost_per_token_flex": 1.8e-07, "output_cost_per_token_priority": 6.3e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/eu-west-2/mistral.voxtral-mini-3b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-08, "output_cost_per_token_batches": 3e-08, "output_cost_per_token_flex": 3e-08, "output_cost_per_token_priority": 1.1e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "bedrock/eu-west-2/mistral.voxtral-small-24b-2507": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "input_cost_per_token_batches": 8e-08, "input_cost_per_token_flex": 8e-08, "input_cost_per_token_priority": 2.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.7e-07, "output_cost_per_token_batches": 2.3e-07, "output_cost_per_token_flex": 2.3e-07, "output_cost_per_token_priority": 8.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/eu-west-2/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "mistral/codestral-2508": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-latest": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-mamba-latest": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true }, "mistral/devstral-small-latest": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/devstral-latest": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/devstral-medium-latest": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/ministral-14b-2512": { "input_cost_per_token": 2e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-14b-latest": { "input_cost_per_token": 2e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 2e-08 }, "mistral/ministral-3b-2512": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1e-08 }, "mistral/ministral-3b-latest": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1e-08 }, "mistral/mistral-embed-2312": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, "mode": "embedding", "source": "https://docs.mistral.ai/models/mistral-embed-23-12" }, "mistral/mistral-medium-3": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/voxtral-mini-transcribe-realtime-latest": { "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-tts-latest": { "input_cost_per_character": 1.6e-05, "litellm_provider": "mistral", "mode": "audio_speech", "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": true }, "mistral/voxtral-mini-transcribe-3": { "input_cost_per_second": 5.83333e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-3-0": { "input_cost_per_second": 5.83333e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-small-transcribe-3": { "input_cost_per_second": 6.66667e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-small-transcribe-3-0": { "input_cost_per_second": 6.66667e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-small-transcribe-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-realtime-3": { "input_cost_per_second": 0.000133333, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-realtime-3-0": { "input_cost_per_second": 0.000133333, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-tts-3": { "input_cost_per_character": 1.3e-05, "litellm_provider": "mistral", "mode": "audio_speech", "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": true }, "mistral/voxtral-mini-tts-3-0": { "input_cost_per_character": 1.3e-05, "litellm_provider": "mistral", "mode": "audio_speech", "source": "https://docs.mistral.ai/models/voxtral-mini-tts-3-0", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": true }, "mistral/voxtral-small-2507": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", "supports_audio_input": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/voxtral-small-latest": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", "supports_audio_input": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "deprecation_date": "2026-10-31", "deprecation_source": "https://docs.mistral.ai/getting-started/models/models_overview", "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/deepseek-v4-1-flash-1017": { "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://docs.mistral.ai/models/deepseek-v4-flash-1017", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/zai-glm-5-3": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-3", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/zai-glm-5-3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-3-flash", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/zai-glm-5": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-3", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/zai-glm-latest": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-3", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, "annotation_cost_per_page": 0.005, "annotation_cost_per_page_batches": 0.0025, "mode": "ocr", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4-0": { "deprecation_date": "2026-09-30", "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, "annotation_cost_per_page": 0.005, "annotation_cost_per_page_batches": 0.0025, "mode": "ocr", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4-1": { "annotation_cost_per_page": 0.005, "annotation_cost_per_page_batches": 0.0025, "litellm_provider": "mistral", "mode": "ocr", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ] }, "mistral/mistral-ocr-2512": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, "ocr_cost_per_page_batches": 0.001, "annotation_cost_per_page": 0.003, "annotation_cost_per_page_batches": 0.0015, "mode": "ocr", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/magistral-medium-latest": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/magistral-small-latest": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed-2505": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, "mode": "embedding" }, "mistral/mistral-large-4": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 7e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.1e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/mistral-large-4-0", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-large-4-0": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 7e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.1e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/mistral-large-4-0", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-large-latest": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-large-3": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-large-2512": { "deprecation_date": "2027-04-30", "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-medium": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-medium-2604": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-medium-latest": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-medium-3-5": { "deprecation_date": "2027-04-30", "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-small": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "reasoning_effort_levels": [ "none", "high" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/mistral-small-latest": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-3-3b-2512": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-3-8b-2512": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-3-14b-2512": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-8b-2512": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-8b-latest": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-tiny": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/open-mistral-nemo": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/pixtral-large-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "moonshot.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_priority": 4.38e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": false }, "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true }, "moonshot/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, "deprecation_date": "2026-08-31", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "moonshot/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "moonshot/kimi-k3.1-pro": { "cache_creation_input_token_cost": 2e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://platform.kimi.ai/docs/pricing/chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "moonshot/kimi-k3.1-pro-highspeed": { "cache_creation_input_token_cost": 0.000004, "cache_creation_input_token_cost_above_1hr": 0.000008, "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000004, "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 0.00002, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://platform.kimi.ai/docs/pricing/chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "moonshot/kimi-k3": { "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "moonshot/kimi-latest": { "alias_of": "moonshot/kimi-k3" }, "moonshot/moonshot-v1-128k": { "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-vision-preview": { "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "moonshot/moonshot-v1-32k": { "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-vision-preview": { "deprecation_date": "2026-08-31", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "moonshot/moonshot-v1-8k": { "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-vision-preview": { "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "moonshot/moonshot-v1-auto": { "deprecation_date": "2026-08-31", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "morph/morph-kimik3": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.4e-05, "cache_read_input_token_cost": 2.9e-07, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-kimik3-fast": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 6e-06, "output_cost_per_token": 2.25e-05, "cache_read_input_token_cost": 6e-07, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-glm53-744b": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.19e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 1.955e-07, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing" }, "morph/morph-glm53flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, "output_cost_per_token": 7e-07, "cache_read_input_token_cost": 4e-08, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-dsv41flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 8e-07, "cache_read_input_token_cost": 8e-09, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-dsv41flash-1017": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 8e-07, "cache_read_input_token_cost": 8e-09, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-dsv41flash-abliterated": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 3e-08, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing", "supports_vision": true }, "morph/morph-dsv4flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.41953125e-07, "output_cost_per_token": 3.99625e-07, "cache_read_input_token_cost": 3.59375e-08, "litellm_provider": "morph", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.morphllm.com/pricing" }, "morph/morph-v3-fast": { "input_cost_per_token": 8e-07, "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": false }, "morph/morph-v3-large": { "input_cost_per_token": 9e-07, "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.9e-06, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_vision": false }, "multimodalembedding": { "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "supports_embedding_image_input": true }, "multimodalembedding@001": { "deprecation_date": "2027-04-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "supports_embedding_image_input": true }, "nscale/Qwen/QwQ-32B": { "input_cost_per_token": 1.8e-07, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { "input_cost_per_token": 1e-08, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { "input_cost_per_token": 1e-08, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/black-forest-labs/FLUX.1-schnell": { "input_cost_per_pixel": 1.3e-09, "litellm_provider": "nscale", "mode": "image_generation", "output_cost_per_pixel": 0.0, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supported_endpoints": [ "/v1/images/generations" ] }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 3.75e-07, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 3.75e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { "input_cost_per_token": 2.5e-08, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2.5e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { "input_cost_per_token": 9e-08, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 9e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { "input_cost_per_token": 7e-08, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "input_cost_per_token": 1.5e-07, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { "input_cost_per_token": 2e-07, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-3.1-8B-Instruct": { "input_cost_per_token": 3e-08, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-3.3-70B-Instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "input_cost_per_token": 9e-08, "litellm_provider": "nscale", "mode": "chat", "output_cost_per_token": 2.9e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { "input_cost_per_token": 6e-07, "litellm_provider": "nscale", "metadata": { "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." }, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" }, "nscale/stabilityai/stable-diffusion-xl-base-1.0": { "input_cost_per_pixel": 3e-09, "litellm_provider": "nscale", "mode": "image_generation", "output_cost_per_pixel": 0.0, "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", "supported_endpoints": [ "/v1/images/generations" ] }, "nebius/deepseek-ai/DeepSeek-R1": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 8e-07, "output_cost_per_token": 2.4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-0528": { "max_input_tokens": 164000, "max_output_tokens": 164000, "input_cost_per_token": 8e-07, "output_cost_per_token": 2.4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 7.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3-0324": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { "max_input_tokens": 110000, "max_output_tokens": 110000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 4e-08 }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/meta-llama/Llama-Guard-3-8B": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, "output_cost_per_token": 6e-08, "litellm_provider": "nebius", "mode": "chat", "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, "output_cost_per_token": 6e-08, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/mistralai/Mistral-Nemo-Instruct-2407": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 4e-08, "output_cost_per_token": 1.2e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-235B-A22B": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-14B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, "output_cost_per_token": 2.4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-4B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, "output_cost_per_token": 2.4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/QwQ-32B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 4.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-72B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-32B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-08, "output_cost_per_token": 2e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-Coder-7B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 3e-08, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 7.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2-VL-7B-Instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 6e-08, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V4-Flash": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" }, "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1e-08 }, "nebius/deepseek-ai/DeepSeek-V4-Pro": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.75e-06, "output_cost_per_token": 3.5e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.4e-07 }, "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { "input_cost_per_token": 1.32e-06, "litellm_provider": "nebius", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, "cache_read_input_token_cost": 4e-08 }, "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { "input_cost_per_token": 3e-07, "litellm_provider": "nebius", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "cache_read_input_token_cost": 1e-08 }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_input_tokens": 196608, "max_output_tokens": 196608, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" }, "nebius/MiniMaxAI/MiniMax-M3": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 6e-08 }, "nebius/moonshotai/Kimi-K2.6": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.6e-07 }, "nebius/moonshotai/Kimi-K2.7-Code": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.5e-07 }, "nebius/moonshotai/Kimi-K3.1-Pro": { "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "nebius/moonshotai/Kimi-K3": { "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 3e-07 }, "nebius/NousResearch/Hermes-4-405B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 2e-07 }, "nebius/NousResearch/Hermes-4-70B": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" }, "nebius/nvidia/Cosmos3-Super-Reasoner": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" }, "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "nebius", "mode": "chat", "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" }, "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, "output_cost_per_token": 2.4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.2e-08 }, "nebius/nvidia/Nemotron-3-Nano-Omni": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, "output_cost_per_token": 2.4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" }, "nebius/nvidia/nemotron-3-super-120b-a12b": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, "output_cost_per_token": 9e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 6e-08 }, "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.2e-07 }, "nebius/nvidia/Nemotron-3_5-Lightning": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 6e-08, "output_cost_per_token": 2.4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 3e-08 }, "nebius/openai/gpt-oss-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1e-07 }, "nebius/openbmb/MiniCPM-V-4_5": { "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 6.58e-07, "output_cost_per_token": 1.11e-06, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.3e-07 }, "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 5e-08 }, "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1e-07 }, "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" }, "nebius/Qwen/Qwen3.5-397B-A17B": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.2e-07 }, "nebius/Qwen/Qwen3.8-27B": { "input_cost_per_token": 4.5e-07, "litellm_provider": "nebius", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, "cache_read_input_token_cost": 1e-07 }, "nebius/zai-org/GLM-5.1": { "max_input_tokens": 202752, "max_output_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 2.6e-07 }, "nebius/zai-org/GLM-5.2": { "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "cache_read_input_token_cost": 1.4e-07 }, "nebius/zai-org/GLM-5.3": { "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", "max_input_tokens": 1048576, "max_output_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, "cache_read_input_token_cost": 2.6e-07 }, "nebius/zai-org/GLM-5.3-Flash": { "max_input_tokens": 1048576, "max_output_tokens": 1024000, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_vision": true, "cache_read_input_token_cost": 3e-08 }, "nebius/BAAI/bge-en-icl": { "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices" }, "nebius/BAAI/bge-multilingual-gemma2": { "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices" }, "nebius/intfloat/e5-mistral-7b-instruct": { "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-Embedding-8B": { "max_input_tokens": 40960, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" }, "nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, "output_cost_per_token_batches": 1.2e-07, "output_cost_per_token_flex": 1.2e-07, "output_cost_per_token_priority": 4e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-07, "output_cost_per_token_batches": 1.2e-07, "output_cost_per_token_flex": 1.2e-07, "output_cost_per_token_priority": 4.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": false }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, "output_cost_per_token_batches": 3.25e-07, "output_cost_per_token_flex": 3.25e-07, "output_cost_per_token_priority": 1.1375e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "o1": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "o1-pro": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "o1-pro-2025-03-19": { "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_native_streaming": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "o3": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "deprecation_date": "2026-12-11", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_flex": 4e-06, "output_cost_per_token_priority": 1.4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol" }, "o3-deep-research-2025-06-26": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "supports_vision": true, "supports_pdf_input": true }, "o3-2025-04-16": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_flex": 4e-06, "output_cost_per_token_priority": 1.4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "standard" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o3-mini": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "o3-pro": { "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o3-pro-2025-06-10": { "deprecation_date": "2026-12-11", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 4e-05, "reasoning_contexts": [ "auto", "current_turn" ], "reasoning_modes": [ "pro" ], "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o4-mini": { "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_flex": 1.38e-07, "cache_read_input_token_cost_priority": 5e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "input_cost_per_token_flex": 5.5e-07, "input_cost_per_token_priority": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "output_cost_per_token_flex": 2.2e-06, "output_cost_per_token_priority": 8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o4-mini-deep-research": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "supports_vision": true, "supports_pdf_input": true, "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol" }, "o4-mini-deep-research-2025-06-26": { "deprecation_date": "2026-07-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-sol", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-06, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": false, "supports_native_streaming": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": false, "supports_vision": true, "supports_pdf_input": true }, "o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_flex": 1.38e-07, "cache_read_input_token_cost_priority": 5e-07, "deprecation_date": "2026-10-23", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-5.6-terra", "input_cost_per_token": 1.1e-06, "input_cost_per_token_batches": 5.5e-07, "input_cost_per_token_flex": 5.5e-07, "input_cost_per_token_priority": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "fedramp_uplift_multiplier": 1.1, "output_cost_per_token_batches": 2.2e-06, "output_cost_per_token_flex": 2.2e-06, "output_cost_per_token_priority": 8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "oci/meta.llama-3.1-8b-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/meta.llama-3.1-70b-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/meta.llama-3.1-405b-instruct": { "input_cost_per_token": 1.068e-05, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.068e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/meta.llama-3.2-90b-vision-instruct": { "input_cost_per_token": 2e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true, "supports_vision": true }, "oci/meta.llama-3.3-70b-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true, "supports_vision": true }, "oci/meta.llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 10485760, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/xai.grok-3": { "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/xai.grok-3-fast": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/xai.grok-3-mini": { "input_cost_per_token": 3e-07, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/xai.grok-3-mini-fast": { "input_cost_per_token": 6e-07, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/xai.grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/cohere.command-latest": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/cohere.command-a-03-2025": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/cohere.command-plus-latest": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true }, "oci/google.gemini-2.5-flash": { "input_cost_per_token": 1.5e-07, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, "supports_image_size": false, "supports_reasoning": true, "supports_system_messages": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_video_input": true }, "oci/google.gemini-2.5-pro": { "input_cost_per_token": 1.25e-06, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_system_messages": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_video_input": true }, "oci/google.gemini-2.5-flash-lite": { "input_cost_per_token": 7.5e-08, "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, "supports_image_size": false, "supports_reasoning": false, "supports_system_messages": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_video_input": true }, "oci/cohere.command-a-vision": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true, "supports_vision": true }, "oci/cohere.command-a-reasoning": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": false, "supports_response_schema": false, "supports_native_streaming": true }, "oci/cohere.embed-multilingual-image-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_embedding_image_input": true, "supports_vision": true }, "oci/cohere.command-a-reasoning-08-2025": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/cohere.command-a-vision-07-2025": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true }, "oci/cohere.command-a-translate-08-2025": { "input_cost_per_token": 9e-08, "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-08, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": false, "supports_response_schema": false }, "oci/cohere.command-r-08-2024": { "input_cost_per_token": 1.5e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/cohere.command-r-plus-08-2024": { "input_cost_per_token": 1.56e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/meta.llama-3.2-11b-vision-instruct": { "input_cost_per_token": 2e-06, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true }, "oci/meta.llama-3.3-70b-instruct-fp8-dynamic": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/xai.grok-4-fast": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/xai.grok-4.1-fast": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/xai.grok-4.20": { "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/xai.grok-4.20-multi-agent": { "input_cost_per_token": 3e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/xai.grok-4.20-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "oci", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true }, "oci/xai.grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "oci", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_reasoning": true }, "oci/xai.grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "oci", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true }, "oci/xai.grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "oci", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_reasoning": true }, "oci/xai.grok-code-fast-1": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false }, "oci/openai.gpt-5": { "input_cost_per_token": 1.25e-06, "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "oci/openai.gpt-5-mini": { "input_cost_per_token": 2.5e-07, "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "oci/openai.gpt-5-nano": { "input_cost_per_token": 5e-08, "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "oci/openai.gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true }, "oci/openai.gpt-oss-20b": { "input_cost_per_token": 7e-08, "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_native_streaming": true, "supports_reasoning": true }, "oci/cohere.embed-english-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "oci/cohere.embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "oci/cohere.embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "oci/cohere.embed-multilingual-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" }, "oci/cohere.embed-english-image-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true }, "oci/cohere.embed-english-light-image-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true }, "oci/cohere.embed-multilingual-light-image-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true }, "oci/cohere.embed-v4.0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true }, "ollama/codegeex4": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": false }, "ollama/codegemma": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0 }, "ollama/codellama": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "ollama/deepseek-coder-v2-base": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/deepseek-coder-v2-instruct": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/deepseek-coder-v2-lite-base": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/deepseek-coder-v2-lite-instruct": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/deepseek-v3.1:671b-cloud": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/gpt-oss:120b-cloud": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/gpt-oss:20b-cloud": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/internlm2_5-20b-chat": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/llama2": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama2-uncensored": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "ollama/llama2:13b": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama2:70b": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama2:7b": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama3": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama3.1": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/llama3:70b": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/llama3:8b": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, "ollama/mistral": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/mistral-7B-Instruct-v0.1": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/mistral-7B-Instruct-v0.2": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/mistral-large-instruct-2407": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/mixtral-8x22B-Instruct-v0.1": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/mixtral-8x7B-Instruct-v0.1": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/orca-mini": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "ollama/qwen3-coder:480b-cloud": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true }, "ollama/vicuna": { "input_cost_per_token": 0.0, "litellm_provider": "ollama", "max_input_tokens": 2048, "max_output_tokens": 2048, "mode": "completion", "output_cost_per_token": 0.0 }, "omni-moderation-2024-09-26": { "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, "omni-moderation-latest": { "input_cost_per_token": 0.0, "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { "supports_vision": false, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { "supports_vision": false, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 7e-08, "input_cost_per_token_batches": 3.5e-08, "input_cost_per_token_flex": 3.5e-08, "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_flex": 1.5e-07, "output_cost_per_token_priority": 5.25e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, "output_cost_per_token_flex": 1e-07, "output_cost_per_token_priority": 3.5e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/Llama-3.1-8B-Instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/Meta-Llama-3_1-70B-Instruct": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": false, "supports_tool_choice": false }, "ovhcloud/Meta-Llama-3_3-70B-Instruct": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/Mistral-7B-Instruct-v0.3": { "input_cost_per_token": 1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 127000, "max_output_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/Mistral-Nemo-Instruct-2407": { "input_cost_per_token": 1.3e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 118000, "max_output_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { "input_cost_per_token": 9e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { "input_cost_per_token": 6.3e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "ovhcloud/Qwen2.5-Coder-32B-Instruct": { "input_cost_per_token": 8.7e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "ovhcloud/Qwen2.5-VL-72B-Instruct": { "input_cost_per_token": 9.1e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "ovhcloud/Qwen3-32B": { "input_cost_per_token": 8e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "ovhcloud/gpt-oss-120b": { "input_cost_per_token": 8e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": false }, "ovhcloud/gpt-oss-20b": { "input_cost_per_token": 4e-08, "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": false }, "ovhcloud/llava-v1.6-mistral-7b-hf": { "input_cost_per_token": 2.9e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "ovhcloud/mamba-codestral-7B-v0.1": { "input_cost_per_token": 1.9e-07, "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false }, "parallel_ai/decision": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "parallel_ai", "max_input_tokens": 32000, "mode": "evaluation", "source": "https://docs.parallel.ai/getting-started/pricing#decisions-api", "supported_endpoints": [ "/v1/decisions", "/v1/systemone" ] }, "parallel_ai/search": { "input_cost_per_query": 0.005, "litellm_provider": "parallel_ai", "mode": "search" }, "parallel_ai/search-fast": { "input_cost_per_query": 0.001, "litellm_provider": "parallel_ai", "mode": "search" }, "parallel_ai/search-pro": { "input_cost_per_query": 0.005, "litellm_provider": "parallel_ai", "mode": "search" }, "parallel_ai/search-turbo": { "input_cost_per_query": 0.001, "litellm_provider": "parallel_ai", "mode": "search" }, "perplexity/codellama-34b-instruct": { "input_cost_per_token": 3.5e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06 }, "perplexity/codellama-70b-instruct": { "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-06 }, "perplexity/llama-2-70b-chat": { "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, "perplexity/llama-3.1-70b-instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06 }, "perplexity/llama-3.1-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07 }, "perplexity/mistral-7b-instruct": { "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "perplexity/mixtral-8x7b-instruct": { "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "perplexity/pplx-70b-chat": { "input_cost_per_token": 7e-07, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, "perplexity/pplx-70b-online": { "input_cost_per_request": 0.005, "input_cost_per_token": 0.0, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, "perplexity/pplx-7b-chat": { "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "perplexity/pplx-7b-online": { "input_cost_per_request": 0.005, "input_cost_per_token": 0.0, "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "perplexity/pplx-decider-v1-27b": { "input_cost_per_token": 2e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/api-reference/decisions-post" }, "perplexity/pplx-decider-v1.1-27b": { "input_cost_per_token": 2e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/getting-started/pricing" }, "perplexity/pplx-decider-v1.2": { "input_cost_per_token": 2e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/decisions/quickstart" }, "perplexity/pplx-decider-latest": { "input_cost_per_token": 2e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/decisions/quickstart" }, "perplexity/pplx-decider-flash-v1.2": { "input_cost_per_token": 1e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/decisions/quickstart" }, "perplexity/pplx-decider-flash-latest": { "input_cost_per_token": 1e-08, "litellm_provider": "perplexity", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.perplexity.ai/docs/decisions/quickstart" }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-06, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_web_search": true }, "perplexity/sonar-deep-research": { "citation_cost_per_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_web_search": true }, "perplexity/sonar-medium-chat": { "input_cost_per_token": 6e-07, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06 }, "perplexity/sonar-medium-online": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, "mode": "chat", "output_cost_per_token": 1.8e-06 }, "perplexity/sonar-pro": { "input_cost_per_token": 3e-06, "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_web_search": true }, "perplexity/sonar-reasoning": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_reasoning": true, "supports_web_search": true }, "perplexity/sonar-reasoning-pro": { "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_reasoning": true, "supports_web_search": true }, "perplexity/sonar-small-chat": { "input_cost_per_token": 7e-08, "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "perplexity/sonar-small-online": { "input_cost_per_request": 0.005, "input_cost_per_token": 0, "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-07 }, "publicai/swiss-ai/apertus-8b-instruct": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": false, "supports_tool_choice": false }, "publicai/swiss-ai/apertus-70b-instruct": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": false, "supports_tool_choice": false }, "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true }, "publicai/BSC-LT/salamandra-7b-instruct-tools-16k": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true }, "publicai/BSC-LT/ALIA-40b-instruct_Q8_0": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true }, "publicai/allenai/Olmo-3-7B-Instruct": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true }, "perplexity/preset/fast-search": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true }, "perplexity/preset/pro-search": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true }, "perplexity/preset/deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true }, "perplexity/preset/advanced-deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true }, "perplexity/openai/gpt-5.2": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": true, "supports_function_calling": true, "input_cost_per_token": 1.75e-06, "output_cost_per_token": 1.4e-05, "cache_read_input_token_cost": 1.75e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.25e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 2.5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_output_config": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-7": { "supports_adaptive_thinking": true, "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_output_config": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_output_config": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "cache_read_input_token_cost": 1e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3-pro-preview": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "perplexity/google/gemini-3-flash-preview": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-2.5-pro": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "perplexity/google/gemini-2.5-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "supports_image_size": false }, "perplexity/xai/grok-4-1-fast-non-reasoning": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "perplexity/perplexity/sonar": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 6.25e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.3e-07, "litellm_provider": "perplexity", "mode": "responses", "output_cost_per_token": 2.6e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "supports_function_calling": true }, "perplexity/perplexity/deepseek-v4-pro-0813": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 1.32e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/glm-5.2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "perplexity", "mode": "responses", "output_cost_per_token": 4.4e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "supports_function_calling": true }, "perplexity/perplexity/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "perplexity", "mode": "responses", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "supports_function_calling": true }, "perplexity/perplexity/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "perplexity", "mode": "responses", "output_cost_per_token": 4e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true }, "perplexity/pplx-embed-v1-0.6b": { "input_cost_per_token": 4e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "perplexity/pplx-embed-v1-4b": { "input_cost_per_token": 3e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true }, "publicai/allenai/Olmo-3-7B-Think": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true }, "publicai/allenai/Olmo-3-32B-Think": { "input_cost_per_token": 0.0, "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, "input_cost_per_token_flex": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "input_cost_per_token_batches": 1.1e-07, "output_cost_per_token_batches": 4.4e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" }, "qwen.qwen3-coder-30b-a3b-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true }, "qwen.qwen3-32b-v1:0": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_flex": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true }, "qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_vision": false }, "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.54e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "output_cost_per_token_batches": 7.1e-07, "output_cost_per_token_flex": 7.1e-07, "output_cost_per_token_priority": 2.47e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.545e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "output_cost_per_token_flex": 7.1e-07, "output_cost_per_token_priority": 2.47e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 2.3e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, "output_cost_per_token_flex": 9.3e-07, "output_cost_per_token_priority": 3.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "output_cost_per_token_flex": 7.2e-07, "output_cost_per_token_priority": 2.54e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, "input_cost_per_token_batches": 2.6e-07, "input_cost_per_token_priority": 9.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, "output_cost_per_token_batches": 1.33e-06, "output_cost_per_token_priority": 4.66e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true, "supports_native_structured_output": true, "supports_response_schema": false }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, "output_cost_per_token_flex": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "reducto/parse-legacy": { "litellm_provider": "reducto", "mode": "ocr", "ocr_cost_per_credit": 0.015, "source": "https://reducto.ai/pricing", "supported_endpoints": [ "/v1/ocr" ] }, "reducto/parse-v3": { "litellm_provider": "reducto", "mode": "ocr", "ocr_cost_per_credit": 0.015, "source": "https://reducto.ai/pricing", "supported_endpoints": [ "/v1/ocr" ] }, "recraft/recraftv2": { "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.022, "source": "https://www.recraft.ai/docs#pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "recraft/recraftv3": { "litellm_provider": "recraft", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://www.recraft.ai/docs#pricing", "supported_endpoints": [ "/v1/images/generations" ] }, "replicate/meta/llama-2-13b": { "input_cost_per_token": 1e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://replicate.com/meta/llama-2-13b", "supports_tool_choice": true }, "replicate/meta/llama-2-13b-chat": { "input_cost_per_token": 1e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://replicate.com/meta/llama-2-13b-chat", "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-70b": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "source": "https://replicate.com/meta/llama-2-70b", "supports_tool_choice": true }, "replicate/meta/llama-2-70b-chat": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "source": "https://replicate.com/meta/llama-2-70b-chat", "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-2-7b": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/meta/llama-2-7b", "supports_tool_choice": true }, "replicate/meta/llama-2-7b-chat": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/meta/llama-2-7b-chat", "supports_system_messages": true, "supports_tool_choice": true }, "replicate/meta/llama-3-70b": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true }, "replicate/meta/llama-3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true }, "replicate/meta/llama-3-8b": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true }, "replicate/meta/llama-3-8b-instruct": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true }, "replicate/mistralai/mistral-7b-instruct-v0.2": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true }, "replicate/mistralai/mistral-7b-v0.1": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/mistralai/mistral-7b-v0.1", "supports_tool_choice": true }, "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { "input_cost_per_token": 3e-07, "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "supports_tool_choice": true }, "replicate/openai/gpt-5": { "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-5", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true }, "replicate/openai/gpt-oss-20b": { "input_cost_per_token": 9e-08, "output_cost_per_token": 3.6e-07, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-oss-20b", "supports_function_calling": true, "supports_system_messages": true }, "replicate/anthropic/claude-4.5-haiku": { "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 4096, "source": "https://replicate.com/anthropic/claude-4.5-haiku" }, "replicate/ibm-granite/granite-3.3-8b-instruct": { "input_cost_per_token": 3e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/ibm-granite/granite-3.3-8b-instruct", "supports_function_calling": true, "supports_system_messages": true }, "replicate/openai/gpt-4o": { "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-4o", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_audio_input": true, "supports_audio_output": true }, "replicate/openai/o4-mini": { "input_cost_per_token": 1e-06, "output_cost_per_token": 4e-06, "output_cost_per_reasoning_token": 4e-06, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true }, "replicate/openai/o1-mini": { "input_cost_per_token": 1.1e-06, "output_cost_per_token": 4.4e-06, "output_cost_per_reasoning_token": 4.4e-06, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true }, "replicate/openai/o1": { "input_cost_per_token": 1.5e-05, "output_cost_per_token": 6e-05, "output_cost_per_reasoning_token": 6e-05, "litellm_provider": "replicate", "mode": "chat", "supports_reasoning": true, "supports_system_messages": true }, "replicate/openai/gpt-4o-mini": { "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-4o-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true }, "replicate/qwen/qwen3-235b-a22b-instruct-2507": { "input_cost_per_token": 2.64e-07, "output_cost_per_token": 1.06e-06, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/qwen/qwen3-235b-a22b-instruct-2507", "supports_function_calling": true, "supports_system_messages": true }, "replicate/anthropic/claude-4-sonnet": { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 1024 }, "replicate/deepseek-ai/deepseek-v3": { "input_cost_per_token": 1.45e-06, "output_cost_per_token": 1.45e-06, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, "source": "https://replicate.com/deepseek-ai/deepseek-v3", "supports_function_calling": true, "supports_system_messages": true }, "replicate/anthropic/claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true }, "replicate/anthropic/claude-3.5-haiku": { "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true }, "replicate/anthropic/claude-3.5-sonnet": { "input_cost_per_token": 3.75e-06, "output_cost_per_token": 1.875e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true }, "replicate/google/gemini-3-pro": { "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_response_schema": false, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.8e-05, "source": "https://replicate.com/google/gemini-3-pro", "supports_audio_input": true, "supports_reasoning": true, "supports_video_input": true }, "replicate/anthropic/claude-4.5-sonnet": { "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 1024, "source": "https://replicate.com/anthropic/claude-4.5-sonnet" }, "replicate/openai/gpt-4.1": { "input_cost_per_token": 2e-06, "output_cost_per_token": 8e-06, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-4.1", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true }, "replicate/openai/gpt-4.1-nano": { "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true }, "replicate/openai/gpt-4.1-mini": { "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-4.1-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true }, "replicate/openai/gpt-5-nano": { "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-5-nano", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5-mini": { "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-5-mini", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true }, "replicate/google/gemini-2.5-flash": { "input_cost_per_token": 3e-07, "output_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/google/gemini-2.5-flash", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_response_schema": false, "supports_image_size": false, "supports_reasoning": true, "supports_video_input": true }, "replicate/openai/gpt-oss-120b": { "input_cost_per_token": 1.8e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "replicate", "mode": "chat", "source": "https://replicate.com/openai/gpt-oss-120b", "supports_function_calling": true, "supports_system_messages": true }, "replicate/deepseek-ai/deepseek-v3.1": { "input_cost_per_token": 6.72e-07, "output_cost_per_token": 2.016e-06, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, "source": "https://replicate.com/deepseek-ai/deepseek-v3.1", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true }, "replicate/xai/grok-4": { "input_cost_per_token": 7.2e-06, "output_cost_per_token": 3.6e-05, "litellm_provider": "replicate", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true }, "replicate/deepseek-ai/deepseek-r1": { "input_cost_per_token": 3.75e-06, "output_cost_per_token": 1e-05, "output_cost_per_reasoning_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, "source": "https://replicate.com/deepseek-ai/deepseek-r1", "supports_reasoning": true, "supports_system_messages": true }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, "rerank-v3.5": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, "rerank-v4.0-fast": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" }, "rerank-v4.0-pro": { "input_cost_per_query": 0.0025, "input_cost_per_token": 0.0, "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" }, "rerank-v5.0-fast": { "input_cost_per_token": 2e-08, "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/blog/rerank-5" }, "rerank-v5.0-pro": { "input_cost_per_token": 5e-08, "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/blog/rerank-5" }, "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0.0 }, "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0.0 }, "nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "nvidia_nim", "mode": "rerank", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-13b": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-13b-f": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-70b": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-70b-b-f": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-7b": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, "sagemaker/meta-textgeneration-llama-2-7b-f": { "input_cost_per_token": 0.0, "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, "sambanova/MiniMax-M2.7": { "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", "max_input_tokens": 196608, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "sambanova/DeepSeek-R1": { "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Llama-4-Maverick-17B-128E-Instruct": { "input_cost_per_token": 6.3e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "sambanova/Meta-Llama-3.3-70B-Instruct": { "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 5.9e-07, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3.2": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gemma-4-31B-it": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.15e-06, "litellm_provider": "sambanova", "mode": "chat", "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "scx-ai/DeepSeek-V4.1-flash": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 375000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://scx.ai/models/deepseek-v4-1-flash", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "scx-ai/GLM-5.3": { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 9.8e-07, "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.08e-06, "source": "https://scx.ai/models/glm-5-3", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": false }, "scx-ai/Kimi-K3": { "cache_read_input_token_cost": 2.8e-07, "input_cost_per_token": 2.83e-06, "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.413e-05, "source": "https://scx.ai/models/kimi-k3", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": false }, "scx-ai/GLM-5.2": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 6.1e-07, "litellm_provider": "scx-ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-06, "source": "https://scx.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "scx-ai/Qwen3.8-Max": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.99e-06, "source": "https://scx.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "snowflake/claude-3-5-sonnet": { "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "supports_computer_use": true, "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true }, "snowflake/deepseek-r1": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "supports_reasoning": true, "supports_system_messages": true }, "snowflake/gemma-7b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-large": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-mini": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/jamba-instruct": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama2-70b-chat": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama3-70b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama3-8b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_system_messages": true }, "snowflake/llama3.1-70b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true }, "snowflake/llama3.1-8b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 2.4e-07, "output_cost_per_token": 2.4e-07, "supports_system_messages": true }, "snowflake/llama3.2-1b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama3.2-3b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/llama3.3-70b": { "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true }, "snowflake/mistral-7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_response_schema": true }, "snowflake/mixtral-8x7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/reka-core": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/reka-flash": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-arctic": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true }, "stability/sd3": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3-large": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3-large-turbo": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3-medium": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3.5-large": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.065, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3.5-large-turbo": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/sd3.5-medium": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.035, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/stable-image-ultra": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.08, "supported_endpoints": [ "/v1/images/generations" ] }, "stability/inpaint": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/outpaint": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.004, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/erase": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/search-and-replace": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/search-and-recolor": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/remove-background": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/replace-background-and-relight": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.008, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/sketch": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/structure": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/style": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.005, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/style-transfer": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.008, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/fast": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.002, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/conservative": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.04, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/creative": { "litellm_provider": "stability", "mode": "image_edit", "output_cost_per_image": 0.06, "supported_endpoints": [ "/v1/images/edits" ] }, "stability/stable-image-core": { "litellm_provider": "stability", "mode": "image_generation", "output_cost_per_image": 0.03, "supported_endpoints": [ "/v1/images/generations" ] }, "stability.sd3-5-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-conservative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.4 }, "us.stability.stable-conservative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.4, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 }, "us.stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 }, "us.stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 }, "us.stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, "us.stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 }, "us.stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08, "source": "https://aws.amazon.com/bedrock/pricing/" }, "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "linkup/search": { "input_cost_per_query": 0.00587, "litellm_provider": "linkup", "mode": "search" }, "linkup/search-deep": { "input_cost_per_query": 0.05867, "litellm_provider": "linkup", "mode": "search" }, "tavily/search": { "input_cost_per_query": 0.008, "litellm_provider": "tavily", "mode": "search" }, "tavily/search-advanced": { "input_cost_per_query": 0.016, "litellm_provider": "tavily", "mode": "search" }, "you_com/search": { "input_cost_per_query": 0.0, "litellm_provider": "you_com", "mode": "search" }, "text-completion-codestral/codestral-2405": { "deprecation_date": "2025-06-16", "deprecation_source": "https://docs.mistral.ai/getting-started/models/", "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-completion-codestral/codestral-latest": { "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-embedding-004": { "deprecation_date": "2027-04-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-005": { "deprecation_date": "2027-04-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-3-large": { "input_cost_per_token": 1.3e-07, "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, "output_vector_size": 3072, "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-3-small": { "input_cost_per_token": 2e-08, "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, "output_vector_size": 1536, "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-ada-002": { "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-ada-002-v2": { "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0 }, "text-embedding-large-exp-03-07": { "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-preview-0409": { "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "text-multilingual-embedding-002": { "deprecation_date": "2027-04-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-unicorn": { "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "text-unicorn@001": { "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "together-ai-21.1b-41b": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-07 }, "together-ai-4.1b-8b": { "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-07 }, "together-ai-41.1b-80b": { "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 9e-07 }, "together-ai-8.1b-21b": { "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_output_tokens": 1000, "max_input_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-07 }, "together-ai-81.1b-110b": { "input_cost_per_token": 1.8e-06, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.8e-06 }, "together-ai-embedding-151m-to-350m": { "input_cost_per_token": 1.6e-08, "litellm_provider": "together_ai", "mode": "embedding", "output_cost_per_token": 0.0 }, "together-ai-embedding-up-to-150m": { "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", "mode": "embedding", "output_cost_per_token": 0.0 }, "together_ai/BAAI/bge-base-en-v1.5": { "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", "max_input_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 768 }, "together-ai-up-to-4b": { "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1e-07 }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "input_cost_per_token": 3e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 32768, "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "deprecation_date": "2026-10-22", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/meta-models/Muse-Glimmer-30B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "metadata": { "successor": "together_ai/moonshotai/Kimi-K3" }, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, "max_output_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-11-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/MiniMaxAI/MiniMax-M3.1-Flash", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/MiniMaxAI/MiniMax-M3.1-Flash": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Prism-ML/Ternary-Bonsai-27B": { "input_cost_per_token": 0.0, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/Qwen/Qwen3.5-9B": { "input_cost_per_token": 1.7e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/Qwen/Qwen3.6-Plus": { "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { "input_cost_per_token": 3.2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-07, "deprecation_date": "2026-11-04", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, "max_output_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/Qwen/Qwen3.7-Max", "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-10-22", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-pro-latest": { "alias_of": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, "together_ai/meta-models/Muse-Glimmer-30B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/meta-models/Muse-Spark-Open-816B-A42B": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/kimi-latest": { "alias_of": "together_ai/moonshotai/Kimi-K3" }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-07, "deprecation_date": "2026-11-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/meta-models/Muse-Spark-Open-816B-A42B", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/zai-org/GLM-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/zai-org/GLM-5.3": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/glm-latest": { "alias_of": "together_ai/zai-org/GLM-5.3" }, "together_ai/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/glm-flash-latest": { "alias_of": "together_ai/zai-org/GLM-5.3-Flash" }, "tts-1": { "deprecation_date": "2027-01-06", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "tts-1-hd": { "deprecation_date": "2027-01-06", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "transcribe/StartTranscriptionJob": { "input_cost_per_second": 0.0001, "litellm_provider": "transcribe", "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://aws.amazon.com/transcribe/pricing/", "metadata": { "notes": "Amazon Transcribe standard batch transcription, billed per second of audio with no minimum. Same rate in every region of the AWS Price List offer file for transcribe (checked 2026-09-17)" } }, "aws_polly/standard": { "input_cost_per_character": 4e-06, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" }, "aws_polly/neural": { "input_cost_per_character": 1.6e-05, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" }, "aws_polly/long-form": { "input_cost_per_character": 0.0001, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" }, "aws_polly/generative": { "input_cost_per_character": 3e-05, "litellm_provider": "aws_polly", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ], "source": "https://aws.amazon.com/polly/pricing/" }, "us.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "output_cost_per_token_batches": 1.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "output_cost_per_token_batches": 7e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "input_cost_per_token_flex": 4e-07, "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, "output_cost_per_token_priority": 5.6e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, "supports_tool_choice": true }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 2048 }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2027-01-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-1-20250805-v1:0", "litellm_provider": "bedrock" } }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "deprecation_date": "2027-04-08", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "us.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "input_cost_per_token_above_200k_tokens": 7.2e-06, "output_cost_per_token_above_200k_tokens": 2.7e-05, "cache_creation_input_token_cost_above_200k_tokens": 9e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, "deprecation_date": "2027-04-27", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "us-gov.anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md", "token_count_model": { "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", "litellm_provider": "bedrock" } }, "us-gov.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us-gov.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" }, "input_cost_per_token_batches": 3e-06, "output_cost_per_token_batches": 1.5e-05 }, "us-gov.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6e-06, "cache_creation_input_token_cost_above_1hr": 9.6e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 4.8e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, "cache_creation_input_token_cost_above_1hr": 2.4e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1.2e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-fable-5-1", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "us-gov.nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true }, "us-gov.nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_vision": false }, "us-gov.nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "us-gov.openai.gpt-oss-20b-1:0": { "supports_vision": false, "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.openai.gpt-oss-120b-1:0": { "supports_vision": false, "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.xai.grok-4.6": { "supports_regex_lookaround": false, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-5-20251101-v1:0", "litellm_provider": "bedrock" } }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-5-20251101-v1:0", "litellm_provider": "bedrock" } }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-4-5-20251101-v1:0", "litellm_provider": "bedrock" } }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-14", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "us.anthropic.claude-sonnet-5", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-sonnet-4-20250514-v1:0", "litellm_provider": "bedrock" } }, "us.deepseek.r1-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false }, "us.deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "input_cost_per_token_batches": 3.1e-07, "input_cost_per_token_flex": 3.1e-07, "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "output_cost_per_token_batches": 9.25e-07, "output_cost_per_token_flex": 9.25e-07, "output_cost_per_token_priority": 3.2375e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "eu.deepseek.v3.2": { "input_cost_per_token": 7.4e-07, "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "mode": "chat", "output_cost_per_token": 2.22e-06, "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-8b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.2e-07, "output_cost_per_token_batches": 1.1e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-11b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { "deprecation_date": "2026-07-07", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-3-70b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-scout-17b-instruct-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 10000000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": false }, "us.mistral.pixtral-large-2502-v1:0": { "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, "v0/v0-1.0-md": { "input_cost_per_token": 3e-06, "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "v0/v0-1.5-lg": { "input_cost_per_token": 1.5e-05, "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "v0/v0-1.5-md": { "input_cost_per_token": 3e-06, "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "vercel_ai_gateway/alibaba/qwen-3-14b": { "input_cost_per_token": 8e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-07 }, "vercel_ai_gateway/alibaba/qwen-3-235b": { "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07 }, "vercel_ai_gateway/alibaba/qwen-3-30b": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07 }, "vercel_ai_gateway/alibaba/qwen-3-32b": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/alibaba/qwen3-coder": { "input_cost_per_token": 4e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/amazon/nova-lite": { "input_cost_per_token": 6e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_vision": true, "supports_function_calling": true, "supports_response_schema": true }, "vercel_ai_gateway/amazon/nova-micro": { "input_cost_per_token": 3.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, "supports_response_schema": true }, "vercel_ai_gateway/amazon/nova-pro": { "input_cost_per_token": 8e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_vision": true, "supports_function_calling": true, "supports_response_schema": true }, "vercel_ai_gateway/amazon/titan-embed-text-v2": { "input_cost_per_token": 2e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/anthropic/claude-3-haiku": { "cache_creation_input_token_cost": 3e-07, "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3-opus": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.5-haiku": { "cache_creation_input_token_cost": 1e-06, "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 8e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-4-opus": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-4-sonnet": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/anthropic/claude-3-5-sonnet": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vercel_ai_gateway/anthropic/claude-3-7-sonnet": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vercel_ai_gateway/anthropic/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-opus-4": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-opus-4.1": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-opus-4.5": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-opus-4.6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-sonnet-4": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-sonnet-4.5": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/cohere/command-a": { "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/cohere/command-r": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/cohere/command-r-plus": { "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/cohere/embed-v4.0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/deepseek/deepseek-r1": { "input_cost_per_token": 5.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_tool_choice": true }, "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 7.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/deepseek/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "supports_tool_choice": true }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_image_size": false, "cache_read_input_token_cost": 3e-08, "supports_reasoning": true, "supports_pdf_input": true, "supports_web_search": true, "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemini-2.5-pro": { "input_cost_per_token": 1.25e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 1.5e-05, "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "supports_reasoning": true, "supports_pdf_input": true, "supports_web_search": true, "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemini-embedding-001": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/google/gemma-2-9b": { "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/google/text-embedding-005": { "input_cost_per_token": 2.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/google/text-multilingual-embedding-002": { "input_cost_per_token": 2.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/inception/mercury-coder-small": { "input_cost_per_token": 2.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06 }, "vercel_ai_gateway/meta/llama-3-70b": { "input_cost_per_token": 5.9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-07, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3-8b": { "input_cost_per_token": 5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-08, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.1-70b": { "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.1-8b": { "input_cost_per_token": 5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-08, "supports_function_calling": true, "supports_response_schema": true }, "vercel_ai_gateway/meta/llama-3.2-11b": { "input_cost_per_token": 1.6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.2-1b": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07 }, "vercel_ai_gateway/meta/llama-3.2-3b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, "supports_response_schema": true }, "vercel_ai_gateway/meta/llama-3.2-90b": { "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.3-70b": { "input_cost_per_token": 7.2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-4-maverick": { "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-4-scout": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/mistral/codestral": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/mistral/codestral-embed": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/mistral/devstral-small": { "input_cost_per_token": 7e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/mistral/magistral-medium": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/mistral/magistral-small": { "input_cost_per_token": 5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true }, "vercel_ai_gateway/mistral/ministral-3b": { "input_cost_per_token": 4e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/mistral/ministral-8b": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/mistral/mistral-large": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/mistral/mistral-saba-24b": { "input_cost_per_token": 7.9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-07 }, "vercel_ai_gateway/mistral/mistral-small": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { "input_cost_per_token": 1.2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true }, "vercel_ai_gateway/mistral/pixtral-12b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/mistral/pixtral-large": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/moonshotai/kimi-k2": { "input_cost_per_token": 5.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/morph/morph-v3-fast": { "input_cost_per_token": 8e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, "vercel_ai_gateway/morph/morph-v3-large": { "input_cost_per_token": 9e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.9e-06 }, "vercel_ai_gateway/openai/gpt-3.5-turbo": { "input_cost_per_token": 5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { "input_cost_per_token": 1.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06 }, "vercel_ai_gateway/openai/gpt-4-turbo": { "input_cost_per_token": 1e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/openai/gpt-4.1": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4.1-mini": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4.1-nano": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4o": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4o-mini": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/o1": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/o3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/o3-mini": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/o4-mini": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true }, "vercel_ai_gateway/openai/text-embedding-3-large": { "input_cost_per_token": 1.3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/openai/text-embedding-3-small": { "input_cost_per_token": 2e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/openai/text-embedding-ada-002": { "input_cost_per_token": 1e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, "vercel_ai_gateway/perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-06 }, "vercel_ai_gateway/perplexity/sonar-pro": { "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05 }, "vercel_ai_gateway/perplexity/sonar-reasoning": { "input_cost_per_token": 1e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 5e-06 }, "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-06 }, "vercel_ai_gateway/vercel/v0-1.0-md": { "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/vercel/v0-1.5-md": { "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-2": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-2-vision": { "input_cost_per_token": 2e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3": { "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3-fast": { "input_cost_per_token": 5e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true }, "vercel_ai_gateway/xai/grok-3-mini": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3-mini-fast": { "input_cost_per_token": 6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.5": { "input_cost_per_token": 6e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.5-air": { "input_cost_per_token": 2e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.6": { "litellm_provider": "vercel_ai_gateway", "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 4.5e-07, "max_input_tokens": 200000, "max_output_tokens": 200000, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://vercel.com/ai-gateway/models/glm-4.6", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "vertex_ai/chirp": { "input_cost_per_character": 3e-05, "litellm_provider": "vertex_ai", "mode": "audio_speech", "source": "https://cloud.google.com/text-to-speech/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "vertex_ai/chirp_3": { "input_cost_per_second": 0.00026667, "litellm_provider": "vertex_ai", "metadata": { "calculation": "$0.016/60 seconds = $0.00026667 per second", "original_pricing_per_minute": 0.016 }, "mode": "audio_transcription", "source": "https://cloud.google.com/speech-to-text/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime" ] }, "vertex_ai/chirp_2": { "input_cost_per_second": 0.00026667, "litellm_provider": "vertex_ai", "metadata": { "calculation": "$0.016/60 seconds = $0.00026667 per second", "original_pricing_per_minute": 0.016 }, "mode": "audio_transcription", "source": "https://cloud.google.com/speech-to-text/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime" ] }, "vertex_ai/claude-3-5-haiku": { "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true }, "vertex_ai/claude-3-5-haiku@20241022": { "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true }, "vertex_ai/claude-haiku-4-5": { "deprecation_date": "2026-10-15", "successor_model": "vertex_ai/claude-haiku-5-5", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_vision": true, "prompt_cache_min_tokens": 4096 }, "vertex_ai/claude-haiku-4-5@20251001": { "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_vision": true, "prompt_cache_min_tokens": 4096 }, "vertex_ai/claude-3-5-sonnet": { "deprecation_date": "2026-02-19", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-3-5-sonnet@20240620": { "deprecation_date": "2026-02-19", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-3-haiku": { "deprecation_date": "2026-08-23", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-3-haiku@20240307": { "deprecation_date": "2026-08-23", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-3-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-3-sonnet@20240229": { "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", "successor_model": "vertex_ai/claude-opus-5-5", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-5@20251101": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6": { "deprecation_date": "2027-02-05", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6@default": { "deprecation_date": "2027-02-05", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7": { "deprecation_date": "2027-04-16", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7@default": { "deprecation_date": "2027-04-16", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5": { "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-03-01", "input_cost_per_token_batches": 5e-06, "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-2": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-11-09", "input_cost_per_token_batches": 4e-06, "output_cost_per_token_batches": 2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-mythos-5-2": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-11-09", "input_cost_per_token_batches": 4e-06, "output_cost_per_token_batches": 2e-05, "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" }, "vertex_ai/claude-fable-latest": { "alias_of": "vertex_ai/claude-fable-5-2" }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-03-01", "input_cost_per_token_batches": 5e-06, "output_cost_per_token_batches": 2.5e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-2@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-11-09", "input_cost_per_token_batches": 4e-06, "output_cost_per_token_batches": 2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-mythos-5-2@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "deprecation_date": "2027-11-09", "input_cost_per_token_batches": 4e-06, "output_cost_per_token_batches": 2e-05, "source": "https://platform.claude.com/docs/en/models/mythos-5-2/overview" }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5@default": { "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5-5": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-latest": { "alias_of": "vertex_ai/claude-opus-5-5" }, "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8": { "deprecation_date": "2027-05-28", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8@default": { "deprecation_date": "2027-05-28", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", "successor_model": "vertex_ai/claude-sonnet-5-5", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6": { "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5@20250929": { "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/codestral-2": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/codestral-2@001": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistralai/codestral-2": { "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/codestral-2501": { "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/codestral@2405": { "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/codestral@latest": { "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-10-21", "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, "output_cost_per_token_batches": 8.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { "cache_read_input_token_cost": 5.6e-08, "deprecation_date": "2026-10-21", "input_cost_per_token": 5.6e-07, "input_cost_per_token_batches": 2.8e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_assistant_prefill": false, "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 1.35e-06, "input_cost_per_token_batches": 6.75e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "output_cost_per_token_batches": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": false, "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/gemini-2.5-flash-image": { "deprecation_date": "2027-03-15", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/gemini-3.1-flash-lite-image", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "rpm": 100000, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": false, "tpm": 8000000, "supports_image_size": false }, "vertex_ai/gemini-3-pro-image": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 6e-05, "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supports_reasoning": false }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.6e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 6e-05, "output_cost_per_image_token_priority": 0.000216, "output_cost_per_token": 1.2e-05, "output_cost_per_token_priority": 2.16e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ] }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_image_token_batches": 3e-05, "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.4e-06, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supports_reasoning": false }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_image_token_batches": 3e-05, "output_cost_per_image_token_priority": 0.000108, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ] }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.1-flash-lite": { "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_audio_token_cost_batches": 2.5e-08, "cache_read_input_audio_token_cost_flex": 2.5e-08, "cache_read_input_audio_token_cost_priority": 9e-08, "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 5e-07, "input_cost_per_audio_token_above_200k_tokens": 5e-07, "input_cost_per_audio_token_above_200k_tokens_batches": 2.5e-07, "input_cost_per_audio_token_above_200k_tokens_flex": 2.5e-07, "input_cost_per_audio_token_above_200k_tokens_priority": 9e-07, "input_cost_per_audio_token_batches": 2.5e-07, "input_cost_per_audio_token_flex": 2.5e-07, "input_cost_per_audio_token_priority": 9e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "vertex_ai/gemini-3.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "cache_read_input_token_cost_flex": 1.5e-08, "cache_read_input_token_cost_priority": 5.4e-08, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count":5000,"period":"month","shared_group":"gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/jamba-1.5": { "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large": { "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large@001": { "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini": { "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini@001": { "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true }, "vertex_ai/lyria-002": { "litellm_provider": "vertex_ai", "mode": "audio_speech", "output_cost_per_image": 0.06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", "supported_audio_formats": [ "wav" ], "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": true, "vertex_ai_audio_api": "lyria_predict" }, "vertex_ai/lyria-3-clip-preview": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.04, "output_cost_per_token": 0, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", "supported_audio_formats": [ "mp3" ], "supported_endpoints": [ "/v1beta/interactions", "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supported_regions": [ "global" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "vertex_ai_audio_api": "lyria_interactions" }, "vertex_ai/lyria-3-pro-preview": { "input_cost_per_token": 0, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.08, "output_cost_per_token": 0, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", "supported_audio_formats": [ "mp3", "wav" ], "supported_endpoints": [ "/v1beta/interactions", "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supported_regions": [ "global" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "vertex_ai_audio_api": "lyria_interactions" }, "vertex_ai/meta/llama-3.1-405b-instruct-maas": { "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.6e-05, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/meta/llama-3.1-70b-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/meta/llama-3.1-8b-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { "input_cost_per_token": 3.5e-07, "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { "input_cost_per_token": 3.5e-07, "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/meta/llama3-405b-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true }, "vertex_ai/meta/llama3-70b-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true }, "vertex_ai/meta/llama3-8b-instruct-maas": { "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true }, "vertex_ai/minimaxai/minimax-m2-maas": { "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-10-21", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/moonshotai/kimi-k2-thinking-maas": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-10-21", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-10-21", "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/zai-org/glm-5-maas": { "cache_read_input_token_cost": 1e-07, "deprecation_date": "2026-10-21", "successor_model": "vertex_ai/zai-org/glm-5.2-maas", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/mistral-medium-3": { "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-medium-3@001": { "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistralai/mistral-medium-3": { "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistralai/mistral-medium-3@001": { "input_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-large-2411": { "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-large@2407": { "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-large@2411-001": { "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-large@latest": { "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-nemo@2407": { "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-nemo@latest": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/mistral-small-2503": { "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-small-2503@001": { "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-ocr-2505": { "litellm_provider": "vertex_ai", "mode": "ocr", "ocr_cost_per_page": 0.0005, "supported_endpoints": [ "/v1/ocr" ], "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/deepseek-ai/deepseek-ocr-maas": { "deprecation_date": "2026-10-21", "litellm_provider": "vertex_ai", "mode": "ocr", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "ocr_cost_per_page": 0.0003, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ] }, "vertex_ai/google/gemma-4-26b-a4b-it-maas": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { "input_cost_per_token": 9e-08, "input_cost_per_token_batches": 4.5e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_pdf_input": false, "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 7e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_pdf_input": false, "supports_reasoning": true, "cache_read_input_token_cost": 7e-09, "input_cost_per_token_batches": 3.5e-08, "output_cost_per_token_batches": 1.25e-07 }, "vertex_ai/xai/grok-4.1-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "vertex_ai/xai/grok-4.1-fast-reasoning": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "vertex_ai/xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "vertex_ai/xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "vertex_ai/xai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/xai/grok-4.6": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_batches": 4.4e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global", "us-south1" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { "cache_read_input_token_cost": 2.2e-08, "deprecation_date": "2026-10-21", "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_batches": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_tool_choice": true }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-3.1-fast-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-3.1-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-3.1-fast-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-3.1-lite-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "voyage/rerank-2": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0.0 }, "voyage/rerank-2-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0 }, "voyage/rerank-1": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/rerank-lite-1": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 4000, "max_output_tokens": 4000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/rerank-2.5": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, "voyage/rerank-2.5-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, "voyage/rerank-3": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/rerank-3-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-2": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-3": { "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-multilingual-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-3-large": { "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-3-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-3.5": { "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-3.5-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-code-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-code-3": { "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-context-3": { "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-finance-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-large-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-large-2-instruct": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-law-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 16000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-lite-01": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-lite-02-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, "voyage/voyage-multimodal-3": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true }, "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.7e-07, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.3e-07, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, "output_cost_per_token": 3e-06, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", "mode": "chat", "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V3.1": { "cache_read_input_token_cost": 2e-07, "supports_reasoning": true, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "wandb", "mode": "chat", "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_prompt_caching": true }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-07, "output_cost_per_token": 7.1e-07, "litellm_provider": "wandb", "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, "watsonx/ibm/granite-3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-07, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "watsonx/mistralai/mistral-large": { "input_cost_per_token": 3e-06, "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_input": false, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, "output_cost_per_token": 1.908e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/bigscience/mt0-xxl": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, "output_cost_per_token": 1.908e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, "output_cost_per_token": 1.8e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, "output_cost_per_token": 6e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, "output_cost_per_token": 6e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, "output_cost_per_token": 6e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 3.8e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 3.8e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 3.8e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, "output_cost_per_token": 3.5e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 1.5e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-06, "output_cost_per_token": 2e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, "output_cost_per_token": 3.5e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1e-05, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, "output_cost_per_token": 3.5e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, "output_cost_per_token": 1.8e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false }, "watsonx/whisper-large-v3-turbo": { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "litellm_provider": "watsonx", "mode": "audio_transcription", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "whisper-1": { "input_cost_per_second": 0.0001, "litellm_provider": "openai", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "deprecation_date": "2027-02-26", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-live-transcribe", "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-4.20-multi-agent-beta-0309": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ "/v1/responses" ] }, "xai/grok-4.20-beta-0309-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "token_count_framing": 185, "token_count_tool_framing": 214, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-4.3-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-4.5": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-4.5-latest": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-build-latest": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-4.6": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "cache_read_input_token_cost_above_200k_tokens_batches": 8e-07, "cache_read_input_token_cost_batches": 4e-07, "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_above_200k_tokens_batches": 3.2e-06, "input_cost_per_token_batches": 1.6e-06, "litellm_provider": "xai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "output_cost_per_token_above_200k_tokens_batches": 9.6e-06, "output_cost_per_token_batches": 4.8e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "xai/grok-latest": { "alias_of": "xai/grok-4.7" }, "zai.glm-4.7": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "zai.glm-5", "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_flex": 1.1e-06, "output_cost_per_token_priority": 3.85e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "input_cost_per_token_flex": 5e-07, "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-4.7-flash": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 7e-08, "input_cost_per_token_batches": 3.5e-08, "input_cost_per_token_flex": 3.5e-08, "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, "output_cost_per_token_priority": 7e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai/glm-5": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-5.3": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "zai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.z.ai/guides/overview/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zai/glm-latest": { "alias_of": "zai/glm-5.3" }, "zai/glm-5.3-flash": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "zai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "supports_vision": true }, "zai/glm-flash-latest": { "alias_of": "zai/glm-5.3-flash" }, "zai/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://vercel.com/ai-gateway/models/glm-5v-turbo", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "zai/glm-5.1": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-5-code": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 5e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.7": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.7-flash": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 0, "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.6": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "zai", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5": { "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5v": { "input_cost_per_token": 6e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-x": { "input_cost_per_token": 2.2e-06, "output_cost_per_token": 8.9e-06, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-air": { "input_cost_per_token": 2e-07, "output_cost_per_token": 1.1e-06, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-airx": { "input_cost_per_token": 1.1e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4-32b-0414-128k": { "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.5-flash": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "zai", "max_input_tokens": 128000, "max_output_tokens": 32000, "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "vertex_ai/search_api": { "input_cost_per_query": 0.0015, "litellm_provider": "vertex_ai", "mode": "vector_store" }, "vertex_ai/semantic-ranker-default": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-default-002": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-default-003": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-default-004": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-default@latest": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-fast": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-fast-004": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/semantic-ranker-fast@latest": { "input_cost_per_query": 0.001, "input_cost_per_token": 0.0, "litellm_provider": "vertex_ai", "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "openai/container": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", "mode": "chat" }, "openai/sora-2": { "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "openai/sora-2-pro": { "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "openai/sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "azure/sora-2": { "deprecation_date": "2026-11-02", "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://ai.azure.com/catalog/models/sora-2", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "azure/sora-2-pro": { "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://ai.azure.com/catalog/models/sora-2-pro", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "azure/sora-2-pro-high-res": { "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://ai.azure.com/catalog/models/sora-2-pro", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "runwayml/gen4_turbo": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_video_per_second": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" } }, "runwayml/gen4.5": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.12, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "12 credits per second @ $0.01 per credit = $0.12 per second" } }, "runwayml/aleph2": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.28, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "28 credits per second @ $0.01 per credit = $0.28 per second; 56 credit minimum per task not modeled" } }, "runwayml/seedance2": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.3, "output_cost_per_second_1080p": 0.4, "output_cost_per_second_4k": 1.5, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": {"comment":"14/30/40/150 credits per second at 480p/720p/1080p/4K @ $0.01 per credit; 56 credit minimum per generation not modeled"}, "output_cost_per_second_480p": 0.14 }, "runwayml/seedance2_fast": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.24, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": {"comment":"11 credits per second at 480p, 24 at 720p @ $0.01 per credit; 44 credit minimum per generation not modeled"}, "output_cost_per_second_480p": 0.11 }, "runwayml/seedance2_mini": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": {"comment":"7 credits per second at 480p, 15 at 720p @ $0.01 per credit; 28 credit minimum per generation not modeled"}, "output_cost_per_second_480p": 0.07 }, "runwayml/seedance2_5": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.3, "output_cost_per_second_480p": 0.2, "output_cost_per_second_1080p": 0.68, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "Output: 20/30/68 credits per second at 480p/720p/1080p @ $0.01 per credit; input video billed additionally at 10/15/34 credits per input second and the 80 credit minimum per task are not modeled" } }, "runwayml/seedance-latest": { "alias_of": "runwayml/seedance2_5" }, "runwayml/hailuo3": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "10 credits per second at 768P, 15 at 2K (mapped to the 1080p tier) @ $0.01 per credit; 2 credits per reference image not modeled" } }, "runwayml/gemini_omni_flash": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "10 credits per second @ $0.01 per credit = $0.10 per second" } }, "runwayml/veo3.1": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "40 credits per second with audio, 20 without @ $0.01 per credit; priced at the with-audio rate" } }, "runwayml/veo3.1_fast": { "litellm_provider": "runwayml", "mode": "video_generation", "output_cost_per_second": 0.15, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ], "metadata": { "comment": "15 credits per second with audio, 10 without @ $0.01 per credit; priced at the with-audio rate" } }, "runwayml/gen4_image": { "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.05, "output_cost_per_image": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ], "metadata": { "comment": "5 credits per 720p image or 8 credits per 1080p image @ $0.01 per credit. Using 5 credits ($0.05) as base cost" } }, "runwayml/gen4_image_turbo": { "litellm_provider": "runwayml", "mode": "image_generation", "input_cost_per_image": 0.02, "output_cost_per_image": 0.02, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ], "metadata": { "comment": "2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image" } }, "runwayml/eleven_multilingual_v2": { "litellm_provider": "runwayml", "mode": "audio_speech", "input_cost_per_character": 0.0002, "source": "https://docs.dev.runwayml.com/guides/pricing/", "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character"} }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.8e-06, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-08, "output_cost_per_token": 4e-08, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-08, "output_cost_per_token": 8e-08, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-09, "output_cost_per_token": 1e-09, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, "output_cost_per_token": 5e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, "output_cost_per_token": 3.5e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 8.8e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 8.8e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 8.8e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat", "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "mode": "rerank", "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 8.8e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 8.8e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, "output_cost_per_token": 1.3e-10, "litellm_provider": "fireworks_ai", "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", "mode": "chat" }, "fireworks_ai/accounts/fireworks/routers/glm-5p1-fast": { "cache_read_input_token_cost": 5.2e-07, "input_cost_per_token": 2.8e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p6", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "scaleway/qwen/qwen3.5-397b-a17b": { "input_cost_per_token": 6e-07, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "scaleway/qwen/qwen3.6-35b-a3b": { "input_cost_per_token": 2.5e-07, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_vision": true, "supports_reasoning": true }, "scaleway/qwen/qwen3-235b-a22b-instruct-2507": { "input_cost_per_token": 7.5e-07, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true }, "scaleway/qwen/qwen3-embedding-8b": { "input_cost_per_token": 1e-07, "litellm_provider": "scaleway", "mode": "embedding", "output_cost_per_token": 0.0 }, "scaleway/qwen/qwen3-coder-30b-a3b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, "deprecation_date": "2026-10-01" }, "scaleway/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true }, "scaleway/openai/whisper-large-v3": { "input_cost_per_audio_token": 0.0, "litellm_provider": "scaleway", "mode": "audio_transcription", "output_cost_per_token": 0.0 }, "scaleway/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 2.5e-07, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "scaleway/mistralai/mistral-medium-3.5-128b": { "input_cost_per_token": 1.5e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.5e-06, "supports_reasoning": true, "supports_function_calling": true, "supports_vision": true, "supports_tool_choice": true }, "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": { "input_cost_per_token": 1.5e-07, "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "supports_function_calling": true, "supports_vision": true }, "scaleway/mistralai/pixtral-12b-2409": { "input_cost_per_token": 2e-07, "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, "supports_function_calling": true, "deprecation_date": "2026-10-01" }, "scaleway/BAAI/bge-multilingual-gemma2": { "input_cost_per_token": 1e-07, "litellm_provider": "scaleway", "mode": "embedding", "output_cost_per_token": 0.0 }, "scaleway/meta/llama-3.3-70b-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true }, "novita/deepseek/deepseek-v3.2": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.69e-07, "output_cost_per_token": 4e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.345e-07, "input_cost_per_token_cache_hit": 1.345e-07, "supports_reasoning": true }, "novita/minimax/minimax-m2.1": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 3e-08, "input_cost_per_token_cache_hit": 3e-08 }, "novita/zai-org/glm-4.7": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token_cache_hit": 1.1e-07, "supports_reasoning": true }, "novita/xiaomimimo/mimo-v2-flash": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.1e-07, "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 2.4e-08, "input_cost_per_token_cache_hit": 2.4e-08, "supports_reasoning": true }, "novita/zai-org/autoglm-phone-9b-multilingual": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.5e-08, "output_cost_per_token": 1.38e-07, "max_input_tokens": 65536, "max_output_tokens": 65536, "supports_vision": true, "supports_system_messages": true }, "novita/moonshotai/kimi-k2-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "cache_read_input_token_cost": 1.5e-07, "supports_prompt_caching": true }, "novita/minimax/minimax-m2": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "cache_read_input_token_cost": 3e-08, "input_cost_per_token_cache_hit": 3e-08, "supports_reasoning": true, "supports_response_schema": true }, "novita/paddlepaddle/paddleocr-vl": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-08, "output_cost_per_token": 2e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, "novita/deepseek/deepseek-v3.2-exp": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-07, "output_cost_per_token": 4.1e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/qwen/qwen3-vl-235b-a22b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9.8e-07, "output_cost_per_token": 3.95e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, "supports_tool_choice": true }, "novita/zai-org/glm-4.6v": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 9e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 5.5e-08, "input_cost_per_token_cache_hit": 5.5e-08, "supports_reasoning": true }, "novita/zai-org/glm-4.6": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token_cache_hit": 1.1e-07, "supports_reasoning": true }, "novita/kwaipilot/kat-coder-pro": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "max_input_tokens": 256000, "max_output_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 6e-08, "input_cost_per_token_cache_hit": 6e-08 }, "novita/qwen/qwen3-next-80b-a3b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/qwen/qwen3-next-80b-a3b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/deepseek/deepseek-ocr": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-08, "output_cost_per_token": 3e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-v3.1-terminus": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-07, "input_cost_per_token_cache_hit": 1.35e-07, "supports_reasoning": true }, "novita/qwen/qwen3-vl-235b-a22b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-max": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.11e-06, "output_cost_per_token": 8.45e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/skywork/r1v4-lite": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-07, "output_cost_per_token": 6e-07, "max_input_tokens": 262144, "max_output_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-v3.1": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-07, "input_cost_per_token_cache_hit": 1.35e-07, "supports_reasoning": true }, "novita/moonshotai/kimi-k2-0905": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-coder-480b-a35b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-coder-30b-a3b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 2.7e-07, "max_input_tokens": 160000, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/openai/gpt-oss-120b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-08, "output_cost_per_token": 2.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/moonshotai/kimi-k2-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.7e-07, "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, "max_output_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-v3-0324": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.35e-07, "input_cost_per_token_cache_hit": 1.35e-07 }, "novita/zai-org/glm-4.5": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 2.2e-06, "max_input_tokens": 131072, "max_output_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token_cache_hit": 1.1e-07, "supports_reasoning": true }, "novita/qwen/qwen3-235b-a22b-thinking-2507": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 3e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true }, "novita/meta-llama/llama-3.1-8b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, "supports_system_messages": true, "supports_response_schema": true }, "novita/google/gemma-3-12b-it": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "max_input_tokens": 131072, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/zai-org/glm-4.5v": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 1.8e-06, "max_input_tokens": 65536, "max_output_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token_cache_hit": 1.1e-07, "supports_reasoning": true }, "novita/openai/gpt-oss-20b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-08, "output_cost_per_token": 1.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/qwen/qwen3-235b-a22b-instruct-2507": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-08, "output_cost_per_token": 5.8e-07, "max_input_tokens": 131072, "max_output_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-r1-distill-qwen-14b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 1.5e-07, "max_input_tokens": 32768, "max_output_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/meta-llama/llama-3.3-70b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.35e-07, "output_cost_per_token": 4e-07, "max_input_tokens": 12288, "max_output_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen-2.5-72b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.8e-07, "output_cost_per_token": 4e-07, "max_input_tokens": 32000, "max_output_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/mistralai/mistral-nemo": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-08, "output_cost_per_token": 1.7e-07, "max_input_tokens": 60288, "max_output_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/minimaxai/minimax-m1-80k": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.2e-06, "max_input_tokens": 1000000, "max_output_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 163840, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "cache_read_input_token_cost": 3.5e-07, "input_cost_per_token_cache_hit": 3.5e-07, "supports_reasoning": true }, "novita/deepseek/deepseek-r1-distill-qwen-32b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 64000, "max_output_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/meta-llama/llama-3-8b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-08, "output_cost_per_token": 4e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_system_messages": true, "supports_response_schema": true }, "novita/microsoft/wizardlm-2-8x22b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6.2e-07, "output_cost_per_token": 6.2e-07, "max_input_tokens": 65535, "max_output_tokens": 8000, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528-qwen3-8b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 6e-08, "output_cost_per_token": 9e-08, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true }, "novita/deepseek/deepseek-r1-distill-llama-70b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/meta-llama/llama-3-70b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5.1e-07, "output_cost_per_token": 7.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-235b-a22b-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true }, "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.7e-07, "output_cost_per_token": 8.5e-07, "max_input_tokens": 1048576, "max_output_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/meta-llama/llama-4-scout-17b-16e-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.8e-07, "output_cost_per_token": 5.9e-07, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_vision": true, "supports_system_messages": true }, "novita/nousresearch/hermes-2-pro-llama-3-8b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen2.5-vl-72b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_vision": true, "supports_system_messages": true }, "novita/sao10k/l3-70b-euryale-v2.1": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.48e-06, "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/baidu/ernie-4.5-21B-a3b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 2.8e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true }, "novita/sao10k/l3-8b-lunaris": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/baichuan/baichuan-m2-32b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 7e-08, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-424b-a47b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4.2e-07, "output_cost_per_token": 1.25e-06, "max_input_tokens": 123000, "max_output_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true }, "novita/baidu/ernie-4.5-300b-a47b-paddle": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, "max_input_tokens": 123000, "max_output_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/deepseek/deepseek-prover-v2-671b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 160000, "max_output_tokens": 160000, "supports_system_messages": true }, "novita/qwen/qwen3-32b-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1e-07, "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, "novita/qwen/qwen3-30b-a3b-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-08, "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, "supports_tool_choice": true }, "novita/google/gemma-3-27b-it": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.19e-07, "output_cost_per_token": 2e-07, "max_input_tokens": 98304, "max_output_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, "novita/deepseek/deepseek-v3-turbo": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 4e-07, "output_cost_per_token": 1.3e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/deepseek/deepseek-r1-turbo": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true }, "novita/Sao10K/L3-8B-Stheno-v3.2": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/gryphe/mythomax-l2-13b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 9e-08, "output_cost_per_token": 9e-08, "max_input_tokens": 4096, "max_output_tokens": 3200, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.9e-07, "output_cost_per_token": 3.9e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true }, "novita/qwen/qwen3-vl-8b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 8e-08, "output_cost_per_token": 5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/zai-org/glm-4.5-air": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.3e-07, "output_cost_per_token": 8.5e-07, "max_input_tokens": 131072, "max_output_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "cache_read_input_token_cost": 2.5e-08, "supports_prompt_caching": true }, "novita/qwen/qwen3-vl-30b-a3b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-07, "output_cost_per_token": 7e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-vl-30b-a3b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2e-07, "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/qwen/qwen3-omni-30b-a3b-thinking": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true, "supports_audio_input": true }, "novita/qwen/qwen3-omni-30b-a3b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_audio_input": true, "supports_audio_output": true }, "novita/qwen/qwen-mt-plus": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 7.5e-07, "max_input_tokens": 16384, "max_output_tokens": 8192, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.6e-07, "max_input_tokens": 30000, "max_output_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true }, "novita/baidu/ernie-4.5-21B-a3b": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 2.8e-07, "max_input_tokens": 120000, "max_output_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/qwen/qwen3-8b-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3.5e-08, "output_cost_per_token": 1.38e-07, "max_input_tokens": 128000, "max_output_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, "novita/qwen/qwen3-4b-fp8": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-08, "output_cost_per_token": 3e-08, "max_input_tokens": 128000, "max_output_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, "supports_tool_choice": true }, "novita/qwen/qwen2.5-7b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 7e-08, "max_input_tokens": 32000, "max_output_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true }, "novita/meta-llama/llama-3.2-3b-instruct": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 3e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/sao10k/l31-70b-euryale-v2.2": { "litellm_provider": "novita", "mode": "chat", "input_cost_per_token": 1.48e-06, "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true }, "novita/qwen/qwen3-embedding-0.6b": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768 }, "novita/qwen/qwen3-embedding-8b": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 4096 }, "novita/baai/bge-m3": { "litellm_provider": "novita", "mode": "embedding", "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8192, "max_output_tokens": 96000 }, "novita/qwen/qwen3-reranker-8b": { "litellm_provider": "novita", "mode": "rerank", "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 4096 }, "novita/baai/bge-reranker-v2-m3": { "litellm_provider": "novita", "mode": "rerank", "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8000, "max_output_tokens": 8000 }, "llamagate/llama-3.1-8b": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, "output_cost_per_token": 5e-08, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/llama-3.2-3b": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, "output_cost_per_token": 8e-08, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/mistral-7b-v0.3": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/qwen3-8b": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, "output_cost_per_token": 1.4e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/dolphin3-8b": { "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.5e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/deepseek-r1-8b": { "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, "output_cost_per_token": 2e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true }, "llamagate/deepseek-r1-7b-qwen": { "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.5e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true }, "llamagate/openthinker-7b": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.5e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true }, "llamagate/qwen2.5-coder-7b": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.2e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/deepseek-coder-6.7b": { "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.2e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/codellama-7b": { "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.2e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true }, "llamagate/qwen3-vl-8b": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5.5e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "llamagate/llava-7b": { "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, "output_cost_per_token": 2e-07, "litellm_provider": "llamagate", "mode": "chat", "supports_response_schema": true, "supports_vision": true }, "llamagate/gemma3-4b": { "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, "output_cost_per_token": 8e-08, "litellm_provider": "llamagate", "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "llamagate/nomic-embed-text": { "max_input_tokens": 8192, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, "litellm_provider": "llamagate", "mode": "embedding" }, "llamagate/qwen3-embedding-8b": { "max_input_tokens": 40960, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, "litellm_provider": "llamagate", "mode": "embedding" }, "libertai/hermes-3-8b-tee": { "max_input_tokens": 16000, "max_output_tokens": 16000, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": false, "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 4e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 4e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.75e-06, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b-thinking": { "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.75e-06, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.75e-06, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": false, "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash-thinking": { "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.75e-06, "litellm_provider": "libertai", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": false, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/" }, "libertai/bge-m3": { "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, "litellm_provider": "libertai", "mode": "embedding", "source": "https://docs.libertai.io/apis/text/" }, "sarvam/sarvam-m": { "cache_creation_input_token_cost": 0, "cache_creation_input_token_cost_above_1hr": 0, "cache_read_input_token_cost": 0, "input_cost_per_token": 0, "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true }, "tts-1-1106": { "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "tts-1-hd-1106": { "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", "supported_endpoints": [ "/v1/audio/speech" ] }, "gpt-4o-mini-tts-2025-12-15": { "deprecation_date": "2027-01-06", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ] }, "gpt-4o-mini-transcribe-2025-03-20": { "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-4o-mini-transcribe-2025-12-15", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "gpt-4o-mini-transcribe-2025-12-15": { "deprecation_date": "2027-02-26", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-live-transcribe", "input_cost_per_audio_token": 1.25e-06, "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "gpt-5-search-api": { "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, "gpt-5-search-api-2025-10-14": { "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false }, "gpt-realtime-mini-2025-12-15": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "deprecation_date": "2027-01-20", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-realtime-2.1-mini", "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-realtime-whisper": { "input_cost_per_second": 0.000283333333333, "litellm_provider": "openai", "mode": "audio_transcription", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "sora-2": { "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "sora-2-pro": { "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "sora-2-pro-high-res": { "litellm_provider": "openai", "deprecation_date": "2026-09-24", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "chatgpt-image-latest": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_image_token_cost_batches": 1e-06, "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_batches": 6.3e-07, "deprecation_date": "2026-12-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "successor_model": "gpt-image-2.5-sunburst", "input_cost_per_image_token": 8e-06, "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, "output_cost_per_image_token_batches": 1.6e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-09-2025": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-12-2025": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true, "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true }, "gemini-3.1-flash-live-preview": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, "supports_response_schema": false }, "gemini-3.8-live": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "gemini_audio_only_live": true, "supports_response_schema": false }, "gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "gemini_audio_only_live": true, "supports_reasoning": true, "supports_response_schema": false }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-09-2025": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "gemini_native_audio": true, "input_cost_per_video_token": 3e-06, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true, "supports_reasoning": true }, "gemini/gemini-3.1-flash-live-preview": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-live", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_response_schema": false, "supports_reasoning": true }, "gemini/gemini-3.1-flash-tts-preview": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "tpm": 4000000, "rpm": 10, "supports_function_calling": false, "supports_response_schema": false, "supports_web_search": false }, "gemini/gemini-3.8-flash-tts": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_token_batches": 4.5e-06, "output_cost_per_token_flex": 4.5e-06, "output_cost_per_token_priority": 1.62e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "supports_prompt_caching": true }, "gemini/gemini-3.8-flash-lite-tts": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, "input_cost_per_token_priority": 9e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 6e-06, "output_cost_per_token": 6e-06, "output_cost_per_token_batches": 3e-06, "output_cost_per_token_flex": 3e-06, "output_cost_per_token_priority": 1.08e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "supports_prompt_caching": true }, "gemini-2.5-flash-preview-tts": { "deprecation_date": "2026-11-17", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "successor_model": "gemini/gemini-3.8-flash-tts", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "supports_audio_input": false, "supports_function_calling": false, "supports_response_schema": false, "supports_web_search": false }, "gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.35e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "output_cost_per_token_priority": 6.75e-06, "prompt_cache_min_tokens": 4096, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_batches": 1.5e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 2e-08, "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.5e-06, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.6e-06, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, "cache_read_input_token_cost_above_200k_tokens_flex": 4e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "cache_read_input_token_cost_batches": 2e-07, "cache_read_input_token_cost_priority": 3.6e-07, "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.6e-06, "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_token_priority": 2.16e-05, "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-07, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "input_cost_per_token_above_200k_tokens_flex": 2e-06, "input_cost_per_token_flex": 1e-06, "output_cost_per_token_above_200k_tokens_batches": 9e-06, "output_cost_per_token_above_200k_tokens_flex": 9e-06, "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 } }, "vertex_ai/claude-sonnet-5@default": { "deprecation_date": "2026-12-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "duckduckgo/search": { "litellm_provider": "duckduckgo", "mode": "search", "input_cost_per_query": 0.0, "metadata": { "notes": "DuckDuckGo Instant Answer API is free and does not require an API key." } }, "bedrock_mantle/openai.gpt-oss-120b": { "supports_vision": false, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-20b": { "supports_vision": false, "input_cost_per_token": 7e-08, "input_cost_per_token_batches": 3.5e-08, "input_cost_per_token_flex": 3.5e-08, "input_cost_per_token_priority": 1.225e-07, "output_cost_per_token": 3e-07, "output_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 1.5e-07, "output_cost_per_token_priority": 5.25e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-120b": { "supports_vision": false, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { "supports_vision": false, "input_cost_per_token": 7e-08, "input_cost_per_token_batches": 3e-08, "input_cost_per_token_flex": 3e-08, "input_cost_per_token_priority": 1.2e-07, "output_cost_per_token": 2e-07, "output_cost_per_token_flex": 1e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 1e-07, "output_cost_per_token_priority": 3.5e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html" }, "bedrock_mantle/openai.gpt-5.6-terra": { "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html" }, "bedrock_mantle/openai.gpt-5.6-cyber": { "input_cost_per_token": 1.375e-05, "cache_creation_input_token_cost": 1.71875e-05, "cache_read_input_token_cost": 1.375e-06, "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_web_search": true }, "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": { "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html", "supports_web_search": true }, "bedrock_mantle/openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "cache_creation_input_token_cost": 2.75e-07, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "us.openai.gpt-5.6-sol": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 4.4e-07, "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-sol": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 1e-05, "cache_read_input_token_cost": 4e-07, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-terra": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-terra": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-luna": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "cache_creation_input_token_cost": 2.75e-07, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.4": { "input_cost_per_token": 2.75e-06, "input_cost_per_token_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "output_cost_per_token": 1.65e-05, "output_cost_per_token_above_272k_tokens": 2.475e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/responses" ] }, "global.openai.gpt-5.4": { "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/responses" ] }, "us.openai.gpt-5.5": { "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/responses" ] }, "global.openai.gpt-5.5": { "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/responses" ] }, "global.openai.gpt-5.6-luna": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "bedrock_mantle/openai.gpt-6-astra": { "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, "cache_read_input_token_cost_ultrafast": 6.6e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, "output_cost_per_token_ultrafast": 0.00033, "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supports_web_search": true }, "bedrock_mantle/gpt-astra-latest": { "alias_of": "bedrock_mantle/openai.gpt-6-astra" }, "bedrock_mantle/openai.gpt-6-sol": { "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", "supports_web_search": true }, "bedrock_mantle/openai.gpt-6-luna": { "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, "cache_read_input_token_cost": 1.1e-08, "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", "supports_web_search": true }, "bedrock_mantle/gpt-luna-latest": { "alias_of": "bedrock_mantle/openai.gpt-6-luna" }, "us.openai.gpt-6-astra": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, "cache_read_input_token_cost_ultrafast": 6.6e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, "output_cost_per_token_ultrafast": 0.00033, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-sol": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-luna": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, "cache_read_input_token_cost": 1.1e-08, "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-6-astra": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, "cache_creation_input_token_cost_ultrafast": 7.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, "cache_read_input_token_cost_ultrafast": 6e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, "input_cost_per_token_ultrafast": 6e-05, "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_ultrafast": 0.0003, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "bedrock/gpt-astra-latest": { "alias_of": "global.openai.gpt-6-astra" }, "openai.gpt-6-sol": { "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-sol": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "openai.gpt-6-luna": { "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-luna": { "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ] }, "bedrock/gpt-luna-latest": { "alias_of": "global.openai.gpt-6-luna" }, "bedrock_mantle/openai.gpt-5.5": { "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html" }, "bedrock_mantle/openai.gpt-5.4": { "input_cost_per_token": 2.75e-06, "input_cost_per_token_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.75e-07, "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "output_cost_per_token": 1.65e-05, "output_cost_per_token_above_272k_tokens": 2.475e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html" }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.45e-07, "output_cost_per_token": 4e-07, "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 7e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-07, "input_cost_per_token_batches": 6.5e-08, "input_cost_per_token_flex": 6.5e-08, "input_cost_per_token_priority": 2.275e-07, "output_cost_per_token": 4e-07, "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 7e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/google.gemma-4-e2b": { "input_cost_per_token": 4e-08, "input_cost_per_token_batches": 2e-08, "input_cost_per_token_flex": 2e-08, "input_cost_per_token_priority": 7e-08, "output_cost_per_token": 8e-08, "output_cost_per_token_flex": 4e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_batches": 4e-08, "output_cost_per_token_priority": 1.4e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/xai.grok-4.3": { "use_openai_responses_path": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_flex": 1.25e-06, "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_flex": 2.75e-07, "cache_read_input_token_cost_priority": 9.625e-07, "input_cost_per_token_flex": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-6.html" }, "bedrock_mantle/anthropic.claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, "output_cost_per_token_batches": 2.5e-06, "token_count_model": {"model":"anthropic.claude-haiku-4-5-20251001-v1:0","litellm_provider":"bedrock"} }, "bedrock_mantle/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 4.4e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", "thinking_always_on": true, "supports_forced_tool_use": false, "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-east-1"} }, "bedrock_mantle/claude-opus-latest": { "alias_of": "bedrock_mantle/anthropic.claude-opus-5-5" }, "bedrock_mantle/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "bedrock_mantle/claude-sonnet-latest": { "alias_of": "bedrock_mantle/anthropic.claude-sonnet-5-5" }, "us.xai.grok-4.6": { "supports_regex_lookaround": false, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_flex": 2.75e-07, "cache_read_input_token_cost_priority": 9.625e-07, "input_cost_per_token_flex": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "global.xai.grok-4.6": { "supports_regex_lookaround": false, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3e-06, "output_cost_per_token_priority": 1.05e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "volcengine/doubao-seed-2-0-pro-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4.6e-07, "output_cost_per_token": 2.3e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 7e-07, "output_cost_per_token": 3.5e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 1.4e-06, "output_cost_per_token": 7e-06, "range": [ 128000.0, 256000.0 ] } ] }, "volcengine/doubao-seed-2-1-pro-260628": { "cache_read_input_token_cost": 1.725e-07, "input_cost_per_token": 8.625e-07, "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true }, "volcengine/doubao-seed-2-1-pro-260915": { "cache_read_input_token_cost": 1.725e-07, "input_cost_per_token": 8.625e-07, "litellm_provider": "volcengine", "max_input_tokens": 1024000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true }, "volcengine/doubao-seed-2-1-lite-260915": { "cache_read_input_audio_token_cost": 3.45e-07, "cache_read_input_token_cost": 2.3e-08, "input_cost_per_audio_token": 1.725e-06, "input_cost_per_token": 1.15e-07, "litellm_provider": "volcengine", "max_input_tokens": 1024000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 3.88126e-07, "source": "https://www.volcengine.com/docs/82379/1544106", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true }, "volcengine/doubao-seed-2-1-turbo-260628": { "cache_read_input_token_cost": 8.625e-08, "input_cost_per_token": 4.3125e-07, "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.15625e-06, "source": "https://www.volcengine.com/docs/82379/1544106", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 8.7e-08, "output_cost_per_token": 5.2e-07, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 1.3e-07, "output_cost_per_token": 7.8e-07, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 2.6e-07, "output_cost_per_token": 1.6e-06, "range": [ 128000.0, 256000.0 ] } ] }, "volcengine/doubao-seed-2-0-mini-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 2.9e-08, "output_cost_per_token": 2.9e-07, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 5.8e-08, "output_cost_per_token": 5.8e-07, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 1.2e-07, "output_cost_per_token": 1.2e-06, "range": [ 128000.0, 256000.0 ] } ] }, "volcengine/doubao-seed-2-0-code-preview-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "tiered_pricing": [ { "input_cost_per_token": 4.6e-07, "output_cost_per_token": 2.3e-06, "range": [ 0, 32000.0 ] }, { "input_cost_per_token": 7e-07, "output_cost_per_token": 3.5e-06, "range": [ 32000.0, 128000.0 ] }, { "input_cost_per_token": 1.4e-06, "output_cost_per_token": 7e-06, "range": [ 128000.0, 256000.0 ] } ] }, "volcengine/doubao-seedance-2-5-260628": { "litellm_provider": "volcengine", "mode": "video_generation", "source": "https://www.volcengine.com/docs/82379/1544106", "output_cost_per_second": 0.216, "output_cost_per_second_480p": 0.096075, "output_cost_per_second_720p": 0.216, "output_cost_per_second_1080p": 0.5346, "supported_modalities": ["text", "image", "video", "audio"], "supported_output_modalities": ["video"], "supported_endpoints": ["/v1/videos"], "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} }, "volcengine/doubao-seedance-2-0-260128": { "litellm_provider": "volcengine", "mode": "video_generation", "source": "https://www.volcengine.com/docs/82379/1544106", "output_cost_per_second": 0.141942857, "output_cost_per_second_480p": 0.066003429, "output_cost_per_second_720p": 0.141942857, "output_cost_per_second_1080p": 0.354085714, "output_cost_per_second_4k": 0.722057143, "supported_modalities": ["text", "image", "video", "audio"], "supported_output_modalities": ["video"], "supported_endpoints": ["/v1/videos"], "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} }, "volcengine/doubao-seedance-2-0-fast-260128": { "litellm_provider": "volcengine", "mode": "video_generation", "source": "https://www.volcengine.com/docs/82379/1544106", "output_cost_per_second": 0.114171429, "output_cost_per_second_480p": 0.053089714, "output_cost_per_second_720p": 0.114171429, "supported_modalities": ["text", "image", "video", "audio"], "supported_output_modalities": ["video"], "supported_endpoints": ["/v1/videos"], "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} }, "volcengine/doubao-seedance-2-0-mini-260615": { "litellm_provider": "volcengine", "mode": "video_generation", "source": "https://www.volcengine.com/docs/82379/1544106", "output_cost_per_second": 0.070971429, "output_cost_per_second_480p": 0.033001714, "output_cost_per_second_720p": 0.070971429, "supported_modalities": ["text", "image"], "supported_output_modalities": ["video"], "supported_endpoints": ["/v1/videos"], "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "input_cost_per_token_flex": 5e-07, "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-west-2/zai.glm-5": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "input_cost_per_token_flex": 5e-07, "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_batches": 1.6e-06, "output_cost_per_token_flex": 1.6e-06, "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_1hr": 2.4e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, "cache_creation_input_token_cost_above_1hr": 2.4e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "token_count_model": { "model": "anthropic.claude-haiku-4-5-20251001-v1:0", "litellm_provider": "bedrock" } }, "snowflake/claude-sonnet-4-5": { "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, "prompt_cache_min_tokens": 1024 }, "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "cache_read_input_token_cost": 1e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true }, "snowflake/openai-gpt-4.1": { "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 2e-06, "output_cost_per_token": 8e-06, "cache_read_input_token_cost": 5e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true }, "snowflake/openai-gpt-5": { "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.25e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true }, "snowflake/openai-gpt-5-mini": { "max_input_tokens": 1000000, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_response_schema": true }, "snowflake/openai-gpt-5-nano": { "max_input_tokens": 5000000, "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_response_schema": true }, "snowflake/llama4-maverick": { "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.4e-07, "output_cost_per_token": 9.7e-07, "litellm_provider": "snowflake", "mode": "chat", "supports_function_calling": true, "supports_system_messages": true }, "snowflake/snowflake-arctic-embed-l-v2.0": { "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, "litellm_provider": "snowflake", "mode": "embedding" }, "snowflake/snowflake-arctic-embed-m-v2.0": { "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, "litellm_provider": "snowflake", "mode": "embedding" }, "soniox/stt-async-v4": { "litellm_provider": "soniox", "max_output_tokens": 8000, "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true }, "soniox/stt-async-v5": { "litellm_provider": "soniox", "max_output_tokens": 8000, "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true }, "soniox/stt-rt-v5": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "soniox/stt-rt-preview": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "soniox/stt-rt-preview-v2": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "soniox/stt-rt-v3": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "soniox/stt-rt-v3-preview": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "soniox/stt-rt-v4": { "input_cost_per_second": 3.333e-05, "litellm_provider": "soniox", "metadata": { "calculation": "$0.12/3600 seconds = $0.00003333 per second", "original_pricing_per_hour": 0.12 }, "mode": "audio_transcription", "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.8e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/Qwen/Qwen3.6-27B-FP8": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 202752, "max_output_tokens": 202752, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/moonshotai/Kimi-K2.6": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 9.6e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/MiniMaxAI/MiniMax-M2.5": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 0, "max_input_tokens": 196608, "max_output_tokens": 196608, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/google/gemma-4-31B-it": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.6e-07, "cache_read_input_token_cost": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/openai/gpt-oss-120b": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 0, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "tensormesh/openai/gpt-oss-20b": { "litellm_provider": "tensormesh", "mode": "chat", "input_cost_per_token": 7e-08, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 0, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, "deepseek-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "streamlake/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "streamlake", "max_input_tokens": 1048566, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.96e-06, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/DeepSeek-V3": { "cache_read_input_token_cost": 1.14e-07, "input_cost_per_token": 2.86e-07, "litellm_provider": "streamlake", "max_input_tokens": 56000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.143e-06, "supports_function_calling": true, "supports_reasoning": false, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/GLM-5.3": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/GLM-5.3-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/Kimi-K2-Instruct-0905": { "cache_read_input_token_cost": 1.43e-07, "input_cost_per_token": 5.71e-07, "litellm_provider": "streamlake", "max_input_tokens": 224000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.286e-06, "supports_function_calling": true, "supports_reasoning": false, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-r1": { "cache_read_input_token_cost": 2.29e-07, "input_cost_per_token": 5.71e-07, "litellm_provider": "streamlake", "max_input_tokens": 98304, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.286e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-v3.1": { "cache_read_input_token_cost": 2.29e-07, "input_cost_per_token": 5.71e-07, "litellm_provider": "streamlake", "max_input_tokens": 98304, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.714e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-v4-pro": { "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-v4.1-flash-1017": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "streamlake", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/deepseek-v4.1-flash-260910": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "streamlake", "max_input_tokens": 1048568, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/glm-5": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "litellm_provider": "streamlake", "max_input_tokens": 202752, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/glm-5.1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "streamlake", "max_input_tokens": 202752, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/glm-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "streamlake", "max_input_tokens": 1048566, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "streamlake", "max_input_tokens": 262144, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, "supports_vision": true, "supports_reasoning": false, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "streamlake", "max_input_tokens": 262144, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/mimo-v2.6-flash": { "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, "litellm_provider": "streamlake", "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/mimo-v2.6-pro": { "cache_read_input_token_cost": 3.6e-09, "input_cost_per_token": 4.35e-07, "litellm_provider": "streamlake", "mode": "chat", "output_cost_per_token": 8.7e-07, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/minimax-m2.5": { "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "streamlake", "max_input_tokens": 196608, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/minimax-m3": { "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_above_512k_tokens": 2.4e-07, "input_cost_per_token": 6e-07, "input_cost_per_token_above_512k_tokens": 1.2e-06, "litellm_provider": "streamlake", "max_input_tokens": 1000000, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_above_512k_tokens": 4.8e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/qwen3.5-397b-a17b": { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "streamlake", "max_input_tokens": 258048, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/qwen3.6-27b": { "input_cost_per_token": 6e-07, "litellm_provider": "streamlake", "max_input_tokens": 229376, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, "supports_vision": true, "supports_reasoning": false, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/qwen3.6-35b-a3b": { "input_cost_per_token": 3.75e-07, "litellm_provider": "streamlake", "max_input_tokens": 229376, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true, "supports_vision": true, "supports_reasoning": false, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/qwen3.8-2.4t-a95b": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "streamlake", "max_input_tokens": 983616, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "cache_creation_input_token_cost": 2.5e-06, "explicit_cache_read_input_token_cost": 1.7e-07, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "streamlake/qwen3.8-27b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "streamlake", "max_input_tokens": 983616, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "cache_creation_input_token_cost": 6.25e-07, "explicit_cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce" }, "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 6.6e-07, "output_cost_per_token": 1.98e-06, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 3.96e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "deepseek/deepseek-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 23, "token_count_tool_framing": 12 }, "deepseek/deepseek-flash-latest": { "alias_of": "deepseek/deepseek-v4-flash" }, "deepseek/deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "deepseek/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 6.6e-07, "output_cost_per_token": 1.98e-06, "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 3.96e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, "token_count_framing": 76, "token_count_tool_framing": 75 }, "deepseek/deepseek-pro-latest": { "alias_of": "deepseek/deepseek-v4-pro" }, "tencent/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "input_cost_per_token_cache_hit": 1.45e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false }, "tencent/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, "input_cost_per_token_cache_hit": 2.8e-09, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false }, "tencent/deepseek-v4-pro-0813": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 6.6e-07, "output_cost_per_token": 1.98e-06, "weekday_timezone": "Asia/Shanghai", "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 3.96e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false }, "tencent/deepseek-v4.1-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "weekday_timezone": "Asia/Shanghai", "windows": [ { "hours_utc": [ "00:00-01:00", "04:00-06:00", "10:00-00:00" ], "weekdays": [ 1, 2, 3, 4, 5 ] }, { "hours_utc": "00:00-00:00", "weekdays": [ 6, 7 ] } ] }, "output_cost_per_token": 1.2e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true }, "tencent/glm-5.3-flashx": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 3.7e-07, "input_cost_per_token_cache_hit": 7.5e-08, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "tencent/glm-5.3-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_cache_hit": 3e-08, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "tencent/glm-5.3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "input_cost_per_token_cache_hit": 2.6e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/glm-5.2": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "input_cost_per_token_cache_hit": 2.6e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/kimi-k3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_cache_hit": 3e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/kimi-k2.8-preview": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_cache_hit": 2.5e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/kimi-k2.7-code-highspeed": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 3.8e-07, "input_cost_per_token": 1.9e-06, "input_cost_per_token_cache_hit": 3.8e-07, "litellm_provider": "tencent", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/kimi-k2.7-code": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "input_cost_per_token_cache_hit": 1.9e-07, "litellm_provider": "tencent", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "tencent/hy4": { "cache_read_input_token_cost": 2.1e-08, "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", "input_cost_per_token": 4.17e-07, "input_cost_per_token_cache_hit": 2.1e-08, "litellm_provider": "tencent", "max_input_tokens": 960000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.2505e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "tencent/hy4-preview": { "cache_read_input_token_cost": 2.1e-08, "comment": "These are the 50% promotional rates. Update on 2026-12-31 when the promotion ends at 23:59:59 Beijing time. List rates per 1M tokens are $0.834 input, $2.501 output and $0.042 cached input.", "input_cost_per_token": 4.17e-07, "input_cost_per_token_cache_hit": 2.1e-08, "litellm_provider": "tencent", "max_input_tokens": 960000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.2505e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "tencent/minimax-m3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_cache_hit": 6e-08, "litellm_provider": "tencent", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, "tencent/seedream-image-v5.0-flash": { "litellm_provider": "tencent", "mode": "image_generation", "output_cost_per_image": 0.018, "output_cost_per_image_token": 1.6e-06, "source": "https://cloud.tencent.com/document/product/1823/130055", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "tencent/seedream-image-v5.0-lite": { "litellm_provider": "tencent", "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_image_token": 1.6e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "tencent/seedream-image-v5.0-pro": { "litellm_provider": "tencent", "mode": "image_generation", "output_cost_per_image": 0.09, "output_cost_per_image_token": 1.6e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "cognition/swe-1.6": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "litellm_provider": "cognition", "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "source": "https://docs.devin.ai/windsurf/plugins/cascade/models" }, "cognition/swe-1.7": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "litellm_provider": "cognition", "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "source": "https://docs.devin.ai/desktop/models" }, "cognition/swe-1.7-lightning": { "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.25e-05, "cache_read_input_token_cost": 1e-06, "litellm_provider": "cognition", "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": true, "source": "https://docs.devin.ai/desktop/models" }, "pinstripes/ps/glm-4.5-air": { "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.25e-07, "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-08, "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 6e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": false, "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1e-07, "output_cost_per_token": 2e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { "max_input_tokens": 1000192, "max_output_tokens": 1000192, "input_cost_per_token": 2.55e-07, "output_cost_per_token": 5.5e-07, "litellm_provider": "pinstripes", "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": false, "source": "https://pinstripes.io/" }, "darkbloom/gemma-4-26b": { "input_cost_per_token": 3e-08, "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.65e-07, "source": "https://www.darkbloom.dev/", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_system_messages": true, "supports_tool_choice": true }, "darkbloom/gpt-oss-20b": { "input_cost_per_token": 1.45e-08, "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://www.darkbloom.dev/", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_system_messages": true, "supports_tool_choice": true }, "xai/grok-4.20-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-0309": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ "/v1/responses" ] }, "xai/grok-build-0.1": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1e-06, "supports_response_schema": true, "supports_vision": true }, "gpt-transcribe": { "input_cost_per_second": 7.5e-05, "litellm_provider": "openai", "mode": "audio_transcription", "provider_specific_entry": { "transcription_json_or_text_only": 1, "transcription_usage_duration": 1 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_native_streaming": true }, "gpt-live-transcribe": { "input_cost_per_second": 0.000283333333333, "litellm_provider": "openai", "mode": "audio_transcription", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_native_streaming": true }, "gpt-live-1": { "input_cost_per_second": 0.000833333333333, "litellm_provider": "openai", "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true }, "gpt-realtime-translate": { "input_cost_per_second": 0.000566666666667, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true }, "claude-mythos-5": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "provider_specific_entry": { "us": 1.1 } }, "claude-mythos-5-1": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-mythos-5-2": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "input_cost_per_token_batches": 4e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "output_cost_per_token_batches": 2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "fast": 2, "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_fast_mode": true, "supports_speed": true }, "claude-mythos-preview": { "deprecation_date": "2026-06-09", "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/models/overview", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "provider_specific_entry": { "us": 1.1 } }, "gemini/gemini-robotics-er-2-streaming-preview": { "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_reasoning": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "mistral/mistral-small-2603": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/labs-leanstral-1-5": { "deprecation_date": "2026-09-30", "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-moderation-2603": { "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 131072, "mode": "moderation", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03" }, "mistral/voxtral-mini-2602": { "deprecation_date": "2027-04-30", "input_cost_per_second": 5e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-transcribe-realtime-2602": { "deprecation_date": "2027-04-30", "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-tts-2603": { "deprecation_date": "2027-04-30", "input_cost_per_character": 1.6e-05, "litellm_provider": "mistral", "mode": "audio_speech", "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": true }, "fallback_generalizations": { "rules": [ { "name": "bedrock-claude-ids", "pattern": "^(?:[a-z-]+\\.)?anthropic\\.claude-", "description": "A Bedrock-syntax Claude id, for every version: anthropic.claude- at the start of the name, optionally behind a single dotted geo segment (us./eu./au./jp./apac./global./us-gov.). Anchored to the start because routing rules see the raw request string and provider inference feeds the proxy's provider/* wildcard access checks: an id under an unrecognized namespace such as bedrockz/anthropic.claude-... must stay unroutable rather than resolve to bedrock and slip through a bedrock/* key. Routes to bedrock before the bare-id Anthropic rule is consulted.", "model_info": { "litellm_provider": "bedrock" } }, { "name": "anthropic-claude-ids", "pattern": "^claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?$", "description": "A bare Claude family-major id with an optional minor and an optional 8-digit date suffix, anchored to the whole name, so claude-newfamily-5 routes like claude-newfamily-5-1 does. Routes an unmapped Claude id that carries no provider namespace to the Anthropic API.", "model_info": { "litellm_provider": "anthropic" } }, { "name": "typesafe-jev-ids", "pattern": "^jev-(?:latest|preview|1\\.13\\.0|1\\.14\\.0)$", "description": "A bare Jev id that has a typesafe/ price entry (jev-latest, jev-preview, jev-1.13.0, jev-1.14.0), the name the /typesafe pass-through forwards to TypeSafe. Listed by name, matched case-insensitively like every rule here, so foo/jev-latest or a model group named like a Jev id TypeSafe does not serve, such as jev-1.0 or jev-internal-router, never resolves to typesafe. A new Jev version goes here together with its price entry. Provider inference feeds the proxy's provider/* wildcard access checks, so this rule is what lets typesafe/* on a key, team or project allowlist cover a jev-latest request.", "model_info": { "litellm_provider": "typesafe" } }, { "name": "claude-family-baseline", "pattern": "claude-[a-z]+-\\d+(?:[-.]\\d+)?(?:-\\d{8})?", "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], "description": "Any Claude family-major id with an optional minor and an optional 8-digit date suffix, under any provider namespace (bare, bedrock-dotted, vertex, databricks, ...), so bare majors like claude-newfamily-5 get the same baseline as claude-newfamily-5-1. Carries the model-family facts every Claude shares; it carries no pricing, so cost stays on the standard unpriced behavior rather than a guessed number. On mapped Claude entries from Anthropic, Azure Foundry, Bedrock and Vertex it only fills the keys an entry leaves out, so the entry's own values always win.", "model_info": { "mode": "chat", "max_input_tokens": 200000, "max_output_tokens": 64000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_system_messages": true } }, { "name": "claude-adaptive-thinking", "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], "description": "Claude at version 4.6 or higher, in any id shape that contains claude--: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.", "model_info": { "supports_adaptive_thinking": true } }, { "name": "claude-legacy-thinking", "pattern": "claude-[a-z]+-4[-._]6(?!\\d)", "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], "description": "Claude at version 4.6 exactly, in any id shape that contains claude--4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.", "model_info": { "supports_legacy_thinking": true } }, { "name": "claude-always-on-thinking", "pattern": "claude-(?:fable|mythos)-", "description": "Any Claude Fable or Mythos id, under any provider namespace and any version. These families always think and reject thinking.type=disabled with a 400; the Anthropic transformations omit the param instead, so the model falls back to its default adaptive thinking.", "model_info": { "thinking_always_on": true } }, { "name": "claude-thinking-on-by-default", "pattern": "claude-[a-z]+-[5-9](?!\\d)", "description": "Claude at major 5 or higher, in any id shape that contains claude--. Anthropic's thinking docs list every Claude 5+ model as thinking by default (on or always on) when the request sends no thinking param, and every 4.x as off. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. The response_format json tool is then left unforced, since a forced tool call skips the model's thinking.", "model_info": { "thinking_on_by_default": true } }, { "name": "claude-mid-conversation-system", "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], "description": "Claude at version 4.8 or higher, in any id shape that contains claude--: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.", "model_info": { "supports_mid_conversation_system": true } }, { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true } }, { "name": "claude-per-turn-control", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", "fill_missing_for_providers": ["bedrock", "bedrock_converse"], "description": "Claude at version 4.5 or higher, with the same id shapes and version boundaries as claude-tool-search. On 2026-11-05 Bedrock InvokeModel answered 200 with the per-turn-control-2026-07-01 beta on every Claude 4.5 and newer model a QA account reached across 13 regions, and 400 invalid beta flag on Claude 3 Haiku in ca-central-1. The jp., au. and in. profiles answered 200 too, AWS lists no apac. profile for Claude 4.5 or newer, and GovCloud was not tested. Claude 3.5, 3.7, Sonnet 4, Opus 4 and Opus 4.1 were unreachable, so they keep the beta dropped as before. The flag means Bedrock accepts the beta name on the model, as supports_tool_search does for the tool search beta, and Bedrock Invoke forwards the beta only where it is set. It does not promise per-turn output_config works, since on 2026-11-05 Opus 4.8, Opus 5, Sonnet 5 and Fable 5 rejected it with or without the beta. A deployment turns the forward off with model_info supports_per_turn_control false.", "model_info": { "supports_per_turn_control": true } }, { "name": "wandb-reasoning-baseline", "pattern": "^wandb/", "description": "Any Weights & Biases Inference model id, anchored to the wandb/ namespace so only that provider's ids match. W&B's serverless catalog is reasoning-first and grows faster than this registry names it, so an id the map has not described yet is treated as reasoning-capable and keeps the caller's reasoning_effort instead of dropping it or raising UnsupportedParamsError. Rules lose to exact entries, so a mapped non-reasoning model such as wandb/meta-llama/Llama-3.1-8B-Instruct is unaffected. Carries no mode and no pricing, so cost stays on the standard unpriced behavior and the deployment does not read as catalog-mapped to the router's reasoning-effort resolver.", "model_info": { "supports_reasoning": true } }, { "name": "minimax-reasoning-baseline", "pattern": "^minimax/", "description": "Any MiniMax model id under the minimax/ namespace, anchored so only that provider's ids match. MiniMax ships reasoning models faster than this registry names them, so an id the map has not described yet is treated as reasoning-capable and keeps the caller's reasoning_effort and thinking instead of dropping them. Rules lose to exact entries, so mapped speech, video and image models are unaffected. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", "model_info": { "supports_reasoning": true } }, { "name": "openai-reasoning-family-baseline", "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", "fill_missing_for_providers": ["azure", "azure_ai", "openai"], "description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", "model_info": { "supports_reasoning": true } }, { "name": "gemini-chat-baseline", "pattern": "gemini-(?!.*(?:-tts|-image|-live|-audio|-embedding|-computer-use|-robotics|-transcribe|-translate))(?:2[.-][5-9]|[3-9](?:[.-]\\d{1,2})?)-(?:pro|flash)(?:-lite)?(?![a-z])", "description": "Any Gemini text-chat id at 2.5 or higher under any namespace, including bare ids, gemini/, vertex_ai/, openrouter/google/, deepinfra/google/, vercel_ai_gateway/google/, oci/google., and databricks-gemini--: gemini-[.minor]-(pro|flash)[-lite] with any trailing preview, date or variant tag. The capability flags were verified against each of those providers' own catalogs and docs. The lookahead excludes the tts, image, live, audio, embedding, computer-use, robotics, transcribe and translate lines, which are different modes with different capabilities. Provider-specific deviations, such as Perplexity's Agent API serving these as mode responses, are carried by their exact map entries, which always win over this rule. Carries no token limits or pricing, so those stay on the standard unmapped behavior rather than a guessed number. Source check 2026-09-15: all 45 first-party 2.5+ text-chat entries in this map carry every field below, and the OpenRouter (openrouter.ai/api/v1/models), Vercel AI Gateway (ai-gateway.vercel.sh/v1/models), DeepInfra (api.deepinfra.com/models/list), OCI and Databricks model docs list reasoning, tools and image input for the same models.", "model_info": { "mode": "chat", "supports_reasoning": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_vision": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true } } ] }, "gemini/gemini-3.5-live-translate-preview": { "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, "rpm": 10, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "audio", "text" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": false, "supports_response_schema": false, "supports_web_search": false, "tpm": 250000 }, "gemini/gemini-3.5-transcribe": { "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "gemini", "max_input_tokens": 98304, "max_output_tokens": 32768, "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "tpm": 800000, "rpm": 2000, "supports_function_calling": false }, "gemini/gemini-3.5-transcribe-live": { "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "tpm": 250000, "rpm": 10, "supports_function_calling": false }, "vertex_ai/gemini-3.5-transcribe-preview": { "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "vertex_ai/gemini-3.5-transcribe-live-preview": { "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "vertex_ai/gemini-3.5-live-translate-preview": { "input_cost_per_audio_token": 3.5e-06, "input_cost_per_second": 8.75e-05, "input_cost_per_token": 3.5e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "audio", "text" ], "supports_audio_input": true, "supports_audio_output": true }, "perplexity/pplx-embed-context-v1-0.6b": { "input_cost_per_token": 8e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.perplexity.ai/getting-started/pricing" }, "perplexity/pplx-embed-context-v1-4b": { "input_cost_per_token": 5e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, "source": "https://docs.perplexity.ai/getting-started/pricing" }, "voyage/voyage-4-large": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-4": { "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-4-lite": { "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-code-4": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-context-4": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing" }, "voyage/voyage-multimodal-3.5": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, "source": "https://docs.voyageai.com/docs/pricing", "supports_embedding_image_input": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { "cache_read_input_token_cost": 6e-09, "cache_read_input_token_cost_priority": 7.5e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_response_schema": true }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/kimi-latest": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-latest": { "alias_of": "fireworks_ai/accounts/fireworks/models/kimi-k3" }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/deepseek-v4p1-flash": { "cache_read_input_token_cost": 6e-09, "cache_read_input_token_cost_priority": 7.5e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "token_count_framing": 23, "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "supports_response_schema": true }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/changelog.md", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/kimi-k3": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-k3-fast": { "cache_read_input_token_cost": 4.5e-07, "input_cost_per_token": 4.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/qwen3p8-max": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_priority": 9e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_priority": 1.25e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/muse-spark-open": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 1.875e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "output_cost_per_token_priority": 6.375e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_priority": 1.25e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 5e-08, "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 6e-07, "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "successor_model": "Nemotron Super VL", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/qwen3p8-max": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_priority": 9e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/qwen-max-latest": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_priority": 9e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us": { "cache_read_input_token_cost": 2.1e-07, "deprecation_date": "2026-09-25", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/glm-5p3", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/kimi-k3-fast": { "cache_read_input_token_cost": 4.5e-07, "input_cost_per_token": 4.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/kimi-fast-latest": { "cache_read_input_token_cost": 4.5e-07, "input_cost_per_token": 4.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/kimi-k3-us": { "cache_read_input_token_cost": 4.5e-07, "cache_read_input_token_cost_priority": 5.625e-07, "input_cost_per_token": 4.5e-06, "input_cost_per_token_priority": 5.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/zai-org/glm-5.3": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 1.32e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/moonshotai/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/tencent/hy3": { "cache_read_input_token_cost": 3.5e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/zai-org/glm-5.2": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/moonshotai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.499999999999999e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/deepseek/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/deepseek/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/mindai/macaron-v1-venti": { "cache_read_input_token_cost": 1.65e-07, "input_cost_per_token": 8.25e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.475e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/minimax/minimax-m3": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/deepseek/deepseek-v4-flash": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-v4-pro": { "cache_read_input_token_cost": 1.35e-07, "input_cost_per_token": 1.6000000000000001e-06, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/inclusionai/ling-3.0-flash-fast": { "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 6e-08, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/qwen/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/inclusionai/ling-3.0-flash": { "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 6e-08, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/mindai/macaron-v1-tall": { "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 2.475e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.43e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/stepfun/step-3.7-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2.0000000000000002e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/nvidia/nemotron-3-nano-30b-a3b": { "input_cost_per_token": 5.0000000000000004e-08, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.0000000000000002e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/baidu/cobuddy": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 2.8e-07, "litellm_provider": "novita", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.13e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/xiaomimimo/mimo-v2.5": { "cache_read_input_token_cost": 3.4e-09, "input_cost_per_token": 1.6800000000000002e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.3600000000000004e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/qwen/qwen3.7-max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/xiaomimimo/mimo-v2.5-pro": { "cache_read_input_token_cost": 4.3e-09, "input_cost_per_token": 5.22e-07, "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.044e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/qwen/qwen3.6-27b": { "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/moonshotai/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 8.000000000000001e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/zai-org/glm-5.1": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.38e-06, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/minimax/minimax-m2.7-highspeed": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/zai-org/glm-5v-turbo": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1.3e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/google/gemma-4-31b-it": { "input_cost_per_token": 1.4e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/zai-org/glm-5-turbo": { "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/minimax/minimax-m2.7": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/minimax/minimax-m2.5-highspeed": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/qwen/qwen3.5-27b": { "input_cost_per_token": 3e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/qwen/qwen3.5-122b-a10b": { "input_cost_per_token": 4.0000000000000003e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/qwen/qwen3.5-35b-a3b": { "input_cost_per_token": 2.5e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/qwen/qwen3.5-397b-a17b": { "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/minimax/minimax-m2.5": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/zai-org/glm-5": { "cache_read_input_token_cost": 2.0000000000000002e-07, "input_cost_per_token": 1e-06, "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/qwen/qwen3-coder-next": { "input_cost_per_token": 2.0000000000000002e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-ocr-2": { "input_cost_per_token": 3e-08, "litellm_provider": "novita", "max_input_tokens": 8192, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://novita.ai/pricing", "supports_vision": true }, "novita/moonshotai/kimi-k2.5": { "cache_read_input_token_cost": 1.0000000000000001e-07, "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/zai-org/glm-4.7-h": { "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 6e-07, "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/zai-org/glm-4.7-flash": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 7e-08, "litellm_provider": "novita", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/qwen/qwen3.6-35b-a3b": { "input_cost_per_token": 2.48e-07, "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.4850000000000002e-06, "source": "https://novita.ai/pricing", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "novita/deepseek/deepseek_v3": { "input_cost_per_token": 8.900000000000001e-07, "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-r1": { "input_cost_per_token": 4e-06, "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-v3/community": { "input_cost_per_token": 8.900000000000001e-07, "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false }, "novita/deepseek/deepseek-r1/community": { "input_cost_per_token": 4e-06, "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "novita/thudm/glm-4-32b-0414": { "input_cost_per_token": 5.5e-07, "litellm_provider": "novita", "max_input_tokens": 32000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.66e-06, "source": "https://api.novita.ai/v3/openai/models", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "novita/meta-llama/llama-3.2-1b-instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "novita", "max_input_tokens": 131000, "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.novita.ai/v3/openai/models", "supports_response_schema": true, "supports_vision": false }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 7e-08, "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 2.7e-07, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/ibm-granite/granite-4.1-8b": { "deprecation_date": "2026-10-05", "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { "deprecation_date": "2026-10-05", "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { "deprecation_date": "2026-10-05", "max_output_tokens": 128000, "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1.2e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, "cache_read_input_token_cost": 1.5e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7e-08, "output_cost_per_token": 2e-07, "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/OpenPipe/Qwen3-14B-Instruct": { "deprecation_date": "2026-10-05", "max_output_tokens": 32768, "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1.5e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.6-35B-A3B": { "cache_read_input_token_cost": 3.5e-08, "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 8.9e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_prompt_caching": true }, "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, "cache_read_input_token_cost": 1.2e-07, "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.5-35B-A3B": { "deprecation_date": "2026-10-05", "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "wandb", "mode": "chat", "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { "deprecation_date": "2026-10-05", "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V4-Pro-0813": { "litellm_provider": "wandb", "mode": "chat", "supports_reasoning": true, "input_cost_per_token": 1.31e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, "max_input_tokens": 1049000, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/ibm-granite/granite-4.2-8b": { "litellm_provider": "wandb", "mode": "chat", "supports_reasoning": true, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.5e-07, "cache_read_input_token_cost": 1.5e-08, "max_input_tokens": 131000, "supports_prompt_caching": true, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.2e-07, "output_cost_per_token": 2.42e-06, "cache_read_input_token_cost": 1.4e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference" }, "deepinfra/openai/gpt-oss-120b-Turbo": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7": { "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1e-06, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-27B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-Ultra": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 7.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.5": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 2.25e-06, "cache_read_input_token_cost": 7e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7-Flash": { "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 1e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.6": { "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-8": { "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 1024, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "deepinfra", "mode": "chat", "prompt_cache_min_tokens": 1024, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_adaptive_thinking": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.5-flash": { "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 8e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.4e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-turbo": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.4e-07, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/thinkingmachines/Inkling-Small": { "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-models/Muse-Glimmer-30B": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max-Thinking": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.4e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 8.8e-07, "cache_read_input_token_cost": 1.1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-27B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 2.6e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.6-35B-A3B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 9.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-5": { "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 512, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4.05e-06, "cache_read_input_token_cost": 1.6e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.6": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 1.5e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.7-Max": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, "cache_read_input_token_cost": 5e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-mini": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 2e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M3": { "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, "cache_read_input_token_cost": 5.6e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-flash-lite": { "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/inclusionAI/Ling-3.0-flash": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 1.2e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-35B-A3B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1e-06, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-1.8": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, "cache_read_input_token_cost": 5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/tencent/Hy3": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, "cache_read_input_token_cost": 3.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-code": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-pro": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5": { "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.08e-06, "cache_read_input_token_cost": 1.2e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, "cache_read_input_token_cost": 2.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.7-Code": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 6.8e-07, "output_cost_per_token": 3.4e-06, "cache_read_input_token_cost": 1.36e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-sonnet-5": { "input_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.5e-05, "prompt_cache_min_tokens": 1024, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 2.2e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 1.5e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-E4B-it": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.2": { "max_output_tokens": 163840, "max_input_tokens": 163840, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 3.8e-07, "cache_read_input_token_cost": 1.3e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-Max": { "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, "cache_read_input_token_cost": 2.06e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-fable-5": { "input_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.2e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-122B-A10B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.9e-07, "output_cost_per_token": 2.4e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.1": { "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 1.05e-06, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 2.05e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.2": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 2.4e-06, "cache_read_input_token_cost": 1.4e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K3": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 2.85e-06, "output_cost_per_token": 1.425e-05, "cache_read_input_token_cost": 2.85e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-7": { "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 2048, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-26B-A4B-it": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7e-08, "output_cost_per_token": 3.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-pro": { "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 2e-07, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-haiku-4-5": { "max_output_tokens": 200000, "max_input_tokens": 200000, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "mode": "chat", "prompt_cache_min_tokens": 4096, "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, "cache_read_input_token_cost": 1.8e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4.2e-07, "cache_read_input_token_cost": 4.2e-09, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash" }, "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4.2e-07, "cache_read_input_token_cost": 4.2e-09, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" }, "deepinfra/openai/gpt-oss-120b-Ultra": { "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 9.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-9B": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.7e-06, "cache_read_input_token_cost": 7e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7": { "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.75e-06, "cache_read_input_token_cost": 8e-08, "supports_prompt_caching": true, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": false, "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it": { "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, "source": "https://deepinfra.com/pricing" }, "gemini/gemini-omni-1.1-flash": { "deprecation_date": "2026-12-03", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", "successor_model": "gemini/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, "tpm": 800000 }, "xai/grok-4.20": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-imagine-image": { "input_cost_per_image": 0.02, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-2026-03-02": { "input_cost_per_image": 0.02, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-quality": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-quality-20260403": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-quality-latest": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-pro": { "deprecation_date": "2026-05-15", "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-image-2.0": { "input_cost_per_image": 0.06, "litellm_provider": "xai", "mode": "image_generation", "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-imagine-video": { "input_cost_per_image": 0.002, "litellm_provider": "xai", "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://docs.x.ai/docs/models/grok-imagine-video", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "xai/grok-imagine-video-1.5": { "input_cost_per_image": 0.01, "litellm_provider": "xai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.25, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "video" ] }, "xai/grok-imagine-video-1.5-lite": { "input_cost_per_image": 0.01, "litellm_provider": "xai", "mode": "video_generation", "output_cost_per_second": 0.02, "output_cost_per_second_1080p": 0.14, "output_cost_per_second_480p": 0.02, "output_cost_per_second_720p": 0.03, "source": "https://docs.x.ai/developers/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "xai/grok-imagine-video-1.5-2026-05-30": { "input_cost_per_image": 0.01, "litellm_provider": "xai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.25, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "video" ] }, "xai/grok-imagine-video-1.5-preview": { "input_cost_per_image": 0.01, "litellm_provider": "xai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.25, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "video" ] }, "xai/grok-voice-transcribe-1.0": { "deprecation_date": "2026-10-02", "deprecation_source": "https://docs.x.ai/docs/release-notes", "successor_model": "xai/grok-voice-transcribe-2.0", "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { "calculation": "$0.10/3600 seconds = $0.00002778 per second", "original_pricing_per_hour": 0.1 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://docs.x.ai/developers/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "xai/grok-voice-transcribe-2.0": { "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { "calculation": "$0.10/3600 seconds = $0.00002778 per second", "original_pricing_per_hour": 0.1 }, "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://docs.x.ai/developers/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "low/1024-x-1024/grok-imagine-image-2.0": { "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", "source": "https://docs.x.ai/docs/models", "supported_endpoints": [ "/v1/images/generations" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-non-reasoning-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-07, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-medium-3.5": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-vibe-cli-latest": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-vibe-cli-with-tools": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-vibe-cli-fast": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ "none", "high" ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/mistral-code-latest": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/mistral-code-fim-latest": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/mistral-code-agent-latest": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "reasoning_effort_levels": [ "none", "high" ], "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/mistral-ocr-3": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, "ocr_cost_per_page_batches": 0.001, "annotation_cost_per_page": 0.003, "annotation_cost_per_page_batches": 0.0015, "mode": "ocr", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-3-0": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, "ocr_cost_per_page_batches": 0.001, "annotation_cost_per_page": 0.003, "annotation_cost_per_page_batches": 0.0015, "mode": "ocr", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4": { "annotation_cost_per_page": 0.005, "annotation_cost_per_page_batches": 0.0025, "litellm_provider": "mistral", "mode": "ocr", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", "supported_endpoints": [ "/v1/ocr", "/v1/batch" ] }, "mistral/voxtral-mini-latest": { "input_cost_per_second": 5e-05, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-realtime-2602": { "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/voxtral-mini-realtime-latest": { "input_cost_per_second": 0.0001, "litellm_provider": "mistral", "mode": "audio_transcription", "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true }, "mistral/labs-leanstral-1-5-1": { "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "supports_function_calling": true, "supports_response_schema": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, "cache_read_input_token_cost_priority": 3.25e-07, "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/glm-latest": { "cache_read_input_token_cost": 2.6e-07, "cache_read_input_token_cost_priority": 3.25e-07, "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-5p3": { "cache_read_input_token_cost": 2.6e-07, "cache_read_input_token_cost_priority": 3.25e-07, "input_cost_per_token": 1.4e-06, "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/glm-fast-latest": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/auto": { "litellm_provider": "fireworks_ai", "mode": "chat", "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/routers/auto-instant": { "litellm_provider": "fireworks_ai", "mode": "chat", "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/routers/firerouter": { "litellm_provider": "fireworks_ai", "mode": "chat", "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/glm-flash-latest": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, "cache_read_input_token_cost_priority": 5.625e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, "cache_read_input_token_cost_priority": 5.625e-08, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/changelog.md", "input_cost_per_token": 2.25e-07, "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/changelog.md", "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, "cache_read_input_token_cost_priority": 1.7e-07, "deprecation_date": "2026-11-07", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1e-06, "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, "output_cost_per_token_priority": 4.05e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "successor_model": "fireworks_ai/accounts/fireworks/models/muse-spark-open", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b": { "input_cost_per_token": 1e-07, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", "max_input_tokens": 40960, "max_output_tokens": 40960, "mode": "embedding", "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "zai/glm-5.2": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "zai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.z.ai/guides/overview/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "zerogpu/deepseek-v4.1-flash": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 3e-07, "litellm_provider": "zerogpu", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/glm-5.3-flash": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "zerogpu", "max_input_tokens": 1048576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4e-07, "litellm_provider": "zerogpu", "max_input_tokens": 1047576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "zerogpu", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/gpt-5.6-luna": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-07, "litellm_provider": "zerogpu", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/gpt-6-luna": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "zerogpu", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "zerogpu/gpt-oss-120b": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "zerogpu", "max_input_tokens": 128000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/LFM2.5-1.2B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "zerogpu", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-08, "source": "https://docs.zerogpu.ai/docs/model-catalog" }, "zerogpu/LFM2.5-1.2B-Thinking": { "input_cost_per_token": 2e-08, "litellm_provider": "zerogpu", "max_input_tokens": 32768, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-08, "source": "https://docs.zerogpu.ai/docs/model-catalog" }, "zerogpu/llama-3.1-8b-instruct-fast": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "zerogpu", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/llama-3.2-3b-instruct-fast": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 5e-08, "litellm_provider": "zerogpu", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog" }, "zerogpu/qwen3-30b-a3b-fp8": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "zerogpu", "max_input_tokens": 32768, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 4.5e-07, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "zerogpu/qwen3.6-35b-a3b": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-07, "litellm_provider": "zerogpu", "max_input_tokens": 262144, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.zerogpu.ai/docs/model-catalog", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/Qwen/Qwen3.8-Flash": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/qwen-flash-latest": { "alias_of": "together_ai/Qwen/Qwen3.8-Flash" }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, "output_cost_per_token": 2.8e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "together_ai/MiniMaxAI/MiniMax-M2.7": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, "litellm_provider": "together_ai", "max_input_tokens": 196608, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, "output_cost_per_token": 7e-06, "litellm_provider": "together_ai", "max_input_tokens": 163840, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "deprecation_date": "2026-02-25", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-7B-Instruct-v0.3": { "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, "mode": "chat", "source": "https://api.together.ai/v1/models" }, "cerebras/gemma-4-31b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 40960, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "elevenlabs/scribe_v2": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", "mode": "audio_transcription", "output_cost_per_second": 0.0, "source": "https://elevenlabs.io/pricing/api", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "scaleway/glm-5.2": { "deprecation_date": "2026-11-16", "input_cost_per_token": 1.8e-06, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false }, "scaleway/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 4e-07, "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, "azure_ai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "deprecation_date": "2027-04-16", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/deepseek-v4.1-flash": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "deprecation_date": "2026-12-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" }, "azure_ai/MAI-Image-2.6": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 3.8e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure_ai/MAI-Image-2.6-Flash": { "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 1.9e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure_ai/FW-DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 8e-09, "input_cost_per_token": 3.75e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-DeepSeek-V4-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.3": { "cache_read_input_token_cost": 3.25e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/glm-latest": { "alias_of": "azure_ai/FW-GLM-5.3" }, "azure_ai/FW-GLM-5.3-Flash": { "cache_read_input_token_cost": 3.8e-08, "input_cost_per_token": 1.88e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/glm-flash-latest": { "alias_of": "azure_ai/FW-GLM-5.3-Flash" }, "azure_ai/FW-GPT-OSS-120B": { "deprecation_date": "2027-07-01", "cache_read_input_token_cost": 8.2e-08, "input_cost_per_token": 1.65e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "azure_ai/Cohere-command-a-plus-05-2026": { "deprecation_date": "2026-10-16", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "coherelabs-command-a-plus-05-2026-fp81", "input_cost_per_token": 8e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/mistral-medium-3-5": { "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": false, "supports_response_schema": true, "supports_vision": true }, "azure_ai/deepseek-r1": { "deprecation_date": "2026-08-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/deepseek-v4-pro", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/deepseek-v3-0324": { "deprecation_date": "2026-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.14e-06, "output_cost_per_token": 4.56e-06, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/deepseek-v3.1": { "deprecation_date": "2026-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/deepseek-v4-flash", "input_cost_per_token": 1.23e-06, "output_cost_per_token": 4.94e-06, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/grok-3": { "deprecation_date": "2026-05-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/grok-4", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/grok-3-mini": { "deprecation_date": "2026-05-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.27e-06, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/grok-4-fast-non-reasoning": { "deprecation_date": "2026-05-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/grok-4-1-fast-non-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "azure_ai/grok-4-fast-reasoning": { "deprecation_date": "2026-05-01", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "successor_model": "azure_ai/grok-4-1-fast-reasoning", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_pdf_input": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 5.04e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 4.8e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "output_cost_per_token_batches": 3.9e-07, "output_cost_per_token_flex": 3.9e-07, "output_cost_per_token_priority": 1.365e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": { "supports_vision": false, "input_cost_per_token": 8.4e-08, "input_cost_per_token_batches": 4.2e-08, "input_cost_per_token_flex": 4.2e-08, "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "output_cost_per_token_flex": 1.8e-07, "output_cost_per_token_priority": 6.3e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": { "supports_vision": false, "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" }, "input_cost_per_token_batches": 3e-06, "output_cost_per_token_batches": 1.5e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json" }, "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6e-06, "cache_creation_input_token_cost_above_1hr": 9.6e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 4.8e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://aws.amazon.com/bedrock/pricing/", "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, "cache_creation_input_token_cost_above_1hr": 2.4e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1.2e-05, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "token_count_model": { "model": "anthropic.claude-fable-5-1", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 5.04e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 4.8e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "output_cost_per_token_batches": 3.9e-07, "output_cost_per_token_flex": 3.9e-07, "output_cost_per_token_priority": 1.365e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": { "supports_vision": false, "input_cost_per_token": 8.4e-08, "input_cost_per_token_batches": 4.2e-08, "input_cost_per_token_flex": 4.2e-08, "input_cost_per_token_priority": 1.47e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, "output_cost_per_token_flex": 1.8e-07, "output_cost_per_token_priority": 6.3e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": { "supports_vision": false, "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-east-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-east-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 7.5e-06, "cache_creation_input_token_cost_above_1hr": 1.2e-05, "cache_read_input_token_cost": 6e-07, "input_cost_per_token": 6e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_batches": 3e-06, "output_cost_per_token_batches": 1.5e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json" }, "bedrock/us-gov-east-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6e-06, "cache_creation_input_token_cost_above_1hr": 9.6e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 4.8e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-gov-east-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, "cache_creation_input_token_cost_above_1hr": 2.4e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1.2e-05, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, "bedrock/us-gov-east-1/anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 2.64e-06, "input_cost_per_token_above_272k_tokens": 5.28e-06, "cache_creation_input_token_cost": 3.3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-05, "cache_creation_input_token_cost_flex": 1.65e-06, "cache_creation_input_token_cost_priority": 6.6e-06, "cache_read_input_token_cost": 2.64e-07, "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-06, "cache_read_input_token_cost_flex": 1.32e-07, "cache_read_input_token_cost_priority": 5.28e-07, "input_cost_per_token_above_272k_tokens_flex": 2.64e-06, "input_cost_per_token_above_272k_tokens_priority": 1.056e-05, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 5.28e-06, "output_cost_per_token": 1.584e-05, "output_cost_per_token_above_272k_tokens": 2.376e-05, "output_cost_per_token_above_272k_tokens_flex": 1.188e-05, "output_cost_per_token_above_272k_tokens_priority": 4.752e-05, "output_cost_per_token_flex": 7.92e-06, "output_cost_per_token_priority": 3.168e-05, "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 2.64e-07, "input_cost_per_token_above_272k_tokens": 5.28e-07, "cache_creation_input_token_cost": 3.3e-07, "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 3.3e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1.32e-06, "cache_creation_input_token_cost_flex": 1.65e-07, "cache_creation_input_token_cost_priority": 6.6e-07, "cache_read_input_token_cost": 2.64e-08, "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 2.64e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 1.056e-07, "cache_read_input_token_cost_flex": 1.32e-08, "cache_read_input_token_cost_priority": 5.28e-08, "input_cost_per_token_above_272k_tokens_flex": 2.64e-07, "input_cost_per_token_above_272k_tokens_priority": 1.056e-06, "input_cost_per_token_flex": 1.32e-07, "input_cost_per_token_priority": 5.28e-07, "output_cost_per_token": 1.584e-06, "output_cost_per_token_above_272k_tokens": 2.376e-06, "output_cost_per_token_above_272k_tokens_flex": 1.188e-06, "output_cost_per_token_above_272k_tokens_priority": 4.752e-06, "output_cost_per_token_flex": 7.92e-07, "output_cost_per_token_priority": 3.168e-06, "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 3.3e-06, "cache_read_input_token_cost": 3.3e-07, "output_cost_per_token": 1.98e-05, "search_context_cost_per_query": {"search_context_size_high":0.0144,"search_context_size_low":0.0144,"search_context_size_medium":0.0144}, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supports_web_search": true }, "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "input_cost_per_token": 1.5e-06, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 2.4e-07, "cache_read_input_token_cost_batches": 1.2e-07, "cache_read_input_token_cost_flex": 1.2e-07, "cache_read_input_token_cost_priority": 4.2e-07, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.625e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "output_cost_per_token_priority": 5.25e-06 }, "bedrock_mantle/us-gov-west-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, "cache_read_input_token_cost_flex": 3.3e-07, "cache_read_input_token_cost_priority": 1.155e-06, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.96e-06, "output_cost_per_token_priority": 1.386e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/google.gemma-4-e2b": { "input_cost_per_token": 4.8e-08, "input_cost_per_token_flex": 2.4e-08, "input_cost_per_token_priority": 8.4e-08, "output_cost_per_token": 9.6e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token_batches": 4.8e-08, "output_cost_per_token_flex": 4.8e-08, "output_cost_per_token_priority": 1.68e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.56e-07, "input_cost_per_token_batches": 7.8e-08, "input_cost_per_token_flex": 7.8e-08, "input_cost_per_token_priority": 2.73e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token_batches": 2.4e-07, "output_cost_per_token_flex": 2.4e-07, "output_cost_per_token_priority": 8.4e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/google.gemma-4-31b": { "input_cost_per_token": 1.68e-07, "input_cost_per_token_batches": 8.4e-08, "input_cost_per_token_flex": 8.4e-08, "input_cost_per_token_priority": 2.94e-07, "output_cost_per_token": 4.8e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token_batches": 2.4e-07, "output_cost_per_token_flex": 2.4e-07, "output_cost_per_token_priority": 8.4e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b": { "supports_vision": false, "input_cost_per_token": 8.4e-08, "input_cost_per_token_batches": 4.2e-08, "input_cost_per_token_flex": 4.2e-08, "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 1.8e-07, "output_cost_per_token_flex": 1.8e-07, "output_cost_per_token_priority": 6.3e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b": { "supports_vision": false, "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6e-06, "cache_creation_input_token_cost_above_1hr": 9.6e-06, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 4.8e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.4e-05, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", "token_count_model": {"model":"anthropic.claude-opus-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": {"model":"anthropic.claude-sonnet-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 3.3e-06, "cache_read_input_token_cost": 3.3e-07, "output_cost_per_token": 1.98e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.md" }, "bedrock_mantle/us-gov-east-1/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, "cache_read_input_token_cost_flex": 3.3e-07, "cache_read_input_token_cost_priority": 1.155e-06, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token_flex": 3.96e-06, "output_cost_per_token_priority": 1.386e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b": { "supports_vision": false, "input_cost_per_token": 8.4e-08, "input_cost_per_token_batches": 4.2e-08, "input_cost_per_token_flex": 4.2e-08, "input_cost_per_token_priority": 1.47e-07, "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 1.8e-07, "output_cost_per_token_flex": 1.8e-07, "output_cost_per_token_priority": 6.3e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b": { "supports_vision": false, "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "bedrock_mantle/deepseek.v3.1": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 5.8e-07, "input_cost_per_token_batches": 2.9e-07, "input_cost_per_token_flex": 2.9e-07, "input_cost_per_token_priority": 1.015e-06, "output_cost_per_token": 1.68e-06, "output_cost_per_token_flex": 8.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 8.4e-07, "output_cost_per_token_priority": 2.94e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/moonshotai.kimi-k2-thinking": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 6e-07, "input_cost_per_token_batches": 3e-07, "input_cost_per_token_flex": 3e-07, "input_cost_per_token_priority": 1.05e-06, "output_cost_per_token": 2.5e-06, "output_cost_per_token_flex": 1.25e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 1.25e-06, "output_cost_per_token_priority": 4.38e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "input_cost_per_token_flex": 1.1e-07, "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 4.4e-07, "output_cost_per_token_priority": 1.54e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-32b": { "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 32000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "input_cost_per_token_flex": 7.5e-08, "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "input_cost_per_token": 4.5e-07, "input_cost_per_token_batches": 2.25e-07, "input_cost_per_token_flex": 2.25e-07, "input_cost_per_token_priority": 7.875e-07, "output_cost_per_token": 1.8e-06, "output_cost_per_token_flex": 9e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 262144, "max_output_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 9e-07, "output_cost_per_token_priority": 3.15e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" }, "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.4e-07, "input_cost_per_token_batches": 7e-08, "input_cost_per_token_flex": 7e-08, "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 6e-07, "output_cost_per_token_priority": 2.1e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 5.3e-07, "input_cost_per_token_batches": 2.6e-07, "input_cost_per_token_flex": 2.6e-07, "input_cost_per_token_priority": 9.3e-07, "output_cost_per_token": 2.66e-06, "output_cost_per_token_flex": 1.33e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "mode": "chat", "output_cost_per_token_batches": 1.33e-06, "output_cost_per_token_priority": 4.66e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, "default_reasoning_effort": "none", "input_cost_per_token": 1.71875e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.375e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "azure/us-gov/o3-mini": { "cache_read_input_token_cost": 7.57e-07, "input_cost_per_token": 1.513e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.05e-06, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us-gov/text-embedding-3-large": { "input_cost_per_token": 1.63e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, "azure/us-gov/text-embedding-3-small": { "input_cost_per_token": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, "cloudflare/@cf/openai/whisper": { "input_cost_per_second": 7.5e-06, "litellm_provider": "cloudflare", "mode": "audio_transcription", "output_cost_per_second": 0.0, "rpm": 720, "source": "https://developers.cloudflare.com/workers-ai/models/whisper/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "cloudflare/@cf/openai/whisper-large-v3-turbo": { "input_cost_per_second": 8.5e-06, "litellm_provider": "cloudflare", "mode": "audio_transcription", "output_cost_per_second": 0.0, "rpm": 720, "source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "gemini/lyria-3.5-clip-preview": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false }, "gemini/lyria-3.5-pro-preview": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "output_cost_per_image": 0.08 }, "gemini/lyria-3.5": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "output_cost_per_image": 0.08 }, "gemini/lyria-realtime-exp": { "input_cost_per_token": 0, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_function_calling": false, "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_web_search": false, "output_cost_per_image": 0.08 }, "perplexity/anthropic/claude-fable-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "cache_read_input_token_cost": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-8": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "cache_read_input_token_cost": 5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-4-6": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-sol": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 4e-06, "output_cost_per_token": 2e-05, "cache_read_input_token_cost": 4e-07, "input_cost_per_token_above_272k_tokens": 8e-06, "output_cost_per_token_above_272k_tokens": 3e-05, "cache_read_input_token_cost_above_272k_tokens": 8e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-terra": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-06, "output_cost_per_token_above_272k_tokens": 1.8e-05, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-luna": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 2e-08, "input_cost_per_token_above_272k_tokens": 4e-07, "output_cost_per_token_above_272k_tokens": 1.8e-06, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 3e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token_above_272k_tokens": 1e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.4": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token_above_272k_tokens": 5e-06, "output_cost_per_token_above_272k_tokens": 2.25e-05, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.4-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 4.5e-06, "cache_read_input_token_cost": 7.5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.4-nano": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.25e-06, "cache_read_input_token_cost": 2e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.25e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5-nano": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 5e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.3-codex": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 3.5e-06, "output_cost_per_token": 2.8e-05, "cache_read_input_token_cost": 3.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.1-pro-preview": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.8e-05, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.1-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, "cache_read_input_token_cost": 2.5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.5-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, "cache_read_input_token_cost": 1.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.5-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-4-argon": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 7.5e-06, "cache_read_input_token_cost": 1.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.7-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, "cache_read_input_token_cost": 7.5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.6": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.3": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.20-reasoning": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.20-non-reasoning": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.20-multi-agent": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/glm-5.3": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/glm-5.3-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/nemotron-3.5-lightning-30b-a3b": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "supports_reasoning": true, "input_cost_per_token": 1.15e-08, "output_cost_per_token": 1.7e-07, "cache_read_input_token_cost": 1.15e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/nemotron-3.5-super-120b-a12b": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 4e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_function_calling": true, "supports_reasoning": true, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "baseten/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/glm-latest": { "alias_of": "baseten/zai-org/GLM-5.3" }, "baseten/zai-org/GLM-5.3-Fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 128000, "max_output_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 3e-06, "input_cost_per_token": 5e-07, "input_cost_per_video_token": 3e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai", "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai", "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-3.5-transcribe": { "input_cost_per_audio_token": 2e-06, "input_cost_per_second": 5e-05, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-3.5-transcribe-live": { "input_cost_per_audio_token": 3.5e-06, "input_cost_per_second": 8.75e-05, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-omni-1.1-flash": { "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "successor_model": "vertex_ai/gemini-omni-1.2-flash" }, "vertex_ai/gemini-omni-1.1-flash-preview": { "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-1-1-flash", "successor_model": "vertex_ai/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_reasoning": true, "supports_video_input": true, "supports_vision": true }, "vertex_ai/gemma-4-26b-a4b-it": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai", "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "gpt-5.5-cyber": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 1.25e-05, "litellm_provider": "openai", "mode": "chat", "output_cost_per_token": 7.5e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_reasoning": true }, "gpt-5.5-cyber-preview": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-02-01", "deprecation_source": "https://developers.openai.com/api/docs/deprecations", "input_cost_per_token": 1.25e-05, "litellm_provider": "openai", "mode": "chat", "output_cost_per_token": 7.5e-05, "fedramp_uplift_multiplier": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_reasoning": true }, "gpt-rosalind-research": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, "together_ai/meta-llama/Llama-3.1-405B-Instruct": { "input_cost_per_token": 3.5e-06, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 4096, "max_output_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, "max_output_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, "max_output_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, "max_output_tokens": 32768 }, "together_ai/Salesforce/Llama-Rank-V1": { "deprecation_date": "2026-02-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-8B": { "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, "mode": "completion", "output_cost_per_token": 2e-07, "source": "https://api.together.xyz/v1/models" }, "together_ai/together/Tev1-4B-experimental": { "input_cost_per_token": 4.2e-08, "litellm_provider": "together_ai", "max_input_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { "deprecation_date": "2026-02-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { "deprecation_date": "2026-01-05", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "deprecation_date": "2026-06-04", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { "deprecation_date": "2026-05-14", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { "deprecation_date": "2026-04-02", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { "deprecation_date": "2026-02-25", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { "deprecation_date": "2026-02-25", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { "deprecation_date": "2026-04-16", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.5-397B-A17B": { "cache_read_input_token_cost": 3.5e-07, "deprecation_date": "2026-06-29", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3.1": { "deprecation_date": "2026-05-14", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.7e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/essentialai/rnj-1-instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.together.ai/models/rnj-1-instruct" }, "together_ai/google/gemma-4-31B-it": { "deprecation_date": "2026-09-15", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/zai-org/GLM-5.3-Flash" }, "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "deprecation_date": "2026-02-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.9e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "deprecation_date": "2026-02-25", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "deprecation_date": "2026-03-06", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "deprecation_date": "2026-04-02", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { "deprecation_date": "2026-04-16", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.6": { "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-08-19", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.7-Code": { "cache_read_input_token_cost": 1.9e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-08-27", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, "max_output_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/openai/gpt-oss-20b": { "deprecation_date": "2026-09-15", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models", "successor_model": "together_ai/Qwen/Qwen3.5-9B" }, "together_ai/zai-org/GLM-4.5-Air-FP8": { "deprecation_date": "2026-04-02", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.7": { "deprecation_date": "2026-04-02", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { "deprecation_date": "2026-06-22", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5.1": { "cache_read_input_token_cost": 2.6e-07, "deprecation_date": "2026-07-10", "deprecation_source": "https://docs.together.ai/docs/deprecations", "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models" }, "azure/eu/codex-mini": { "deprecation_date": "2026-11-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { "deprecation_date": "2027-01-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { "deprecation_date": "2027-03-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.1-codex", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-mini", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_batches": 1.375e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4-nano", "cache_read_input_token_cost": 5.5e-09, "cache_read_input_token_cost_batches": 2.75e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.2-pro", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2": { "deprecation_date": "2027-06-08", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.4", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_batches": 9.625e-08, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, "input_cost_per_token_batches": 9.625e-07, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.3-codex", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_batches": 4.125e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, "input_cost_per_token_batches": 4.125e-07, "input_cost_per_token_priority": 1.65e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_batches": 1.1e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 3.3e-05, "input_cost_per_token_above_272k_tokens": 6.6e-05, "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-6-astra": { "deprecation_date": "2028-01-11", "cache_creation_input_token_cost": 1.5e-05, "cache_creation_input_token_cost_above_272k_tokens": 3e-05, "cache_read_input_token_cost": 1.2e-06, "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, "input_cost_per_token": 1.2e-05, "input_cost_per_token_above_272k_tokens": 2.4e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6-luna": { "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 1.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 3e-07, "cache_read_input_token_cost": 1.2e-08, "cache_read_input_token_cost_above_272k_tokens": 2.4e-08, "input_cost_per_token": 1.2e-07, "input_cost_per_token_above_272k_tokens": 2.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6-sol": { "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost": 2.4e-07, "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, "input_cost_per_token": 2.4e-06, "input_cost_per_token_above_272k_tokens": 4.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "azure/eu/o1-mini": { "cache_read_input_token_cost": 6.05e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3": { "deprecation_date": "2026-11-19", "successor_model": "azure/eu/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { "deprecation_date": "2026-11-19", "successor_model": "azure/eu/gpt-5.6-sol", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6-sol", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6-terra", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/eu/gpt-5.6-terra", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-small": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-ada-002": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "gemini/gemini-3.8-live": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true, "supports_reasoning": true }, "gemini/gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, "supports_web_search": true, "supports_reasoning": true }, "azure/us/codex-mini": { "deprecation_date": "2026-11-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/computer-use-preview": { "input_cost_per_token": 3.3e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.32e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, "output_cost_per_token_priority": 1.54e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, "output_cost_per_token_priority": 3.08e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { "deprecation_date": "2027-04-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { "deprecation_date": "2027-01-14", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_batches": 6.875e-08, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "input_cost_per_token_batches": 6.875e-07, "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, "output_cost_per_token_priority": 2.2e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { "deprecation_date": "2027-03-17", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.1-codex", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-mini", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_batches": 1.375e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, "input_cost_per_token_batches": 1.375e-07, "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, "output_cost_per_token_priority": 3.96e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { "deprecation_date": "2027-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4-nano", "cache_read_input_token_cost": 5.5e-09, "cache_read_input_token_cost_batches": 2.75e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { "deprecation_date": "2027-04-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.2-pro", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { "deprecation_date": "2027-05-18", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2": { "deprecation_date": "2027-06-08", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.4", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_batches": 9.625e-08, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, "input_cost_per_token_batches": 9.625e-07, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.54e-05, "output_cost_per_token_batches": 7.7e-06, "output_cost_per_token_priority": 3.08e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { "deprecation_date": "2027-07-13", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.3-codex", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-pro": { "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_batches": 4.125e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, "input_cost_per_token_batches": 4.125e-07, "input_cost_per_token_priority": 1.65e-06, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.95e-06, "output_cost_per_token_batches": 2.475e-06, "output_cost_per_token_priority": 9.9e-06, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { "default_reasoning_effort": "none", "deprecation_date": "2027-09-21", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_batches": 1.1e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 1.375e-06, "output_cost_per_token_batches": 6.875e-07, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { "deprecation_date": "2027-09-07", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 3.3e-05, "input_cost_per_token_above_272k_tokens": 6.6e-05, "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 9.9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o1-mini": { "cache_read_input_token_cost": 6.05e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o3-deep-research": { "deprecation_date": "2026-11-19", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/us/gpt-5.6-sol", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "mode": "chat", "output_cost_per_token": 4.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-large": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-small": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-ada-002": { "deprecation_date": "2028-02-09", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-realtime-2": { "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "successor_model": "azure/gpt-realtime-2.1", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-live-1": { "deprecation_date": "2027-09-10", "input_cost_per_second": 0.000833333333333, "litellm_provider": "azure", "mode": "realtime", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true }, "azure/gpt-live-transcribe": { "deprecation_date": "2028-02-01", "input_cost_per_second": 0.000283333333333, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "audio_transcription", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "provider_specific_entry": { "realtime_ga_only": 1 }, "supports_native_streaming": true }, "azure/gpt-transcribe": { "deprecation_date": "2028-02-01", "input_cost_per_second": 7.5e-05, "litellm_provider": "azure", "mode": "audio_transcription", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime/transcription_sessions", "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "provider_specific_entry": { "realtime_ga_only": 1, "transcription_json_or_text_only": 1, "transcription_usage_duration": 1 }, "supports_native_streaming": true }, "azure/gpt-realtime-translate": { "deprecation_date": "2027-11-09", "input_cost_per_second": 0.000566666666667, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "provider_specific_entry": { "realtime_ga_only": 1 }, "supports_native_streaming": true }, "aihubmix/agnes-2.5-flash": { "input_cost_per_token": 3e-08, "litellm_provider": "aihubmix", "max_input_tokens": 512000, "max_output_tokens": 65500, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_vision": true }, "aihubmix/agnes-2.5-pro": { "cache_read_input_token_cost": 3.78e-09, "input_cost_per_token": 4.5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "aihubmix/cc-glm-5.1": { "input_cost_per_token": 6e-08, "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/claude-fable-5": { "cache_read_input_token_cost": 1.1e-06, "cache_creation_input_token_cost": 1.375e-05, "input_cost_per_token": 1.1e-05, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_sampling_params": false }, "aihubmix/claude-haiku-4-5": { "cache_read_input_token_cost": 1.1e-07, "cache_creation_input_token_cost": 1.375e-06, "input_cost_per_token": 1.1e-06, "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "prompt_cache_min_tokens": 4096 }, "aihubmix/claude-opus-4-8-think": { "cache_read_input_token_cost": 5e-07, "cache_creation_input_token_cost": 6.25e-06, "input_cost_per_token": 5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_sampling_params": false }, "aihubmix/claude-opus-5": { "cache_read_input_token_cost": 5e-07, "cache_creation_input_token_cost": 6.25e-06, "input_cost_per_token": 5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false }, "aihubmix/claude-sonnet-5": { "cache_read_input_token_cost": 2e-07, "cache_creation_input_token_cost": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_sampling_params": false }, "aihubmix/coding-glm-5.3": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/coding-kimi-k3": { "cache_read_input_token_cost": 6.6e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.61333e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/coding-xiaomi-mimo-v2-omni": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 8e-08, "litellm_provider": "aihubmix", "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/coding-xiaomi-mimo-v2.5": { "cache_read_input_token_cost": 1.6e-09, "input_cost_per_token": 8e-08, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/coding-xiaomi-mimo-v2.5-pro": { "cache_read_input_token_cost": 1.6e-09, "input_cost_per_token": 2e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/command-a-plus-05-2026": { "input_cost_per_token": 2.5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 128000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/deepseek-v4-flash": { "cache_read_input_token_cost": 2.84e-08, "input_cost_per_token": 1.42e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.84e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/deepseek-v4-pro": { "cache_read_input_token_cost": 1.4027e-07, "input_cost_per_token": 1.69e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.38e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/doubao-seed-2-0-code-preview": { "cache_read_input_token_cost": 9.644e-08, "input_cost_per_token": 4.822e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/doubao-seed-2-0-lite-260428": { "cache_read_input_token_cost": 1.8082e-08, "input_cost_per_token": 9.041e-08, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.4246e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/doubao-seed-2-0-mini": { "cache_read_input_token_cost": 6.027e-09, "input_cost_per_token": 3.0136e-08, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.0136e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/doubao-seed-2-0-pro": { "cache_read_input_token_cost": 9.644e-08, "input_cost_per_token": 4.822e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/doubao-seed-2-1-turbo": { "cache_read_input_token_cost": 9.295e-08, "input_cost_per_token": 4.6475e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.32375e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/ernie-5.1": { "cache_read_input_token_cost": 5.634e-07, "input_cost_per_token": 5.634e-07, "litellm_provider": "aihubmix", "max_input_tokens": 119000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5353e-06, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true }, "aihubmix/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemini-3-flash-preview-search": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.499999e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemini-3.7-flash": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, "aihubmix/gemma-4-26b-a4b-it": { "input_cost_per_token": 1.4e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_vision": true }, "aihubmix/gemma-4-31b-it": { "input_cost_per_token": 1.4e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_vision": true }, "aihubmix/glm-5.2-fast-preview": { "cache_read_input_token_cost": 5.635e-07, "input_cost_per_token": 2.254e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.889e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/glm-5.3": { "cache_read_input_token_cost": 2.817e-07, "input_cost_per_token": 1.1268e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/glm-5.3-flash": { "cache_read_input_token_cost": 2.817e-08, "input_cost_per_token": 1.1268e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/glm-5v-turbo": { "cache_read_input_token_cost": 1.69008e-07, "input_cost_per_token": 7.042e-07, "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.09848e-06, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "aihubmix/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/gpt-5.4-high": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.4-low": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.4-mini": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.5": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.5-pro": { "input_cost_per_token": 3e-05, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/gpt-5.6-luna": { "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/gpt-5.6-sol-disc": { "cache_read_input_token_cost": 4e-07, "cache_creation_input_token_cost": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/gpt-5.6-terra": { "cache_read_input_token_cost": 2e-07, "cache_creation_input_token_cost": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/grok-4-20-non-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/grok-4-20-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/grok-4.6": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/grok-build-0.1": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1e-06, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/hy3": { "cache_read_input_token_cost": 3.905e-08, "input_cost_per_token": 1.562e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.248e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_web_search": true }, "aihubmix/hy4-preview": { "cache_read_input_token_cost": 4.225e-08, "input_cost_per_token": 8.45e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.535e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_web_search": true }, "aihubmix/kimi-k2.6": { "cache_read_input_token_cost": 1.60835e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.9995e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/kimi-k2.7-code-highspeed": { "cache_read_input_token_cost": 3.2167e-07, "input_cost_per_token": 1.9e-06, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.999e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/longcat-2.0": { "cache_read_input_token_cost": 1.5492e-08, "input_cost_per_token": 7.746e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.0984e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true }, "aihubmix/mai-thinking-1": { "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/mimo-v2-omni": { "cache_read_input_token_cost": 8.8e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/mimo-v2-pro": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_web_search": true }, "aihubmix/minimax-m2.7": { "cache_read_input_token_cost": 5.916e-08, "input_cost_per_token": 2.958e-07, "litellm_provider": "aihubmix", "max_input_tokens": 204800, "max_output_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.1832e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true }, "aihubmix/minimax-m3": { "input_cost_per_token": 2.88e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.152e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "aihubmix/muse-spark-1.2": { "input_cost_per_token": 1.375e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.675e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "aihubmix/qwen3-coder-next": { "input_cost_per_token": 1.37e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 5.48e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_response_schema": true }, "aihubmix/qwen3.5-122b-a10b": { "input_cost_per_token": 1.126e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.008e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.5-397b-a17b": { "input_cost_per_token": 1.644e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.864e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.6-27b": { "input_cost_per_token": 4.22e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.532e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.6-35b-a3b": { "input_cost_per_token": 2.54e-07, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.524e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.6-max-preview": { "cache_read_input_token_cost": 1.268e-07, "cache_creation_input_token_cost": 1.585e-06, "input_cost_per_token": 1.268e-06, "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.608e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_web_search": true }, "aihubmix/qwen3.7-plus": { "cache_read_input_token_cost": 5.64e-08, "cache_creation_input_token_cost": 3.525e-07, "input_cost_per_token": 2.82e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.128e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.8-2.4t-a95b": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_web_search": true }, "aihubmix/qwen3.8-flash": { "cache_read_input_token_cost": 1.4075e-08, "cache_creation_input_token_cost": 1.75937e-07, "input_cost_per_token": 1.126e-07, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.80025e-07, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/qwen3.8-max": { "cache_read_input_token_cost": 1.69e-07, "cache_creation_input_token_cost": 2.1125e-06, "input_cost_per_token": 1.69e-06, "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.07e-06, "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_web_search": true }, "aihubmix/step-3.7-flash": { "cache_read_input_token_cost": 4.4e-08, "input_cost_per_token": 2.2e-07, "litellm_provider": "aihubmix", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "aiand/deepseek-ai/deepseek-v4-flash": { "cache_read_input_token_cost": 8e-08, "deprecation_date": "2026-10-27", "input_cost_per_token": 1.5e-07, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/deepseek-ai/deepseek-v4-pro": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 1e-06, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/deepseek-ai/deepseek-v4.1-flash": { "cache_read_input_token_cost": 2e-08, "deprecation_date": "2026-11-05", "input_cost_per_token": 3e-07, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/deepseek-ai/deepseek-v4.1-flash-1017": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 3e-07, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/google/gemma-4-31b-it": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "aiand", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/meta/muse-spark-open": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 943718, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/moonshotai/kimi-k2.7-code": { "cache_read_input_token_cost": 2e-07, "deprecation_date": "2026-10-27", "input_cost_per_token": 7.5e-07, "litellm_provider": "aiand", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/moonshotai/kimi-k3": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 3e-06, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/motif-technologies/motif-3": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 5e-07, "litellm_provider": "aiand", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/openai/gpt-oss-120b": { "cache_read_input_token_cost": 8e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "aiand", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/qwen/qwen3.6-27b": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 3.2e-07, "litellm_provider": "aiand", "max_input_tokens": 262144, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/qwen/qwen3.8-27b": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 4e-07, "litellm_provider": "aiand", "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "aiand/zai-org/glm-5.2": { "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-10-27", "input_cost_per_token": 1e-06, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/zai-org/glm-5.3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 1e-06, "litellm_provider": "aiand", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "aiand/zai-org/glm-5.3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "aiand", "max_input_tokens": 1048550, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.aiand.com/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bespoke/nimble-latest": { "input_cost_per_token": 0.0, "litellm_provider": "bespoke", "max_input_tokens": 8192, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://github.com/bespokelabsai/nimble", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "bespoke/nimble": { "input_cost_per_token": 0.0, "litellm_provider": "bespoke", "max_input_tokens": 8192, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://ollama.com/library/nimble", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately" } }, "bespoke/bespokelabs/Bespoke-Nimble-9B": { "input_cost_per_token": 0.0, "litellm_provider": "bespoke", "max_input_tokens": 8192, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://github.com/bespokelabsai/nimble", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "laya/english": { "input_cost_per_token": 0.0, "litellm_provider": "laya", "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://github.com/NandhaKishorM/laya", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "laya/multilingual": { "input_cost_per_token": 0.0, "litellm_provider": "laya", "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://github.com/NandhaKishorM/laya", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "laya/typed-decisions": { "input_cost_per_token": 0.0, "litellm_provider": "laya", "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://github.com/NandhaKishorM/laya", "supported_endpoints": [ "/v1/systemone" ], "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "strands_decider/strands-decider-2B-hobson-v19": { "input_cost_per_token": 0.0, "litellm_provider": "strands_decider", "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", "metadata": { "notes": "Self-hosted decision model; infrastructure costs are paid separately" } }, "nace/drex-v1.0": { "input_cost_per_token": 4e-08, "litellm_provider": "nace", "max_input_tokens": 32768, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://console.nace.ai/docs/drex/reference/models" }, "nace/drex-v1.5": { "input_cost_per_token": 5e-08, "litellm_provider": "nace", "max_input_tokens": 131072, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://console.nace.ai/docs/drex/reference/models" }, "nace/drex-v2.0": { "input_cost_per_token": 6e-08, "litellm_provider": "nace", "max_input_tokens": 131072, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://console.nace.ai/docs/drex/reference/models" }, "nace/drex-latest": { "input_cost_per_token": 6e-08, "litellm_provider": "nace", "max_input_tokens": 131072, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://console.nace.ai/docs/drex/reference/models" }, "typesafe/jev-1.13.0": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" }, "typesafe/jev-1.14.0": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models", "supports_box_questions": true }, "typesafe/jev-latest": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models", "supports_box_questions": true }, "typesafe/jev-preview": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models", "supports_box_questions": true }, "eu_jev/eu-jeff-1.0.0": { "input_cost_per_token": 4.15e-08, "litellm_provider": "eu_jev", "max_input_tokens": 32768, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://eu-jev.com/docs", "supported_endpoints": [ "/v1/systemone" ] }, "eu_jev/eu-jeff-latest": { "input_cost_per_token": 4.15e-08, "litellm_provider": "eu_jev", "max_input_tokens": 32768, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://eu-jev.com/docs", "supported_endpoints": [ "/v1/systemone" ] }, "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 2e-09, "input_cost_per_token": 1.3e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "wandb/google/gemma-4-26B-A4B-it": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "wandb", "max_input_tokens": 262000, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://wandb.ai/site/pricing/tokens/", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "wandb/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "moonshotai.kimi-k3": { "supports_regex_lookaround": false, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_flex": 2.0625e-06, "cache_creation_input_token_cost_priority": 7.21875e-06, "cache_read_input_token_cost": 3.3e-07, "cache_read_input_token_cost_flex": 1.65e-07, "cache_read_input_token_cost_priority": 5.775e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", "token_count_framing": 64, "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, "output_cost_per_token_priority": 2.8875e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "global.moonshotai.kimi-k3": { "supports_regex_lookaround": false, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_flex": 1.875e-06, "cache_creation_input_token_cost_priority": 6.5625e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_flex": 1.5e-07, "cache_read_input_token_cost_priority": 5.25e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_flex": 1.5e-06, "input_cost_per_token_priority": 5.25e-06, "litellm_provider": "bedrock_converse", "token_count_framing": 64, "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_priority": 2.625e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/kimi-latest": { "alias_of": "global.moonshotai.kimi-k3" }, "us.moonshotai.kimi-k3": { "supports_regex_lookaround": false, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_flex": 2.0625e-06, "cache_creation_input_token_cost_priority": 7.21875e-06, "cache_read_input_token_cost": 3.3e-07, "cache_read_input_token_cost_flex": 1.65e-07, "cache_read_input_token_cost_priority": 5.775e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", "token_count_framing": 64, "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, "output_cost_per_token_priority": 2.8875e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "xiaomi_mimo/mimo-v2.6-pro": { "cache_read_input_token_cost": 3.6e-09, "input_cost_per_token": 4.35e-07, "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "xiaomi_mimo/mimo-v2.6-flash": { "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "xai/grok-4.20-0309": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta-0309": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta-latest-non-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-beta-latest-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-beta-non-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-beta-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-0304": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-0304-non-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-0304-reasoning": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-non-reasoning-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-experimental-beta-reasoning-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-beta-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ "/v1/responses" ] }, "xai/grok-4.20-multi-agent-experimental-beta-0304": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ "/v1/responses" ] }, "xai/grok-4.20-multi-agent-experimental-beta-latest": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ "/v1/responses" ] }, "xai/grok-4.20-non-reasoning-gv2": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-reasoning-gv2": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/moonshotai/Kimi-K2.6": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/moonshotai/Kimi-K2.7-Code": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/kimi-latest": { "alias_of": "baseten/moonshotai/Kimi-K3" }, "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 202800, "max_output_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/thinkingmachines/inkling": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/thinkingmachines/inkling-small": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/zai-org/GLM-5.2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/glm-flash-latest": { "alias_of": "baseten/zai-org/GLM-5.3-Flash" }, "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/deepseek-flash-latest": { "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Flash-0731" }, "baseten/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.32e-07, "input_cost_per_token": 1.32e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "baseten/deepseek-pro-latest": { "alias_of": "baseten/deepseek-ai/DeepSeek-V4-Pro-0813" }, "baseten/zai-org/GLM-5.2-Fast": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "xai/grok-code-fast": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "deprecation_date": "2026-05-15", "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, "source": "https://api.x.ai/v1/language-models", "successor_model": "xai/grok-build-0.1", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "xai/grok-code-fast-1-0825": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 1e-06, "input_cost_per_token_above_200k_tokens": 2e-06, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { "cache_read_input_token_cost": 6e-07, "cache_read_input_token_cost_priority": 6e-07, "deprecation_date": "2026-08-27", "input_cost_per_token": 1.2e-06, "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.2e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { "cache_read_input_token_cost_priority": 6e-07, "deprecation_date": "2026-08-27", "input_cost_per_token_priority": 1.2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 196608, "mode": "chat", "output_cost_per_token_priority": 1.2e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "fireworks_ai/accounts/fireworks/routers/rune": { "cache_read_input_token_cost": 8.4e-09, "input_cost_per_token": 4.2e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.fireworks.ai" }, "fireworks_ai/accounts/fireworks/models/ember-1": { "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/gemini-3.5-flash-lite", "input_cost_per_audio_token": 1e-06, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_character": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "vertex_ai", "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-2.0-flash-lite": { "deprecation_date": "2026-06-01", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/gemini-3.5-flash-lite", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_audio_token_batches": 3.75e-08, "input_cost_per_character": 1.875e-08, "input_cost_per_token": 7.5e-08, "input_cost_per_token_batches": 3.75e-08, "litellm_provider": "vertex_ai", "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/zai-org/glm-5.2-maas": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": ["global"], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "vertex_ai/meta/llama-3.3-70b-instruct-maas": { "deprecation_date": "2026-10-21", "input_cost_per_token": 7.2e-07, "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text", "code" ], "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/veo-3.0-generate-001": { "deprecation_date": "2026-06-30", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/veo-3.1-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-3.0-fast-generate-001": { "deprecation_date": "2026-06-30", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/veo-3.1-fast-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/veo-2.0-generate-001": { "deprecation_date": "2026-06-30", "deprecation_source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", "successor_model": "vertex_ai/veo-3.1-generate-001", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.5, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "vertex_ai/virtual-try-on-001": { "deprecation_date": "2027-03-15", "litellm_provider": "vertex_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "image" ], "supported_output_modalities": [ "image" ] }, "vertex_ai/gemini-2.5-flash-tts": { "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai", "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-2.5-pro-tts": { "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai", "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "anthropic.claude-mythos-5-1": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_read_input_token_cost": 2.5e-07, "output_cost_per_token": 5e-05, "input_cost_per_token": 1e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-mythos-5-1": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "cache_read_input_token_cost": 2.5e-07, "cache_creation_input_token_cost": 1.25e-05, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-mythos-5-1": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "input_cost_per_token": 1.1e-05, "output_cost_per_token": 5.5e-05, "cache_read_input_token_cost": 2.75e-07, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "us.anthropic.claude-mythos-5": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost": 1.375e-05, "input_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 1.1e-06, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-mythos-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" } }, "apac.anthropic.claude-fable-5": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_read_input_token_cost": 1.1e-06, "input_cost_per_token": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-fable-5": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_read_input_token_cost": 1.1e-06, "input_cost_per_token": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "output_cost_per_token": 2.75e-05, "cache_creation_input_token_cost": 6.875e-06, "input_cost_per_token": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-7", "litellm_provider": "bedrock_mantle", "region": "ap-northeast-1" } }, "apac.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "output_cost_per_token": 2.75e-05, "cache_read_input_token_cost": 5.5e-07, "cache_creation_input_token_cost": 6.875e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-4-8", "litellm_provider": "bedrock_mantle", "region": "ap-northeast-1" } }, "apac.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_creation_input_token_cost": 6.875e-06, "input_cost_per_token": 5.5e-06, "cache_read_input_token_cost": 5.5e-07, "output_cost_per_token": 2.75e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/ap-northeast-1/index.json", "token_count_model": { "model": "anthropic.claude-opus-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" }, "input_cost_per_token_batches": 2.75e-06, "output_cost_per_token_batches": 1.375e-05 }, "apac.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, "cache_creation_input_token_cost_above_1hr": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, "input_cost_per_token": 4.4e-06, "output_cost_per_token": 2.2e-05, "cache_read_input_token_cost": 2.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "apac.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "output_cost_per_token": 1.65e-05, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_token_cost": 4.125e-06, "input_cost_per_token": 3.3e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-sonnet-4-6", "litellm_provider": "bedrock" } }, "apac.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 2.2e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "token_count_model": { "model": "anthropic.claude-sonnet-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" } }, "us.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "cache_creation_input_token_cost_above_1hr": 5.5e-05, "cache_read_input_token_cost": 2.75e-06, "cache_creation_input_token_cost": 3.4375e-05, "output_cost_per_token": 0.0001375, "input_cost_per_token": 2.75e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "input_cost_per_token": 2.75e-05, "cache_creation_input_token_cost": 3.4375e-05, "output_cost_per_token": 0.0001375, "cache_creation_input_token_cost_above_1hr": 5.5e-05, "cache_read_input_token_cost": 2.75e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "input_cost_per_token": 2.75e-05, "cache_creation_input_token_cost": 3.4375e-05, "output_cost_per_token": 0.0001375, "cache_creation_input_token_cost_above_1hr": 5.5e-05, "cache_read_input_token_cost": 2.75e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "deepseek.r1-v1:0": { "deprecation_date": "2027-03-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false }, "mistral.pixtral-large-2502-v1:0": { "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_tool_choice": false }, "azure_ai/MAI-Cyber-1-Flash": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/mistral-ocr-2505": { "litellm_provider": "azure_ai", "mode": "ocr", "ocr_cost_per_page": 0.001, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, "azure_ai/mistral-ocr-2512": { "litellm_provider": "azure_ai", "mode": "ocr", "ocr_cost_per_page": 0.002, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, "anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 1.1e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-sonnet-5-5": { "token_count_model": { "model": "au.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" }, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "azure_ai/claude-sonnet-5-5": { "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 1e-07, "deprecation_date": "2027-09-29", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": false, "supports_web_search": true, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, "azure_ai/claude-sonnet-latest": { "alias_of": "azure_ai/claude-sonnet-5-5" }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "eu.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "global.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "bedrock/claude-sonnet-latest": { "alias_of": "global.anthropic.claude-sonnet-5-5" }, "jp.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "perplexity/anthropic/claude-sonnet-5-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-fable-5-1": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "cache_read_input_token_cost": 2.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-5-5": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 4e-06, "output_cost_per_token": 2e-05, "cache_read_input_token_cost": 2e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6.1-sol": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, "input_cost_per_token_above_272k_tokens": 4e-06, "output_cost_per_token_above_272k_tokens": 1.5e-05, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6-sol": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-06, "output_cost_per_token_above_272k_tokens": 1.5e-05, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6-astra": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "cache_read_input_token_cost": 1e-06, "cache_creation_input_token_cost": 1.25e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "cache_read_input_token_cost_above_272k_tokens": 2e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6-luna": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 1e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "input_cost_per_token_above_272k_tokens": 2e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3.8-flash": { "litellm_provider": "perplexity", "mode": "responses", "supports_sampling_params": false, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, "cache_read_input_token_cost": 7.5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/xai/grok-4.7": { "litellm_provider": "perplexity", "mode": "responses", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token_above_200k_tokens": 4e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 3e-06, "cache_creation_input_token_cost_above_1hr": 4.8e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-sonnet-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us.anthropic.claude-sonnet-5-5": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_1hr": 4.4e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "us.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "vertex_ai/claude-sonnet-5-5": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-latest": { "alias_of": "vertex_ai/claude-sonnet-5-5" }, "vertex_ai/claude-sonnet-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "prism/deepseek-v4.1-flash": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 1.7e-07, "litellm_provider": "prism", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://prisminference.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "prism/deepseek-v4-flash": { "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 1.7e-07, "litellm_provider": "prism", "max_input_tokens": 1000000, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.1e-07, "source": "https://prisminference.com/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "global.xai.grok-4.7": { "supports_regex_lookaround": false, "supported_endpoints": ["/v1/chat/completions"], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_flex": 3e-06, "output_cost_per_token_priority": 1.05e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/grok-latest": { "alias_of": "global.xai.grok-4.7" }, "us.xai.grok-4.7": { "supports_regex_lookaround": false, "supported_endpoints": ["/v1/chat/completions"], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_flex": 2.75e-07, "cache_read_input_token_cost_priority": 9.625e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_flex": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "us-gov.xai.grok-4.7": { "supports_regex_lookaround": false, "supported_endpoints": ["/v1/chat/completions"], "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "supports_bedrock_runtime_chat_completions_response_format": true, "cache_read_input_token_cost": 6.6e-07, "cache_read_input_token_cost_flex": 3.3e-07, "cache_read_input_token_cost_priority": 1.155e-06, "input_cost_per_token": 2.64e-06, "input_cost_per_token_batches": 1.32e-06, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 7.92e-06, "output_cost_per_token_batches": 3.96e-06, "output_cost_per_token_flex": 3.96e-06, "output_cost_per_token_priority": 1.386e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_12hr": 5e-06, "cache_creation_input_token_cost_above_12hr_ultrafast": 3e-05, "cache_creation_input_token_cost_above_12hr_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 1e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 2e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast": 6e-05, "cache_creation_input_token_cost_above_12hr_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_creation_input_token_cost_flex": 1.25e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_ultrafast": 1.5e-05, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 2e-07, "cache_read_input_token_cost_ultrafast": 6e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_batches": 2e-06, "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_ultrafast": 1.2e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, "output_cost_per_token_above_272k_tokens_priority": 3e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, "output_cost_per_token_ultrafast": 6e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-sol-latest": { "alias_of": "gpt-6.1-sol" }, "global.openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, "cache_creation_input_token_cost_ultrafast": 1.5e-05, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-07, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, "cache_read_input_token_cost_ultrafast": 6e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, "input_cost_per_token_ultrafast": 1.2e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, "output_cost_per_token_ultrafast": 6e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_sampling_params": false, "supports_xhigh_reasoning_effort": true }, "bedrock/gpt-sol-latest": { "alias_of": "global.openai.gpt-6.1-sol" }, "bedrock_mantle/openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, "cache_creation_input_token_cost_ultrafast": 1.65e-05, "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, "cache_read_input_token_cost_ultrafast": 6.6e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, "input_cost_per_token_ultrafast": 1.32e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "responses", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, "output_cost_per_token_ultrafast": 6.6e-05, "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "use_openai_responses_path": true }, "bedrock_mantle/gpt-sol-latest": { "alias_of": "bedrock_mantle/openai.gpt-6.1-sol" }, "us.openai.gpt-6.1-sol": { "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, "cache_creation_input_token_cost_ultrafast": 1.65e-05, "cache_read_input_token_cost": 1.1e-07, "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, "cache_read_input_token_cost_ultrafast": 6.6e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, "input_cost_per_token_ultrafast": 1.32e-05, "litellm_provider": "bedrock_converse", "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, "output_cost_per_token_ultrafast": 6.6e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_sampling_params": false, "supports_xhigh_reasoning_effort": true }, "vertex_ai/gemini-3.8-flash-tts": { "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 9e-06, "output_cost_per_token": 9e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "vertex_ai/gemini-3.8-flash-lite-tts": { "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_output_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 6e-06, "output_cost_per_token": 6e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "vertex_ai/xai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "vertex_ai/grok-latest": { "alias_of": "vertex_ai/xai/grok-4.7" }, "azure_ai/kimi-k2-thinking": { "deprecation_date": "2026-03-29", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "successor_model": "azure_ai/kimi-k2.5", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": false, "supports_vision": false }, "global.zai.glm-5.3": { "cache_creation_input_token_cost": 2.1e-06, "cache_creation_input_token_cost_batches": 1.05e-06, "cache_creation_input_token_cost_flex": 1.05e-06, "cache_creation_input_token_cost_priority": 3.675e-06, "cache_read_input_token_cost": 3.12e-07, "cache_read_input_token_cost_batches": 1.56e-07, "cache_read_input_token_cost_flex": 1.56e-07, "cache_read_input_token_cost_priority": 5.46e-07, "input_cost_per_token": 1.68e-06, "input_cost_per_token_batches": 8.4e-07, "input_cost_per_token_flex": 8.4e-07, "input_cost_per_token_priority": 2.94e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.28e-06, "output_cost_per_token_batches": 2.64e-06, "output_cost_per_token_flex": 2.64e-06, "output_cost_per_token_priority": 9.24e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock/glm-latest": { "alias_of": "global.zai.glm-5.3" }, "us.zai.glm-5.3": { "cache_creation_input_token_cost": 2.31e-06, "cache_creation_input_token_cost_batches": 1.155e-06, "cache_creation_input_token_cost_flex": 1.155e-06, "cache_creation_input_token_cost_priority": 4.0425e-06, "cache_read_input_token_cost": 3.432e-07, "cache_read_input_token_cost_batches": 1.716e-07, "cache_read_input_token_cost_flex": 1.716e-07, "cache_read_input_token_cost_priority": 6.006e-07, "input_cost_per_token": 1.848e-06, "input_cost_per_token_batches": 9.24e-07, "input_cost_per_token_flex": 9.24e-07, "input_cost_per_token_priority": 3.234e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.808e-06, "output_cost_per_token_batches": 2.904e-06, "output_cost_per_token_flex": 2.904e-06, "output_cost_per_token_priority": 1.0164e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "amazon.nova-2-5-sonic": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 3.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-5-sonic.md", "supports_audio_input": true, "supports_audio_output": true }, "azure/model-router": { "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it", "deprecation_date": "2027-05-20", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_token": 1.4e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/", "supports_vision": true }, "azure/whisper": { "deprecation_date": "2027-02-26", "deprecation_source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", "output_cost_per_second": 0.0001, "source": "https://management.azure.com/subscriptions/a88257a5-3323-4ef9-95bf-5681a46c9624/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01" }, "gemini/gemini-nano-banana-2.1": { "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "rpm": 1000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, "gemini/nano-banana-latest": { "alias_of": "gemini/gemini-nano-banana-2.1" }, "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_image": 0.00168, "input_cost_per_token": 1.5e-06, "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, "output_cost_per_image_token_batches": 1.5e-05, "output_cost_per_image_token_priority": 5.4e-05, "output_cost_per_token": 7.5e-06, "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/nano-banana-latest": { "alias_of": "vertex_ai/gemini-nano-banana-2.1" }, "azure_ai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "deprecation_date": "2027-10-05", "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://docs.x.ai/developers/models/grok-4.7", "supports_function_calling": true, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "azure_ai/grok-latest": { "alias_of": "azure_ai/grok-4.7" }, "in.moonshotai.kimi-k3": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_flex": 2.0625e-06, "cache_creation_input_token_cost_priority": 7.21875e-06, "cache_read_input_token_cost": 3.3e-07, "cache_read_input_token_cost_flex": 1.65e-07, "cache_read_input_token_cost_priority": 5.775e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_flex": 1.65e-06, "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", "token_count_framing": 64, "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_flex": 8.25e-06, "output_cost_per_token_priority": 2.8875e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_creation_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_batches": 2.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", "supports_web_search": true, "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, "claude-haiku-latest": { "alias_of": "claude-haiku-5-5" }, "bedrock_mantle/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, "bedrock_mantle/claude-haiku-latest": { "alias_of": "bedrock_mantle/anthropic.claude-haiku-5-5" }, "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, "cache_creation_input_token_cost_above_1hr": 2.4e-07, "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock_mantle", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html", "token_count_model": {"model":"anthropic.claude-haiku-5-5","litellm_provider":"bedrock_mantle","region":"us-gov-west-1"} }, "anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, "input_cost_per_token": 1.1e-07, "output_cost_per_token": 5.5e-07, "cache_read_input_token_cost": 1.1e-08, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { "token_count_model": { "model": "au.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "ap-southeast-4" }, "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "azure_ai/claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_read_input_token_cost": 1e-08, "deprecation_date": "2027-09-29", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": true, "supports_web_search": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide" }, "azure_ai/claude-haiku-latest": { "alias_of": "azure_ai/claude-haiku-5-5" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, "cache_creation_input_token_cost_above_1hr": 2.4e-07, "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, "cache_creation_input_token_cost_above_1hr": 2.4e-07, "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-haiku-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "eu.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "global.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "bedrock/claude-haiku-latest": { "alias_of": "global.anthropic.claude-haiku-5-5" }, "jp.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "perplexity/anthropic/claude-haiku-5-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_adaptive_thinking": true, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 6e-07, "output_cost_per_token_above_100k_tokens": 3e-06, "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, "cache_creation_input_token_cost_above_1hr": 2.4e-07, "cache_read_input_token_cost": 1.2e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "token_count_model": { "model": "anthropic.claude-haiku-5-5", "litellm_provider": "bedrock_mantle", "region": "us-gov-west-1" } }, "us.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", "token_count_model": { "model": "us.anthropic.claude-opus-5-5", "litellm_provider": "bedrock_mantle", "region": "us-east-1" }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_bedrock_native_structured_output_by_default": true, "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "vertex_ai/claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_creation_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_batches": 2.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/claude-haiku-latest": { "alias_of": "vertex_ai/claude-haiku-5-5" }, "vertex_ai/claude-haiku-5-5@default": { "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_creation_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_batches": 2.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "microsoft_365_copilot/chat": { "litellm_provider": "microsoft_365_copilot", "mode": "chat", "supports_mid_conversation_system": true, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0 }, "us.twelvelabs.pegasus-1-5-v1:0": { "input_cost_per_video_per_second": 0.00049, "litellm_provider": "bedrock", "max_input_tokens": 261120, "max_output_tokens": 98304, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", "supports_video_input": true }, "global.twelvelabs.pegasus-1-5-v1:0": { "input_cost_per_video_per_second": 0.00049, "litellm_provider": "bedrock", "max_input_tokens": 261120, "max_output_tokens": 98304, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", "supports_video_input": true }, "twelvelabs.pegasus-1-5-v1:0": { "input_cost_per_video_per_second": 0.00049, "litellm_provider": "bedrock", "max_input_tokens": 261120, "max_output_tokens": 98304, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", "supports_video_input": true }, "azure_ai/Microsoft-Decision-1": { "input_cost_per_token": 4.2e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" }, "gpt-rosalind-discovery": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://developers.openai.com/api/docs/pricing" }, "chatgpt/gpt-rosalind-discovery": { "litellm_provider": "chatgpt", "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ] }, "azure_ai/Cohere-Embed-V5-Fast": { "deprecation_date": "2027-01-23", "input_cost_per_image_token": 4e-07, "input_cost_per_token": 8e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048.0, "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true }, "azure_ai/Cohere-Embed-V5-Pro": { "deprecation_date": "2027-01-23", "input_cost_per_image_token": 4e-07, "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048.0, "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true }, "scaledown/extract": { "input_cost_per_token": 5e-08, "output_cost_per_token": 0.0, "litellm_provider": "scaledown", "mode": "chat", "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, "supports_function_calling": false }, "scaledown/summarize": { "input_cost_per_token": 5e-08, "output_cost_per_token": 0.0, "litellm_provider": "scaledown", "mode": "chat", "supports_system_messages": true, "supports_vision": false, "supports_function_calling": false }, "scaledown/compress": { "input_cost_per_token": 5e-08, "output_cost_per_token": 0.0, "litellm_provider": "scaledown", "mode": "chat", "supports_system_messages": true, "supports_function_calling": false, "supports_vision": false }, "scaledown/classify": { "input_cost_per_token": 5e-08, "output_cost_per_token": 0.0, "litellm_provider": "scaledown", "mode": "chat", "supports_system_messages": false, "supports_vision": false, "supports_function_calling": false }, "scaledown/decisions": { "input_cost_per_token": 5e-08, "output_cost_per_token": 0.0, "litellm_provider": "scaledown", "mode": "chat", "supports_system_messages": false, "supports_vision": false, "supports_function_calling": false }, "vertex_ai/gemini-robotics-er-2-preview": { "cache_read_input_token_cost": 1e-07, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini-robotics-er-2-preview": { "cache_read_input_token_cost": 1e-07, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "gemini/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 4096.0, "rpm": 2000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000.0, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 2e-06, "input_cost_per_audio_token_batches": 1e-06, "input_cost_per_audio_token_priority": 3.6e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-argon-cyber-permissive": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 4e-06, "input_cost_per_audio_token_batches": 2e-06, "input_cost_per_audio_token_priority": 7.2e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 7.2e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 6144.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "github_copilot/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "openinfer/@oi/GLM-5.3-Flash": { "max_input_tokens": 393216, "max_output_tokens": 393216, "input_cost_per_token": 1.95e-07, "output_cost_per_token": 1.56e-06, "litellm_provider": "openinfer", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://api.openinfer.ai/v1/models" }, "openinfer/@oi/Qwen3.5-27B": { "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.95e-07, "output_cost_per_token": 1.56e-06, "litellm_provider": "openinfer", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://api.openinfer.ai/v1/models" }, "openinfer/@oi/Qwen3.5-9B": { "max_input_tokens": 100000, "max_output_tokens": 100000, "input_cost_per_token": 5e-06, "output_cost_per_token": 1.5e-07, "litellm_provider": "openinfer", "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, "source": "https://api.openinfer.ai/v1/models" }, "xai/grok-voice-3.0": { "input_cost_per_second": 0.001333333333333, "input_cost_per_text_message": 0.004, "litellm_provider": "xai", "mode": "realtime", "source": "https://docs.x.ai/developers/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true }, "xai/grok-voice-latest": { "input_cost_per_second": 0.001333333333333, "input_cost_per_text_message": 0.004, "litellm_provider": "xai", "mode": "realtime", "source": "https://docs.x.ai/developers/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true }, "xai/grok-voice-2.0": { "input_cost_per_second": 0.001333333333333, "input_cost_per_text_message": 0.004, "litellm_provider": "xai", "mode": "realtime", "source": "https://docs.x.ai/developers/pricing", "successor_model": "xai/grok-voice-3.0", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true }, "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "jp.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 9.9e-08, "cache_read_input_token_cost_flex": 4.95e-08, "cache_read_input_token_cost_priority": 1.7325e-07, "input_cost_per_token": 3.96e-07, "input_cost_per_token_batches": 1.98e-07, "input_cost_per_token_flex": 1.98e-07, "input_cost_per_token_priority": 6.93e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.311e-06, "output_cost_per_token_batches": 1.6555e-06, "output_cost_per_token_flex": 1.6555e-06, "output_cost_per_token_priority": 5.79425e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "azure_ai/claude-opus-5-5-fast": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-15", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "input_cost_per_token": 8e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, "source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "thinking_always_on": true }, "baseten/meta-models/muse-spark-open": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://inference.baseten.co/v1/models", "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true, "supports_vision": true }, "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "max_output_tokens": 943718, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/reflection/Beam-1.0-501B-A23B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true }, "baseten/reflection/Beam-1.0": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "nebius/reflection/beam": { "input_cost_per_token": 2.5e-07, "litellm_provider": "nebius", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://tokenfactory.nebius.com/api/public/models_info", "supports_function_calling": true, "supports_reasoning": true, "cache_read_input_token_cost": 5e-08 }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": { "cache_read_input_token_cost": 6e-09, "cache_read_input_token_cost_priority": 7.5e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/deepseek-flash-latest": { "cache_read_input_token_cost": 6e-09, "cache_read_input_token_cost_priority": 7.5e-09, "input_cost_per_token": 3e-07, "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.5e-06, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "github_copilot/claude-sonnet-4.6": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-09-01", "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "github_copilot", "max_input_tokens": 272000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.25e-06, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/grok-4.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "deprecation_date": "2026-10-19", "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/grok-4.6": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "github_copilot", "max_input_tokens": 500000, "max_output_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/grok-latest": { "alias_of": "github_copilot/grok-4.7" }, "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "meta/muse-image-1.0": { "litellm_provider": "meta", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://dev.meta.ai/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 2.25e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 9e-07, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "meta/sam-3.1": { "input_cost_per_image": 0.0025, "litellm_provider": "meta", "mode": "responses", "source": "https://dev.meta.ai/docs/pricing-rate-limits.md", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ] }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": { "cache_read_input_token_cost": 9e-09, "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/us-only-serverless", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "wandb/reflection/Beam-1.0-501B-A23B": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "wandb/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "azure_ai/MAI-Code-1.1-Flash": { "cache_read_input_token_cost": 2e-08, "deprecation_date": "2026-12-09", "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "opencode_go/grok-4.7": { "litellm_provider": "opencode_go", "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, "max_output_tokens": 500000, "max_input_tokens": 500000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "tiered_pricing": [ { "range": [ 0, 200000 ], "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07 }, { "range": [ 200000, 500000 ], "input_cost_per_token": 4e-06, "output_cost_per_token": 1.2e-05, "cache_read_input_token_cost": 1e-06 } ], "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/gpt-6-luna": { "litellm_provider": "opencode_go", "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "tiered_pricing": [ { "range": [ 0, 272000 ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07 }, { "range": [ 272000, 1050000 ], "input_cost_per_token": 2.0000000000000002e-07, "output_cost_per_token": 7.5e-07, "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07 } ], "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/gpt-5.6-luna": { "litellm_provider": "opencode_go", "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "input_cost_per_token": 2.0000000000000002e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "tiered_pricing": [ { "range": [ 0, 272000 ], "input_cost_per_token": 2.0000000000000002e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07 }, { "range": [ 272000, 1050000 ], "input_cost_per_token": 4.0000000000000003e-07, "output_cost_per_token": 1.8000000000000001e-06, "cache_read_input_token_cost": 4e-08, "cache_creation_input_token_cost": 5e-07 } ], "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/claude-haiku-5-5": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/messages" ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "tiered_pricing": [ { "range": [ 0, 100000 ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07 }, { "range": [ 100000, 1000000 ], "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 5.0000000000000004e-08, "cache_creation_input_token_cost": 6.25e-07 } ], "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/gemini-4-argon": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1beta/models" ], "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, "max_output_tokens": 65536, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/glm-5.3-flash": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/glm-5.3": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/glm-5.2": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/kimi-k3.1-pro": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2.0000000000000002e-07, "cache_creation_input_token_cost": 2e-06, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/kimi-k3": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3e-06, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/kimi-k2.7-code": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 9.499999999999999e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 1.9e-07, "max_output_tokens": 262144, "max_input_tokens": 262144, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/longcat-2.0": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/deepseek-v4.1-flash": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/deepseek-v4-pro": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.32e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/mimo-v2.6-flash": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/mimo-v2.6-pro": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/mimo-v2.5": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/mimo-v2.5-pro": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, "max_output_tokens": 128000, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/minimax-m3.1-flash": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 1.5e-08, "max_output_tokens": 512000, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/minimax-m3": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/messages" ], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/muse-spark-1.3-contributor": { "litellm_provider": "opencode_go", "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/muse-spark-1.2-contributor": { "litellm_provider": "opencode_go", "mode": "responses", "supported_endpoints": [ "/v1/responses" ], "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/qwen3.8-max": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/messages" ], "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.5e-07, "cache_creation_input_token_cost": 2.5e-06, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/qwen3.8-flash": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/messages" ], "input_cost_per_token": 1.5e-07, "output_cost_per_token": 4.6999999999999995e-07, "cache_read_input_token_cost": 1.6e-08, "cache_creation_input_token_cost": 2.0000000000000002e-07, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/qwen3.7-plus": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/messages" ], "input_cost_per_token": 4.0000000000000003e-07, "output_cost_per_token": 1.6000000000000001e-06, "cache_read_input_token_cost": 4e-08, "cache_creation_input_token_cost": 5e-07, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "tiered_pricing": [ { "range": [ 0, 256000 ], "input_cost_per_token": 4.0000000000000003e-07, "output_cost_per_token": 1.6000000000000001e-06, "cache_read_input_token_cost": 4e-08, "cache_creation_input_token_cost": 5e-07 }, { "range": [ 256000, 1000000 ], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.8e-06, "cache_read_input_token_cost": 1.2e-07, "cache_creation_input_token_cost": 1.5e-06 } ], "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/hy4-preview": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 8.34e-07, "output_cost_per_token": 2.501e-06, "cache_read_input_token_cost": 4.2000000000000006e-08, "max_output_tokens": 64000, "max_input_tokens": 1024000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/hy3": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, "cache_read_input_token_cost": 3.5e-08, "max_output_tokens": 128000, "max_input_tokens": 192000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/longcat-2.5-preview-free": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/step-5-preview": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 1e-06, "output_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1.0000000000000001e-07, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": true, "source": "https://opencode.ai/v2/docs/console/go/" }, "opencode_go/beam-free": { "litellm_provider": "opencode_go", "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" ], "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, "supports_reasoning": true, "supports_vision": false, "source": "https://opencode.ai/v2/docs/console/go/" }, "bedrock/claude_platform/claude-fable-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-fable-5-1": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "input_cost_per_token_batches": 5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, "cache_creation_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost": 1e-08, "cache_read_input_token_cost_batches": 5e-09, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_batches": 2.5e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_forced_tool_use": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", "supports_web_search": true, "input_cost_per_token_above_100k_tokens": 5e-07, "output_cost_per_token_above_100k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, "bedrock/claude_platform/claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-opus-4-6": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-opus-4-7": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 2048, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-opus-4-8": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-opus-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-opus-5-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_batches": 1.5e-07, "deprecation_date": "2026-11-30", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html", "successor_model": "bedrock/claude_platform/claude-sonnet-5-5", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-sonnet-4-6": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "provider_specific_entry": { "us": 1.1 }, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-sonnet-5": { "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing" }, "bedrock/claude_platform/claude-sonnet-5-5": { "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_forced_tool_use": false, "thinking_always_on": true, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", "supports_web_search": true }, "gpt-6.1-terra": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_12hr": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 1e-05, "cache_creation_input_token_cost_above_12hr_batches": 1.25e-06, "cache_creation_input_token_cost_above_12hr_flex": 1.25e-06, "cache_creation_input_token_cost_above_12hr_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-06, "cache_creation_input_token_cost_batches": 6.25e-07, "cache_creation_input_token_cost_flex": 6.25e-07, "cache_creation_input_token_cost_priority": 2.5e-06, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_above_272k_tokens": 1e-07, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-08, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-07, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, "cache_read_input_token_cost_priority": 1e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_above_272k_tokens": 2e-06, "input_cost_per_token_above_272k_tokens_batches": 1e-06, "input_cost_per_token_above_272k_tokens_flex": 1e-06, "input_cost_per_token_above_272k_tokens_priority": 4e-06, "input_cost_per_token_batches": 5e-07, "input_cost_per_token_flex": 5e-07, "input_cost_per_token_priority": 2e-06, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, "output_cost_per_token_above_272k_tokens_batches": 3.75e-06, "output_cost_per_token_above_272k_tokens_flex": 3.75e-06, "output_cost_per_token_above_272k_tokens_priority": 1.5e-05, "output_cost_per_token_batches": 2.5e-06, "output_cost_per_token_flex": 2.5e-06, "output_cost_per_token_priority": 1e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-terra-latest": { "alias_of": "gpt-6.1-terra" }, "chatgpt/gpt-6.1-terra": { "litellm_provider": "chatgpt", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "global.openai.gpt-6.1-terra": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_above_272k_tokens": 1e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_bedrock_converse_tool_result_images": false, "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "bedrock/gpt-terra-latest": { "alias_of": "global.openai.gpt-6.1-terra" }, "us.openai.gpt-6.1-terra": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, "cache_read_input_token_cost": 5.5e-08, "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_above_272k_tokens": 2.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-06, "output_cost_per_token_above_272k_tokens": 8.25e-06, "source": "https://developers.openai.com/api/docs/models/gpt-6.1-terra", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_bedrock_converse_tool_result_images": false, "supports_bedrock_runtime_chat_completions_response_format": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "baseten/decision-models/baseten-elephant-9b-latest": { "input_cost_per_token": 3.5e-08, "litellm_provider": "baseten", "max_input_tokens": 16384, "mode": "decisions", "output_cost_per_token": 0.0, "source": "https://inference.baseten.co/v1/models", "supports_vision": true }, "baseten/decision-models/baseten-mammoth-27b-latest": { "input_cost_per_token": 1e-07, "litellm_provider": "baseten", "max_input_tokens": 16384, "mode": "decisions", "output_cost_per_token": 0.0, "source": "https://inference.baseten.co/v1/models", "supports_vision": true }, "github_copilot/gpt-6.1-terra": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_above_272k_tokens": 1e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_above_272k_tokens": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, "source": "https://github.blog/changelog/2026-10-26-gpt-6-1-terra-in-github-copilot", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-terra-latest": { "alias_of": "github_copilot/gpt-6.1-terra" }, "refuseless/glm-5.3-abliterated": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1e-06, "litellm_provider": "refuseless", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://refuseless.com/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "low", "high", "max" ] }, "refuseless/glm-5.3-flash-abliterated": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 1.2e-07, "litellm_provider": "refuseless", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://refuseless.com/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "low", "high", "max" ] }, "refuseless/deepseek-v4.1-flash-abliterated": { "cache_read_input_token_cost": 3.5e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "refuseless", "max_input_tokens": 1048576, "max_output_tokens": 130000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://refuseless.com/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "low", "high", "max" ] }, "refuseless/deepseek-v4.1-flash-fast": { "cache_read_input_token_cost": 3e-09, "input_cost_per_token": 5e-08, "litellm_provider": "refuseless", "max_input_tokens": 1048576, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://refuseless.com/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "low", "high", "max" ] }, "refuseless/minimax-m3.1-flash": { "cache_read_input_token_cost": 2e-09, "input_cost_per_token": 5e-08, "litellm_provider": "refuseless", "max_input_tokens": 1048576, "max_output_tokens": 512000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://refuseless.com/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false, "reasoning_effort_levels": [ "low", "high", "max" ] }, "fireworks_ai/accounts/fireworks/models/rune": { "cache_read_input_token_cost": 8.4e-09, "input_cost_per_token": 4.2e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "decisions", "output_cost_per_token": 0.0, "source": "https://api.fireworks.ai/v1/serverless/models?format=nested" }, "bedrock_mantle/openai.gpt-6.1-terra": { "cache_creation_input_token_cost": 1.375e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-06, "cache_read_input_token_cost": 5.5e-08, "cache_read_input_token_cost_above_272k_tokens": 1.1e-07, "input_cost_per_token": 1.1e-06, "input_cost_per_token_above_272k_tokens": 2.2e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 5.5e-06, "output_cost_per_token_above_272k_tokens": 8.25e-06, "search_context_cost_per_query": {"search_context_size_high":0.012,"search_context_size_low":0.012,"search_context_size_medium":0.012}, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-terra.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "use_openai_responses_path": true }, "bedrock_mantle/gpt-terra-latest": { "alias_of": "bedrock_mantle/openai.gpt-6.1-terra" }, "clf_ai_gateway/glm-5.3": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 5.6e-07, "output_cost_per_token": 1.76e-06, "cache_read_input_token_cost": 1.04e-07, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/glm-5.3-flash": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 2e-07, "cache_read_input_token_cost": 1.2e-08, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "supports_vision": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/glm-5.2": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 5.6e-07, "output_cost_per_token": 1.76e-06, "cache_read_input_token_cost": 1.04e-07, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/glm-4.7-flash": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.4e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high" ], "supports_response_schema": true, "supports_system_messages": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/deepseek-v4-pro": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 5.28e-07, "output_cost_per_token": 1.584e-06, "cache_read_input_token_cost": 1.7e-08, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/deepseek-v4-flash": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.76e-07, "output_cost_per_token": 5.28e-07, "cache_read_input_token_cost": 5e-09, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high", "xhigh", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/deepseek-v4.1-flash": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 4.8e-07, "cache_read_input_token_cost": 2e-09, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "supports_vision": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/kimi-k2.6": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.6e-06, "cache_read_input_token_cost": 6.4e-08, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "none", "low", "medium", "high" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "supports_vision": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/kimi-k2.7-code": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.6e-06, "cache_read_input_token_cost": 7.6e-08, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "high" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "supports_vision": true, "source": "https://clfaigateway.dev/models" }, "clf_ai_gateway/qwen3.8-27b": { "metadata": { "comment": "Billed price checked 2026-10-29, which the gateway shows as 60% off a list price 2.5x higher. Update the rows when the discount ends." }, "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1.8e-07, "output_cost_per_token": 1.28e-06, "cache_read_input_token_cost": 2e-08, "litellm_provider": "clf_ai_gateway", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "medium", "xhigh" ], "supports_response_schema": true, "supports_system_messages": true, "supports_prompt_caching": true, "supports_vision": true, "source": "https://clfaigateway.dev/models" }, "kyma/claude-fable-5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 1.35e-05, "output_cost_per_token": 6.75e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "thinking_always_on": true }, "kyma/claude-fable-5.1": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 1.35e-05, "output_cost_per_token": 6.75e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "thinking_always_on": true }, "kyma/claude-haiku-4-5": { "max_input_tokens": 200000, "max_output_tokens": 64000, "input_cost_per_token": 1.35e-06, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 6.75e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false, "prompt_cache_min_tokens": 4096 }, "kyma/claude-haiku-5.5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 1.35e-07, "cache_read_input_token_cost": 1.35e-08, "output_cost_per_token": 6.75e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "thinking_always_on": false, "prompt_cache_min_tokens": 512 }, "kyma/claude-opus-4-7": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 6.75e-06, "cache_read_input_token_cost": 6.75e-07, "output_cost_per_token": 3.375e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 2048 }, "kyma/claude-opus-5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 6.75e-06, "cache_read_input_token_cost": 6.75e-07, "output_cost_per_token": 3.375e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512 }, "kyma/claude-opus-5.5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 5.4e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 2.7e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "thinking_always_on": true, "prompt_cache_min_tokens": 512 }, "kyma/claude-sonnet-4-6": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 4.05e-06, "cache_read_input_token_cost": 4.05e-07, "output_cost_per_token": 2.025e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 1024 }, "kyma/claude-sonnet-5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 1.35e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 1024 }, "kyma/claude-sonnet-5.5": { "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 1.35e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true, "supports_adaptive_thinking": true, "thinking_always_on": true, "prompt_cache_min_tokens": 512 }, "kyma/deepseek-r1": { "max_input_tokens": 64000, "max_output_tokens": 32768, "input_cost_per_token": 7.425e-07, "output_cost_per_token": 2.957e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/deepseek-v3": { "max_input_tokens": 160000, "max_output_tokens": 8192, "input_cost_per_token": 5.18e-07, "output_cost_per_token": 7.571e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/deepseek-v4-flash": { "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token": 1.23e-07, "cache_read_input_token_cost": 2.43e-08, "output_cost_per_token": 2.458e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/deepseek-v4-flash-vision-exp": { "max_input_tokens": 1048576, "max_output_tokens": 384000, "input_cost_per_token": 3.892e-07, "output_cost_per_token": 1.168e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/deepseek-v4.1-flash": { "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 8.1e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gemini-3-flash": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 6.75e-07, "cache_read_input_token_cost": 6.75e-08, "output_cost_per_token": 4.05e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gemini-3.1-pro": { "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 1.62e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gemini-3.5-flash": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 2.025e-06, "cache_read_input_token_cost": 2.025e-07, "output_cost_per_token": 1.215e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gemini-3.5-flash-lite": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 4.05e-07, "cache_read_input_token_cost": 4.05e-08, "output_cost_per_token": 3.375e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gemini-3.6-flash": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 1.013e-06, "cache_read_input_token_cost": 1.0125e-07, "output_cost_per_token": 5.063e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_pdf_input": false }, "kyma/gemini-3.7-flash": { "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token": 2.026e-06, "cache_read_input_token_cost": 1.0125e-07, "output_cost_per_token": 1.0126e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gemini-3.8-flash": { "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token": 2.026e-06, "output_cost_per_token": 1.0126e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gemini-4-argon": { "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token": 5.4e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 2.7e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gemma-4-31b": { "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 1.642e-07, "cache_read_input_token_cost": 1.642e-07, "output_cost_per_token": 4.689e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-4.5-air": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 1.797e-07, "cache_read_input_token_cost": 3.375e-08, "output_cost_per_token": 1.175e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-4.7-flash": { "max_input_tokens": 203000, "max_output_tokens": 65536, "input_cost_per_token": 8.1e-08, "cache_read_input_token_cost": 1.35e-08, "output_cost_per_token": 5.4e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-5.1": { "max_input_tokens": 203000, "max_output_tokens": 65536, "input_cost_per_token": 1.89e-06, "cache_read_input_token_cost": 2.7675e-07, "output_cost_per_token": 5.94e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-5.2": { "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 9.029e-07, "cache_read_input_token_cost": 2.9835e-07, "output_cost_per_token": 3.083e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-5.3": { "max_input_tokens": 1310720, "max_output_tokens": 131072, "input_cost_per_token": 1.178e-06, "output_cost_per_token": 3.702e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/glm-5.3-flash": { "max_input_tokens": 1310720, "max_output_tokens": 65536, "input_cost_per_token": 1.72e-07, "output_cost_per_token": 5.733e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gpt-5.6-luna": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 2.944e-07, "cache_read_input_token_cost": 2.7e-08, "output_cost_per_token": 1.767e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-5.6-luna-pro": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 2.703e-07, "cache_read_input_token_cost": 2.7e-08, "output_cost_per_token": 1.621e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-5.6-sol": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 5.4e-06, "cache_read_input_token_cost": 6.75e-07, "output_cost_per_token": 2.7e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-5.6-sol-pro": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 5.4e-06, "cache_read_input_token_cost": 6.75e-07, "output_cost_per_token": 2.7e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-5.6-terra": { "max_input_tokens": 1050000, "max_output_tokens": 8192, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 1.62e-05, "input_cost_per_token_above_272k_tokens": 5.4e-06, "output_cost_per_token_above_272k_tokens": 2.43e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gpt-5.6-terra-pro": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 1.62e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-6-astra": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 1.35e-05, "cache_read_input_token_cost": 1.35e-06, "output_cost_per_token": 6.75e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/gpt-6-luna": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 1.639e-07, "cache_read_input_token_cost": 1.35e-08, "output_cost_per_token": 8.195e-07, "input_cost_per_token_above_272k_tokens": 2.7e-07, "output_cost_per_token_above_272k_tokens": 1.0125e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-6.1-sol": { "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 1.35e-05, "input_cost_per_token_above_272k_tokens": 5.4e-06, "output_cost_per_token_above_272k_tokens": 2.025e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/gpt-oss-120b": { "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 4.73e-08, "output_cost_per_token": 2.303e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/grok-4.20": { "max_input_tokens": 2000000, "max_output_tokens": 8192, "input_cost_per_token": 1.763e-06, "output_cost_per_token": 3.528e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/grok-4.20-multi-agent": { "max_input_tokens": 2000000, "max_output_tokens": 8192, "input_cost_per_token": 1.767e-06, "output_cost_per_token": 3.534e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": false, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/grok-4.3": { "max_input_tokens": 1000000, "max_output_tokens": 32768, "input_cost_per_token": 1.92e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 3.838e-06, "input_cost_per_token_above_200k_tokens": 3.375e-06, "output_cost_per_token_above_200k_tokens": 6.75e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/grok-4.5": { "max_input_tokens": 500000, "max_output_tokens": 8192, "input_cost_per_token": 2.73e-06, "output_cost_per_token": 8.189e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/grok-4.6": { "max_input_tokens": 500000, "max_output_tokens": 8192, "input_cost_per_token": 2.758e-06, "output_cost_per_token": 8.274e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/grok-4.7": { "max_input_tokens": 500000, "max_output_tokens": 450000, "input_cost_per_token": 2.16e-06, "cache_read_input_token_cost": 5.4e-07, "output_cost_per_token": 6.48e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/grok-build": { "max_input_tokens": 256000, "max_output_tokens": 32768, "input_cost_per_token": 1.389e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 2.777e-06, "input_cost_per_token_above_200k_tokens": 2.7e-06, "output_cost_per_token_above_200k_tokens": 5.4e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/hy3": { "max_input_tokens": 262144, "max_output_tokens": 8192, "input_cost_per_token": 1.594e-07, "output_cost_per_token": 6.576e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/hy4-preview": { "max_input_tokens": 1048576, "max_output_tokens": 64000, "input_cost_per_token": 1.1259e-06, "output_cost_per_token": 3.3764e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/kimi-k2.6": { "max_input_tokens": 262144, "max_output_tokens": 32768, "input_cost_per_token": 5.909e-07, "output_cost_per_token": 2.758e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/kimi-k2.7-code": { "max_input_tokens": 262144, "max_output_tokens": 16384, "input_cost_per_token": 1.009e-06, "output_cost_per_token": 4.774e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/kimi-k3": { "max_input_tokens": 1048576, "max_output_tokens": 32768, "input_cost_per_token": 3.052e-06, "cache_read_input_token_cost": 4.05e-07, "output_cost_per_token": 1.5258e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/kimi-k3.1-pro": { "max_input_tokens": 1048576, "max_output_tokens": 943718, "input_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 2.7e-07, "output_cost_per_token": 1.35e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/llama-3.3-70b": { "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 1.35e-07, "output_cost_per_token": 4.32e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/llama-4-maverick": { "max_input_tokens": 1048576, "max_output_tokens": 16384, "input_cost_per_token": 3.344e-07, "output_cost_per_token": 1.337e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/mimo-v2.5": { "max_input_tokens": 1050000, "max_output_tokens": 16384, "input_cost_per_token": 1.859e-07, "output_cost_per_token": 3.718e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/mimo-v2.6-flash": { "max_input_tokens": 1050000, "max_output_tokens": 131072, "input_cost_per_token": 1.89e-07, "output_cost_per_token": 3.78e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/mimo-v2.6-pro": { "max_input_tokens": 1050000, "max_output_tokens": 131072, "input_cost_per_token": 5.805e-07, "output_cost_per_token": 1.1745e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/minimax-m2.5": { "max_input_tokens": 196608, "max_output_tokens": 32768, "input_cost_per_token": 4.188e-07, "output_cost_per_token": 1.675e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/minimax-m2.7": { "max_input_tokens": 204800, "max_output_tokens": 32768, "input_cost_per_token": 4.05e-07, "output_cost_per_token": 1.62e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/minimax-m3": { "max_input_tokens": 1048576, "max_output_tokens": 32768, "input_cost_per_token": 3.956e-07, "cache_read_input_token_cost": 7.56e-08, "output_cost_per_token": 1.582e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/minimax-m3.1-flash": { "max_input_tokens": 1048576, "max_output_tokens": 524288, "input_cost_per_token": 2.025e-07, "cache_read_input_token_cost": 2.025e-08, "output_cost_per_token": 8.1e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/muse-glimmer-30b": { "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4.554e-07, "output_cost_per_token": 1.821e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/muse-spark-1.1": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 1.542e-06, "output_cost_per_token": 5.243e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/muse-spark-1.2": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 1.773e-06, "output_cost_per_token": 6.025e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/muse-spark-1.3": { "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token": 1.688e-06, "output_cost_per_token": 5.738e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/muse-spark-open": { "max_input_tokens": 1048576, "max_output_tokens": 943718, "input_cost_per_token": 1.688e-06, "output_cost_per_token": 5.738e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/muse-wonder": { "max_input_tokens": 1048576, "max_output_tokens": 943718, "input_cost_per_token": 5.4e-06, "output_cost_per_token": 2.7e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": true }, "kyma/nemotron-3-ultra-550b": { "max_input_tokens": 1000000, "max_output_tokens": 32768, "input_cost_per_token": 6.75e-07, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 3.375e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/nemotron-3.5-super-vl": { "max_input_tokens": 1048576, "max_output_tokens": 235929, "input_cost_per_token": 8.1e-08, "cache_read_input_token_cost": 1.35e-08, "output_cost_per_token": 4.725e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3-32b": { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.08e-07, "output_cost_per_token": 3.78e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3-coder": { "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_token": 3.546e-07, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 1.612e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3.6-plus": { "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token": 4.388e-07, "output_cost_per_token": 2.633e-06, "input_cost_per_token_above_256k_tokens": 1.755e-06, "output_cost_per_token_above_256k_tokens": 5.265e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3.7-max": { "max_input_tokens": 1000000, "max_output_tokens": 32768, "input_cost_per_token": 2.071e-06, "cache_read_input_token_cost": 1.6875e-07, "output_cost_per_token": 6.207e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3.7-plus": { "max_input_tokens": 1000000, "max_output_tokens": 32768, "input_cost_per_token": 4.325e-07, "cache_read_input_token_cost": 8.64e-08, "output_cost_per_token": 1.731e-06, "input_cost_per_token_above_256k_tokens": 1.296e-06, "output_cost_per_token_above_256k_tokens": 5.184e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen-3.8-max": { "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 2.228e-06, "cache_read_input_token_cost": 2.781e-07, "output_cost_per_token": 6.684e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen3.7-flash": { "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_token": 4.35e-08, "cache_read_input_token_cost": 8.1e-09, "output_cost_per_token": 1.886e-07, "input_cost_per_token_above_32k_tokens": 1.35e-07, "output_cost_per_token_above_32k_tokens": 5.4e-07, "input_cost_per_token_above_256k_tokens": 2.7e-07, "output_cost_per_token_above_256k_tokens": 1.08e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen3.8-27b": { "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 3.826e-07, "output_cost_per_token": 2.732e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/qwen3.8-flash": { "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 2.045e-07, "output_cost_per_token": 6.41e-07, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/sonar": { "max_input_tokens": 127072, "max_output_tokens": 4096, "input_cost_per_token": 1.35e-06, "output_cost_per_token": 1.35e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": false, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": false, "supports_pdf_input": false }, "kyma/sonar-pro": { "max_input_tokens": 200000, "max_output_tokens": 8000, "input_cost_per_token": 4.05e-06, "output_cost_per_token": 2.025e-05, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": false, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_response_schema": false, "supports_pdf_input": false }, "kyma/step-3.7-flash": { "max_input_tokens": 256000, "max_output_tokens": 8192, "input_cost_per_token": 2.229e-07, "cache_read_input_token_cost": 5.4e-08, "output_cost_per_token": 1.282e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "kyma/step-5-preview": { "max_input_tokens": 1048576, "max_output_tokens": 64000, "input_cost_per_token": 1.35e-06, "cache_read_input_token_cost": 1.35e-07, "output_cost_per_token": 3.645e-06, "litellm_provider": "kyma", "mode": "chat", "supports_function_calling": true, "supports_vision": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_pdf_input": false }, "databricks/databricks-claude-haiku-5-5": { "cache_creation_input_token_cost": 1.2502e-07, "cache_creation_input_token_cost_above_100k_tokens": 6.2503e-07, "cache_creation_input_token_cost_above_1hr": 1.9999e-07, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.00002e-06, "cache_read_input_token_cost": 1.001e-08, "cache_read_input_token_cost_above_100k_tokens": 4.998e-08, "input_cost_per_token": 1.0003e-07, "input_cost_per_token_above_100k_tokens": 5.0001e-07, "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.0001e-07, "output_cost_per_token_above_100k_tokens": 2.49998e-06, "output_dbu_cost_per_token": 7.143e-06, "prompt_cache_min_tokens": 512.0, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "thinking_on_by_default": true, "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": false }, "databricks/claude-haiku-latest": { "alias_of": "databricks/databricks-claude-haiku-5-5" }, "databricks/databricks-claude-sonnet-5-5": { "cache_creation_input_token_cost": 2.49998e-06, "cache_creation_input_token_cost_above_1hr": 4.00001e-06, "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.99997e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.00014286, "prompt_cache_min_tokens": 512.0, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": false, "thinking_always_on": true }, "databricks/claude-sonnet-latest": { "alias_of": "databricks/databricks-claude-sonnet-5-5" }, "databricks/databricks-deepseek-v4-1-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.003e-08, "deprecation_date": "2026-11-19", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "input_cost_per_token": 3.0002e-07, "input_dbu_cost_per_token": 4.286e-06, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 384000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. The docs list only databricks-deepseek-v4-1-flash (retiring 2026-11-19) and databricks-deepseek-v4-1-flash-1017, so the pricing page's 'DeepSeek V4.1 Flash (0910)' row prices the unsuffixed endpoint." }, "mode": "chat", "output_cost_per_token": 1.20001e-06, "output_dbu_cost_per_token": 1.7143e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token_priority": 2.1e-06, "cache_read_input_token_cost_priority": 5.25e-08, "cache_creation_input_token_cost_priority": 5.25e-07, "successor_model": "databricks/databricks-deepseek-v4-1-flash-1017" }, "databricks/databricks-deepseek-v4-1-flash-1017": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3.0002e-07, "input_dbu_cost_per_token": 4.286e-06, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 384000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.20001e-06, "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-gemini-2-5-flash-lite": { "cache_creation_input_token_cost": 1.2502e-07, "cache_read_input_audio_token_cost": 3.752e-08, "cache_read_input_token_cost": 1.253e-08, "input_cost_per_audio_token": 3.7499e-07, "input_cost_per_image_token": 1.2502e-07, "input_cost_per_token": 1.2502e-07, "input_dbu_cost_per_token": 1.786e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.0001e-07, "output_dbu_cost_per_token": 7.143e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "databricks/databricks-gemini-3-1-flash-lite-image": { "cache_creation_input_token_cost": 3.1248e-07, "cache_read_input_token_cost": 3.1248e-07, "input_cost_per_image_token": 3.1248e-07, "input_cost_per_token": 3.1248e-07, "input_dbu_cost_per_token": 4.464e-06, "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 4096, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_image_token": 3.749998e-05, "output_cost_per_token": 1.87502e-06, "output_dbu_cost_per_token": 2.6786e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_function_calling": false, "supports_vision": true }, "databricks/databricks-gemini-4-argon": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 1.2502e-07, "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 1.249997e-05, "output_dbu_cost_per_token": 0.00017857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, "input_cost_per_token_priority": 4.50002e-06, "output_cost_per_token_priority": 2.250003e-05, "cache_read_input_token_cost_priority": 2.2498e-07, "cache_creation_input_token_cost_priority": 4.50002e-06 }, "databricks/databricks-gpt-5-4-pro": { "cache_creation_input_token_cost": 2.999997e-05, "cache_read_input_token_cost": 2.999997e-05, "input_cost_per_token": 2.999997e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_dbu_cost_per_token": 0.00042857, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 0.0001800001, "output_cost_per_token_above_272k_tokens": 0.00027, "output_dbu_cost_per_token": 0.0025714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "databricks/databricks-gpt-6-1-sol": { "cache_creation_input_token_cost": 2.49998e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, "cache_read_input_token_cost": 1.0003e-07, "cache_read_input_token_cost_above_272k_tokens": 1.9999e-07, "input_cost_per_token": 1.99997e-06, "input_cost_per_token_above_272k_tokens": 4.00001e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 9.99999e-06, "output_cost_per_token_above_272k_tokens": 1.5e-05, "output_dbu_cost_per_token": 0.00014286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 4.00001e-06, "output_cost_per_token_priority": 1.99997e-05, "cache_read_input_token_cost_priority": 1.9999e-07, "cache_creation_input_token_cost_priority": 5.00003e-06, "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 3.9998e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, "databricks/gpt-sol-latest": { "alias_of": "databricks/databricks-gpt-6-1-sol" }, "databricks/databricks-gpt-6-1-terra": { "cache_creation_input_token_cost": 1.24999e-06, "cache_creation_input_token_cost_above_272k_tokens": 2.49998e-06, "cache_read_input_token_cost": 4.998e-08, "cache_read_input_token_cost_above_272k_tokens": 1.0003e-07, "input_cost_per_token": 1.00002e-06, "input_cost_per_token_above_272k_tokens": 1.99997e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.00003e-06, "output_cost_per_token_above_272k_tokens": 7.50001e-06, "output_dbu_cost_per_token": 7.1429e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.99997e-06, "output_cost_per_token_priority": 9.99999e-06, "cache_read_input_token_cost_priority": 1.0003e-07, "cache_creation_input_token_cost_priority": 2.49998e-06, "input_cost_per_token_above_272k_tokens_priority": 4.00001e-06, "output_cost_per_token_above_272k_tokens_priority": 1.500002e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 1.9999e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5.00003e-06 }, "databricks/gpt-terra-latest": { "alias_of": "databricks/databricks-gpt-6-1-terra" }, "databricks/databricks-gpt-6-astra": { "cache_creation_input_token_cost": 1.249997e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, "cache_read_input_token_cost": 1.00002e-06, "cache_read_input_token_cost_above_272k_tokens": 1.99997e-06, "input_cost_per_token": 9.99999e-06, "input_cost_per_token_above_272k_tokens": 2e-05, "input_dbu_cost_per_token": 0.00014286, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 5.000002e-05, "output_cost_per_token_above_272k_tokens": 7.50001e-05, "output_dbu_cost_per_token": 0.00071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.999998e-05, "output_cost_per_token_priority": 9.99999e-05, "cache_read_input_token_cost_priority": 1.99997e-06, "cache_creation_input_token_cost_priority": 2.500001e-05, "input_cost_per_token_above_272k_tokens_priority": 4.000003e-05, "output_cost_per_token_above_272k_tokens_priority": 0.0001500002, "cache_read_input_token_cost_above_272k_tokens_priority": 4.00001e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 5.000002e-05 }, "databricks/gpt-astra-latest": { "alias_of": "databricks/databricks-gpt-6-astra" }, "databricks/databricks-gpt-6-luna": { "cache_creation_input_token_cost": 1.2502e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.4997e-07, "cache_read_input_token_cost": 1.001e-08, "cache_read_input_token_cost_above_272k_tokens": 2.002e-08, "input_cost_per_token": 1.0003e-07, "input_cost_per_token_above_272k_tokens": 1.9999e-07, "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 5.0001e-07, "output_cost_per_token_above_272k_tokens": 7.497e-07, "output_dbu_cost_per_token": 7.143e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 1.9999e-07, "output_cost_per_token_priority": 1.0003e-06, "cache_read_input_token_cost_priority": 2.002e-08, "cache_creation_input_token_cost_priority": 2.4997e-07, "input_cost_per_token_above_272k_tokens_priority": 3.9998e-07, "output_cost_per_token_above_272k_tokens_priority": 1.5001e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 3.997e-08, "cache_creation_input_token_cost_above_272k_tokens_priority": 5.0001e-07 }, "databricks/gpt-luna-latest": { "alias_of": "databricks/databricks-gpt-6-luna" }, "databricks/databricks-gpt-6-sol": { "cache_creation_input_token_cost": 2.49998e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.00003e-06, "cache_read_input_token_cost": 1.9999e-07, "cache_read_input_token_cost_above_272k_tokens": 3.9998e-07, "input_cost_per_token": 1.99997e-06, "input_cost_per_token_above_272k_tokens": 4.00001e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "responses", "output_cost_per_token": 9.99999e-06, "output_cost_per_token_above_272k_tokens": 1.50003e-05, "output_dbu_cost_per_token": 0.00014286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "input_cost_per_token_priority": 4.00001e-06, "output_cost_per_token_priority": 1.99997e-05, "cache_read_input_token_cost_priority": 3.9998e-07, "cache_creation_input_token_cost_priority": 5.00003e-06, "input_cost_per_token_above_272k_tokens_priority": 8.00002e-06, "output_cost_per_token_above_272k_tokens_priority": 2.99999e-05, "cache_read_input_token_cost_above_272k_tokens_priority": 8.0003e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 9.99999e-06 }, "databricks/databricks-gpt-image-1": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 1.24999e-06, "input_cost_per_image_token": 9.99999e-06, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "image_generation", "output_cost_per_image_token": 4.000003e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-image-1-5": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 1.24999e-06, "input_cost_per_image_token": 8.00002e-06, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "image_generation", "output_cost_per_image_token": 3.200001e-05, "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.00014286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_pdf_input": true, "supports_vision": true }, "databricks/databricks-gpt-image-1-mini": { "cache_creation_input_token_cost": 1.99997e-06, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_image_token": 2.49998e-06, "input_cost_per_token": 1.99997e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "image_generation", "output_cost_per_image_token": 8.00002e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" }, "databricks/databricks-gpt-image-2": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 1.24999e-06, "input_cost_per_image_token": 8.00002e-06, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "image_generation", "output_cost_per_image_token": 2.999997e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_pdf_input": true, "supports_vision": true }, "databricks/databricks-grok-4-7": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 6.2503e-07, "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", "max_input_tokens": 500000, "max_output_tokens": 500000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 7.50001e-06, "output_dbu_cost_per_token": 0.00010714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "databricks/grok-latest": { "alias_of": "databricks/databricks-grok-4-7" }, "databricks/databricks-kimi-k2-7": { "cache_creation_input_token_cost": 9.4997e-07, "cache_read_input_token_cost": 1.8998e-07, "deprecation_date": "2026-10-30", "deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy", "input_cost_per_token": 9.4997e-07, "input_dbu_cost_per_token": 1.3571e-05, "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 262144, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", "output_cost_per_token": 4.00001e-06, "output_dbu_cost_per_token": 5.7143e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "successor_model": "databricks/databricks-kimi-k3", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash": { "cache_read_input_token_cost": 2.1e-08, "deprecation_date": "2026-08-14", "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md", "input_cost_per_token": 1.05e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.1e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "successor_model": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/kimi-k3-spot": { "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.05e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-spot": { "cache_read_input_token_cost": 1.82e-07, "input_cost_per_token": 9.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.08e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot": { "cache_read_input_token_cost": 4.2e-09, "input_cost_per_token": 2.1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast": { "cache_read_input_token_cost": 4.8e-08, "input_cost_per_token": 2.4e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 9.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing.md", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": { "cache_read_input_token_cost": 4.2e-09, "input_cost_per_token": 2.1e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "mode": "chat", "output_cost_per_token": 8.4e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bigmodel/glm-5.3": { "input_cost_per_token": 1.1428571428571428e-06, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2.857142857142857e-07, "litellm_provider": "bigmodel", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "metadata": { "comment": "Official API list price checked 2026-10-27: input 8, output 28, cached input 2 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_native_streaming": true }, "bigmodel/glm-5.3-flash": { "input_cost_per_token": 1.142857142857143e-07, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 3.2857142857142855e-08, "litellm_provider": "bigmodel", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "supports_vision": true, "supports_video_input": true, "metadata": { "comment": "Official API list price checked 2026-10-27: input 0.8, output 2.8, cached input 0.23 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_native_streaming": true }, "bigmodel/glm-5.3-flashx": { "input_cost_per_token": 2.857142857142857e-07, "output_cost_per_token": 1e-06, "cache_read_input_token_cost": 8.142857142857142e-08, "litellm_provider": "bigmodel", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "source": "https://docs.bigmodel.cn/cn/guide/start/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "supports_vision": true, "supports_video_input": true, "metadata": { "comment": "Official API list price checked 2026-10-27: input 2, output 7, cached input 0.57 CNY per million tokens; converted at 7.0 CNY/USD. Cache storage is temporarily free and is not encoded." }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supports_native_streaming": true }, "fireworks_ai/accounts/fireworks/models/ultramarine-1-flash-us": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, "source": "https://docs.fireworks.ai/serverless/pricing.md", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, "supports_vision": true }, "baseten/decision-models/baseten-joey-2b-latest": { "input_cost_per_token": 1e-08, "litellm_provider": "baseten", "max_input_tokens": 16384, "mode": "decisions", "output_cost_per_token": 0.0, "source": "https://inference.baseten.co/v1/models", "supports_vision": true }, "gpt-6-rosalind": { "cache_creation_input_token_cost": 1.875e-05, "cache_creation_input_token_cost_above_12hr": 3.75e-05, "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 7.5e-05, "cache_creation_input_token_cost_above_272k_tokens": 3.75e-05, "cache_read_input_token_cost": 1.5e-06, "cache_read_input_token_cost_above_272k_tokens": 3e-06, "input_cost_per_token": 1.5e-05, "input_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-6-rosalind": { "litellm_provider": "chatgpt", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-cyber": { "cache_creation_input_token_cost": 2.5e-05, "cache_creation_input_token_cost_above_12hr": 5e-05, "cache_read_input_token_cost": 2e-06, "cache_read_input_token_cost_above_272k_tokens": 4e-06, "input_cost_per_token": 2e-05, "input_cost_per_token_above_272k_tokens": 4e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0001, "output_cost_per_token_above_272k_tokens": 0.00015, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true }, "gpt-6-astra-law": { "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "reasoning_contexts": [ "auto", "current_turn", "all_turns" ], "reasoning_modes": [ "standard", "pro" ], "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "fedramp_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-6-astra-law": { "litellm_provider": "chatgpt", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true }, "nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "max_input_tokens": 1048576, "input_cost_per_token": 3e-07, "cache_read_input_token_cost": 6e-09, "output_cost_per_token": 1.2e-06, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "supports_reasoning": true, "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "nebius/meta-models/muse-spark-open": { "max_input_tokens": 1048576, "input_cost_per_token": 1.25e-06, "cache_read_input_token_cost": 1.5e-07, "output_cost_per_token": 4.25e-06, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "supports_video_input": true, "supports_reasoning": true, "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "nebius/MiniMaxAI/MiniMax-M3.1-Flash": { "max_input_tokens": 1048576, "input_cost_per_token": 1.5e-07, "cache_read_input_token_cost": 1.5e-08, "output_cost_per_token": 6e-07, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "supports_reasoning": true, "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "nebius/nvidia/Nemotron-3.5-Super-VL": { "max_input_tokens": 1048576, "input_cost_per_token": 3e-07, "cache_read_input_token_cost": 6e-08, "output_cost_per_token": 9e-07, "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, "supports_video_input": true, "supports_reasoning": true, "supports_function_calling": true, "source": "https://tokenfactory.nebius.com/api/public/models_info" }, "empiriolabs/aplomb-1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "input_cost_per_token": 2e-08, "output_cost_per_token": 0.0, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages", "/v1/decisions" ], "supports_vision": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/aplomb-1" }, "empiriolabs/deepseek-v4-1-flash-1017": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-1-flash-1017", "cache_read_input_token_cost": 2e-08, "supports_prompt_caching": true, "supports_function_calling": true }, "empiriolabs/deepseek-v4-flash-0731": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 4.24e-07, "output_cost_per_token": 1.272e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", "supports_function_calling": true }, "empiriolabs/deepseek-v4-flash-0731:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 4.4e-07, "output_cost_per_token": 1.32e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-flash-0731", "supports_function_calling": true }, "empiriolabs/deepseek-v4-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 3.3e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-pro", "supports_function_calling": true }, "empiriolabs/deepseek-v4-pro-0813": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 1.32e-06, "output_cost_per_token": 3.96e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-pro-0813", "supports_function_calling": true }, "empiriolabs/deepseek-v4-pro:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 2.4e-06, "output_cost_per_token": 4.8e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-pro", "supports_function_calling": true }, "empiriolabs/deepseek-v4-pro:variant2": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 3.301e-06, "cache_read_input_token_cost": 1.38e-07, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-pro", "supports_function_calling": true }, "empiriolabs/deepseek-v4-pro:variant3": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token": 2.4e-06, "output_cost_per_token": 4.8e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/deepseek-v4-pro", "supports_function_calling": true }, "empiriolabs/fugu-max": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.5e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.007, "search_context_size_medium": 0.007, "search_context_size_high": 0.007 }, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/fugu-max" }, "empiriolabs/fugu-ultra-v1-0": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 7.5e-06, "output_cost_per_token": 4.5e-05, "input_cost_per_token_above_272k_tokens": 1.5e-05, "output_cost_per_token_above_272k_tokens": 6.75e-05, "cache_read_input_token_cost_above_272k_tokens": 3e-06, "cache_read_input_token_cost": 1.5e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/fugu-ultra-v1-0" }, "empiriolabs/fugu-ultra-v1-1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 5e-06, "output_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 1e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost": 5e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/fugu-ultra-v1-1" }, "empiriolabs/fugu-ultra-v2-0": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 5e-06, "output_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 1e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost": 5e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/fugu-ultra-v2-0" }, "empiriolabs/gemma-4-26b-a4b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.9e-07, "cache_read_input_token_cost": 2.5e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/gemma-4-26b-a4b" }, "empiriolabs/glm-4-6v-flashx": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 3.6e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.033, "search_context_size_medium": 0.033, "search_context_size_high": 0.033 }, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-4-6v-flashx" }, "empiriolabs/glm-4-7-flashx": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 202752, "max_output_tokens": 131072, "input_cost_per_token": 7e-08, "output_cost_per_token": 4e-07, "cache_read_input_token_cost": 6.3e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.033, "search_context_size_medium": 0.033, "search_context_size_high": 0.033 }, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-4-7-flashx" }, "empiriolabs/glm-5-1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 202745, "max_output_tokens": 128000, "input_cost_per_token": 8.25e-07, "output_cost_per_token": 3.301e-06, "input_cost_per_token_above_32k_tokens": 1.1e-06, "output_cost_per_token_above_32k_tokens": 3.851e-06, "cache_read_input_token_cost_above_32k_tokens": 2.2e-07, "cache_read_input_token_cost": 1.65e-07, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-1" }, "empiriolabs/glm-5-2": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.033, "search_context_size_medium": 0.033, "search_context_size_high": 0.033 }, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-2" }, "empiriolabs/glm-5-2:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.1e-06, "output_cost_per_token": 3.851e-06, "cache_read_input_token_cost": 2.75e-07, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-2", "supports_function_calling": true }, "empiriolabs/glm-5-2:variant2": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-2", "supports_function_calling": true }, "empiriolabs/glm-5-3": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.033, "search_context_size_medium": 0.033, "search_context_size_high": 0.033 }, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-3" }, "empiriolabs/glm-5-3-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 7.5e-08, "output_cost_per_token": 2.5e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.033, "search_context_size_medium": 0.033, "search_context_size_high": 0.033 }, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/glm-5-3-flash" }, "empiriolabs/kimi-k2-6": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 16000, "input_cost_per_token": 8.939e-07, "output_cost_per_token": 3.7131e-06, "cache_read_input_token_cost": 1.788e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/kimi-k2-6", "supports_function_calling": true }, "empiriolabs/kimi-k2-7-code": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/kimi-k2-7-code", "supports_function_calling": true }, "empiriolabs/kimi-k2-7-code-highspeed": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1.9e-06, "output_cost_per_token": 8e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/kimi-k2-7-code-highspeed", "supports_function_calling": true }, "empiriolabs/kimi-k2-7-code:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 16384, "input_cost_per_token": 8.939e-07, "output_cost_per_token": 3.7131e-06, "cache_read_input_token_cost": 1.788e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/kimi-k2-7-code", "supports_function_calling": true }, "empiriolabs/kimi-k3": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/kimi-k3", "supports_function_calling": true }, "empiriolabs/kimi-k3-1-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.8e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_prompt_caching": true, "supports_response_schema": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/kimi-k3-1-pro" }, "empiriolabs/mimo-v2-6-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/mimo-v2-6-flash", "supports_function_calling": true }, "empiriolabs/mimo-v2-6-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/mimo-v2-6-pro", "supports_function_calling": true }, "empiriolabs/mimo-v2-6-pro-ultraspeed": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 4.35e-06, "output_cost_per_token": 8.7e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/mimo-v2-6-pro-ultraspeed", "supports_function_calling": true }, "empiriolabs/minimax-m2-7": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 204800, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 3e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/minimax-m2-7" }, "empiriolabs/minimax-m2-7-highspeed": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 204800, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 3e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/minimax-m2-7-highspeed" }, "empiriolabs/minimax-m3": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 524288, "input_cost_per_token": 2.25e-07, "output_cost_per_token": 9e-07, "input_cost_per_token_above_512k_tokens": 4.5e-07, "output_cost_per_token_above_512k_tokens": 1.8e-06, "cache_read_input_token_cost_above_512k_tokens": 9e-08, "cache_read_input_token_cost": 4.5e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/minimax-m3" }, "empiriolabs/minimax-m3-1-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 524288, "input_cost_per_token": 1.125e-07, "output_cost_per_token": 4.5e-07, "cache_read_input_token_cost": 1.125e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/minimax-m3-1-flash" }, "empiriolabs/minimax-m3:priority": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048458, "max_output_tokens": 524288, "input_cost_per_token": 3.375e-07, "output_cost_per_token": 1.35e-06, "input_cost_per_token_above_512k_tokens": 6.75e-07, "output_cost_per_token_above_512k_tokens": 2.7e-06, "cache_read_input_token_cost_above_512k_tokens": 1.35e-07, "cache_read_input_token_cost": 6.75e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/minimax-m3" }, "empiriolabs/mistral-small-4": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 65536, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.084, "search_context_size_medium": 0.084, "search_context_size_high": 0.14 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/mistral-small-4", "supports_function_calling": true }, "empiriolabs/muse-glimmer-30b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, "output_cost_per_token": 8e-07, "cache_read_input_token_cost": 5e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/muse-glimmer-30b", "supports_function_calling": true }, "empiriolabs/muse-spark-1-1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 4.25e-06, "cache_read_input_token_cost": 1e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/muse-spark-1-1" }, "empiriolabs/muse-spark-1-2": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 4.25e-06, "cache_read_input_token_cost": 1e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/muse-spark-1-2" }, "empiriolabs/muse-spark-1-3": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_cost_per_token": 1.25e-06, "output_cost_per_token": 4.25e-06, "cache_read_input_token_cost": 1e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/muse-spark-1-3" }, "empiriolabs/nova-lite-1-0": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 317379, "max_output_tokens": 10000, "input_cost_per_token": 6.9e-08, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 3.86e-08, "supports_system_messages": true, "supports_vision": true, "supports_prompt_caching": true, "source": "https://empiriolabs.ai/models/nova-lite-1-0", "supports_function_calling": true }, "empiriolabs/nova-lite-2": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 3.16e-06, "cache_read_input_token_cost": 2.128e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://empiriolabs.ai/models/nova-lite-2", "supports_function_calling": true }, "empiriolabs/nova-micro-1-0": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 133003, "max_output_tokens": 10000, "input_cost_per_token": 4e-08, "output_cost_per_token": 1.6e-07, "cache_read_input_token_cost": 2.24e-08, "supports_system_messages": true, "supports_prompt_caching": true, "source": "https://empiriolabs.ai/models/nova-micro-1-0", "supports_function_calling": true }, "empiriolabs/nova-pro-1-0": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 317319, "max_output_tokens": 10000, "input_cost_per_token": 2.4e-06, "output_cost_per_token": 9.6e-06, "supports_system_messages": true, "supports_vision": true, "source": "https://empiriolabs.ai/models/nova-pro-1-0", "supports_function_calling": true }, "empiriolabs/perplexity-advanced-deep-research": { "litellm_provider": "empiriolabs", "mode": "chat", "max_output_tokens": 16000, "input_cost_per_token": 1.2e-05, "output_cost_per_token": 6e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.012, "search_context_size_medium": 0.012, "search_context_size_high": 0.012 }, "source": "https://empiriolabs.ai/models/perplexity-advanced-deep-research" }, "empiriolabs/perplexity-deep-research": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 919327, "input_cost_per_token": 4.8e-06, "output_cost_per_token": 1.9e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "source": "https://empiriolabs.ai/models/perplexity-deep-research" }, "empiriolabs/perplexity-pro-search": { "litellm_provider": "empiriolabs", "mode": "chat", "max_output_tokens": 32768, "input_cost_per_token": 7.8e-06, "output_cost_per_token": 3.9e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "source": "https://empiriolabs.ai/models/perplexity-pro-search" }, "empiriolabs/perplexity-sonar": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 919327, "input_cost_per_token": 2.4e-06, "output_cost_per_token": 2.4e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "source": "https://empiriolabs.ai/models/perplexity-sonar" }, "empiriolabs/perplexity-sonar-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 919328, "max_output_tokens": 32768, "input_cost_per_token": 7.2e-06, "output_cost_per_token": 3.6e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "source": "https://empiriolabs.ai/models/perplexity-sonar-pro" }, "empiriolabs/perplexity-sonar-reasoning-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 919330, "max_output_tokens": 131072, "input_cost_per_token": 4.8e-06, "output_cost_per_token": 1.9e-05, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "source": "https://empiriolabs.ai/models/perplexity-sonar-reasoning-pro" }, "empiriolabs/qwen3-5-122b-a10b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 258048, "max_output_tokens": 64000, "input_cost_per_token": 1.15e-07, "output_cost_per_token": 9.17e-07, "input_cost_per_token_above_128k_tokens": 2.87e-07, "output_cost_per_token_above_128k_tokens": 2.294e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-122b-a10b", "supports_function_calling": true }, "empiriolabs/qwen3-5-27b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 258048, "max_output_tokens": 64000, "input_cost_per_token": 8.6e-08, "output_cost_per_token": 6.88e-07, "input_cost_per_token_above_128k_tokens": 2.58e-07, "output_cost_per_token_above_128k_tokens": 2.064e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-27b", "supports_function_calling": true }, "empiriolabs/qwen3-5-35b-a3b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 258048, "max_output_tokens": 64000, "input_cost_per_token": 5.7e-08, "output_cost_per_token": 4.59e-07, "input_cost_per_token_above_128k_tokens": 2.29e-07, "output_cost_per_token_above_128k_tokens": 1.835e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-35b-a3b", "supports_function_calling": true }, "empiriolabs/qwen3-5-397b-a17b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 258048, "max_output_tokens": 64000, "input_cost_per_token": 1.72e-07, "output_cost_per_token": 1.032e-06, "input_cost_per_token_above_128k_tokens": 4.3e-07, "output_cost_per_token_above_128k_tokens": 2.58e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-397b-a17b", "supports_function_calling": true }, "empiriolabs/qwen3-5-4b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, "output_cost_per_token": 7e-08, "cache_read_input_token_cost": 2e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-4b" }, "empiriolabs/qwen3-5-9b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 32768, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.3e-07, "cache_read_input_token_cost": 4.5e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-9b" }, "empiriolabs/qwen3-5-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 995904, "max_output_tokens": 32768, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.68e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-flash", "supports_function_calling": true }, "empiriolabs/qwen3-5-flash:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 995904, "max_output_tokens": 65536, "input_cost_per_token": 2.9e-08, "output_cost_per_token": 2.87e-07, "input_cost_per_token_above_128k_tokens": 1.15e-07, "output_cost_per_token_above_128k_tokens": 1.147e-06, "input_cost_per_token_above_256k_tokens": 1.72e-07, "output_cost_per_token_above_256k_tokens": 1.72e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-flash", "supports_function_calling": true }, "empiriolabs/qwen3-5-omni-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 196608, "max_output_tokens": 32768, "input_cost_per_token": 8e-07, "output_cost_per_token": 4.4e-06, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/qwen3-5-omni-flash", "supports_function_calling": true }, "empiriolabs/qwen3-5-omni-plus": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 196608, "max_output_tokens": 32768, "input_cost_per_token": 2.8e-06, "output_cost_per_token": 1.66e-05, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/qwen3-5-omni-plus", "supports_function_calling": true }, "empiriolabs/qwen3-5-plus": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 3.6e-07, "output_cost_per_token": 2.21e-06, "input_cost_per_token_above_256k_tokens": 4.5e-07, "output_cost_per_token_above_256k_tokens": 2.76e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.015, "search_context_size_medium": 0.015, "search_context_size_high": 0.015 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-plus", "supports_function_calling": true }, "empiriolabs/qwen3-5-plus:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 1.15e-07, "output_cost_per_token": 6.88e-07, "input_cost_per_token_above_128k_tokens": 2.87e-07, "output_cost_per_token_above_128k_tokens": 1.72e-06, "input_cost_per_token_above_256k_tokens": 5.73e-07, "output_cost_per_token_above_256k_tokens": 3.44e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-5-plus", "supports_function_calling": true }, "empiriolabs/qwen3-6-27b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229376, "max_output_tokens": 64000, "input_cost_per_token": 4.12564e-07, "output_cost_per_token": 2.475384e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-27b", "supports_function_calling": true }, "empiriolabs/qwen3-6-35b-a3b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, "output_cost_per_token": 4.2e-07, "cache_read_input_token_cost": 3.5e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-35b-a3b", "supports_function_calling": true }, "empiriolabs/qwen3-6-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, "input_cost_per_token_above_256k_tokens": 1e-06, "output_cost_per_token_above_256k_tokens": 4e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-flash", "supports_function_calling": true }, "empiriolabs/qwen3-6-flash:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 1.65e-07, "output_cost_per_token": 9.9e-07, "input_cost_per_token_above_256k_tokens": 6.6e-07, "output_cost_per_token_above_256k_tokens": 3.961e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-flash", "supports_function_calling": true }, "empiriolabs/qwen3-6-plus": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, "input_cost_per_token_above_256k_tokens": 2e-06, "output_cost_per_token_above_256k_tokens": 6e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.026, "search_context_size_medium": 0.026, "search_context_size_high": 0.026 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-plus", "supports_function_calling": true }, "empiriolabs/qwen3-6-plus:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 2.76e-07, "output_cost_per_token": 1.651e-06, "input_cost_per_token_above_256k_tokens": 1.101e-06, "output_cost_per_token_above_256k_tokens": 6.602e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-6-plus", "supports_function_calling": true }, "empiriolabs/qwen3-7-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.3e-07, "input_cost_per_token_above_32k_tokens": 1e-07, "output_cost_per_token_above_32k_tokens": 4e-07, "cache_read_input_token_cost_above_32k_tokens": 2e-08, "input_cost_per_token_above_256k_tokens": 2e-07, "output_cost_per_token_above_256k_tokens": 8e-07, "cache_read_input_token_cost_above_256k_tokens": 4e-08, "cache_read_input_token_cost": 6e-09, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.03, "search_context_size_medium": 0.03, "search_context_size_high": 0.03 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-flash", "supports_function_calling": true }, "empiriolabs/qwen3-7-flash:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 2.8e-08, "output_cost_per_token": 1.1e-07, "input_cost_per_token_above_32k_tokens": 8.3e-08, "output_cost_per_token_above_32k_tokens": 3.3e-07, "cache_read_input_token_cost_above_32k_tokens": 1.7e-08, "input_cost_per_token_above_256k_tokens": 1.65e-07, "output_cost_per_token_above_256k_tokens": 6.6e-07, "cache_read_input_token_cost_above_256k_tokens": 3.3e-08, "cache_read_input_token_cost": 6e-09, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-flash", "supports_function_calling": true }, "empiriolabs/qwen3-7-max": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-max", "supports_function_calling": true }, "empiriolabs/qwen3-7-max:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-max", "supports_function_calling": true }, "empiriolabs/qwen3-7-plus": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.6e-06, "input_cost_per_token_above_256k_tokens": 1.2e-06, "output_cost_per_token_above_256k_tokens": 4.8e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.03, "search_context_size_medium": 0.03, "search_context_size_high": 0.03 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-plus", "supports_function_calling": true }, "empiriolabs/qwen3-7-plus:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 65536, "input_cost_per_token": 2.76e-07, "output_cost_per_token": 1.101e-06, "input_cost_per_token_above_256k_tokens": 8.26e-07, "output_cost_per_token_above_256k_tokens": 3.301e-06, "cache_read_input_token_cost_above_256k_tokens": 1.66e-07, "cache_read_input_token_cost": 5.6e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_prompt_caching": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-7-plus", "supports_function_calling": true }, "empiriolabs/qwen3-8-27b": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 32768, "input_cost_per_token": 1.7e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 8e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-8-27b" }, "empiriolabs/qwen3-8-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 131072, "input_cost_per_token": 1.6e-07, "output_cost_per_token": 4.7e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-8-flash", "supports_function_calling": true }, "empiriolabs/qwen3-8-max": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 131072, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-8-max", "supports_function_calling": true }, "empiriolabs/qwen3-8-max-0902": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 131072, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-8-max-0902", "supports_function_calling": true }, "empiriolabs/qwen3-8-max:variant1": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 983616, "max_output_tokens": 131072, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.01, "search_context_size_medium": 0.01, "search_context_size_high": 0.01 }, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/qwen3-8-max", "supports_function_calling": true }, "empiriolabs/qwen3-8-omni-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1006592, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 9.4e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.02, "search_context_size_medium": 0.02, "search_context_size_high": 0.02 }, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/qwen3-8-omni-flash", "supports_function_calling": true }, "empiriolabs/seed-2-0-code": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229096, "max_output_tokens": 128000, "input_cost_per_token": 4e-07, "output_cost_per_token": 2.4e-06, "input_cost_per_token_above_128k_tokens": 8e-07, "output_cost_per_token_above_128k_tokens": 4.8e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "source": "https://empiriolabs.ai/models/seed-2-0-code", "supports_function_calling": true }, "empiriolabs/seed-2-0-lite": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229096, "max_output_tokens": 128000, "input_cost_per_token": 3.1e-07, "output_cost_per_token": 2.5e-06, "input_cost_per_token_above_128k_tokens": 6.2e-07, "output_cost_per_token_above_128k_tokens": 5e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/seed-2-0-lite", "supports_function_calling": true }, "empiriolabs/seed-2-0-mini": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229156, "max_output_tokens": 128000, "input_cost_per_token": 1.2e-07, "output_cost_per_token": 5e-07, "input_cost_per_token_above_128k_tokens": 2.4e-07, "output_cost_per_token_above_128k_tokens": 1e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/seed-2-0-mini", "supports_function_calling": true }, "empiriolabs/seed-2-0-pro": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229096, "max_output_tokens": 128000, "input_cost_per_token": 6.3e-07, "output_cost_per_token": 3.79e-06, "input_cost_per_token_above_128k_tokens": 1.26e-06, "output_cost_per_token_above_128k_tokens": 7.58e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/seed-2-0-pro", "supports_function_calling": true }, "empiriolabs/seed-2-1-turbo": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 229093, "max_output_tokens": 65536, "input_cost_per_token": 6.3e-07, "output_cost_per_token": 3.13e-06, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/seed-2-1-turbo", "supports_function_calling": true }, "empiriolabs/skylark-embedding-vision": { "litellm_provider": "empiriolabs", "mode": "embedding", "max_input_tokens": 8000, "input_cost_per_token": 2.5e-07, "supports_embedding_image_input": true, "source": "https://empiriolabs.ai/models/skylark-embedding-vision" }, "empiriolabs/step-3-5-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "cache_read_input_token_cost": 2e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/step-3-5-flash" }, "empiriolabs/step-3-5-flash-2603": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "cache_read_input_token_cost": 2e-08, "supports_system_messages": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_function_calling": true, "source": "https://empiriolabs.ai/models/step-3-5-flash-2603" }, "empiriolabs/step-3-7-flash": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, "cache_read_input_token_cost": 4e-08, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/step-3-7-flash" }, "empiriolabs/step-5-preview": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 1024000, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, "output_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1e-07, "supports_system_messages": true, "supports_vision": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "source": "https://empiriolabs.ai/models/step-5-preview" }, "empiriolabs/stepaudio-2-5-chat": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 3e-07, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.013, "search_context_size_medium": 0.013, "search_context_size_high": 0.013 }, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/stepaudio-2-5-chat" }, "empiriolabs/stepaudio-3-chat": { "litellm_provider": "empiriolabs", "mode": "chat", "max_input_tokens": 262144, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 3e-07, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_function_calling": true, "supports_response_schema": true, "supports_audio_input": true, "source": "https://empiriolabs.ai/models/stepaudio-3-chat" }, "empiriolabs/text-embedding-v4": { "litellm_provider": "empiriolabs", "mode": "embedding", "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "source": "https://empiriolabs.ai/models/text-embedding-v4" }, "empiriolabs/tongyi-embedding-vision-flash": { "litellm_provider": "empiriolabs", "mode": "embedding", "max_input_tokens": 1024, "input_cost_per_token": 9e-08, "supports_embedding_image_input": true, "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-flash" }, "empiriolabs/tongyi-embedding-vision-plus": { "litellm_provider": "empiriolabs", "mode": "embedding", "max_input_tokens": 1024, "input_cost_per_token": 9e-08, "supports_embedding_image_input": true, "source": "https://empiriolabs.ai/models/tongyi-embedding-vision-plus" }, "wally/glm-5.3-flash": { "cache_read_input_token_cost": 7.6e-08, "input_cost_per_token": 2.72e-07, "litellm_provider": "wally", "max_input_tokens": 1048567, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.5e-07, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/deepseek-v4.1-flash": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "wally", "max_input_tokens": 1048569, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "reasoning_effort_levels": [ "none", "low", "medium", "high", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "wally/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "wally/deepseek-v4.1-flash-fast": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 6e-07, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "reasoning_effort_levels": [ "none", "low", "medium", "high", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "wally/glm-5.3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "reasoning_effort_levels": [ "low", "medium", "high", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/deepseek-v4-pro-fast": { "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 1.91e-06, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.83e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.32e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/minimax-m3": { "cache_read_input_token_cost": 6.6e-08, "input_cost_per_token": 3.3e-07, "litellm_provider": "wally", "max_input_tokens": 524287, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.32e-06, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://www.runwally.com/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/deepseek-v4.1-flash-1017": { "cache_read_input_token_cost": 8e-09, "input_cost_per_token": 3.75e-07, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "max" ], "source": "https://inference.runanywhere.ai/v1/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "wally/deepseek-v4.1-flash-f2": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "wally", "max_input_tokens": 1048576, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "reasoning_effort_levels": [ "none", "minimal", "low", "medium", "high", "max" ], "source": "https://inference.runanywhere.ai/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/moonshotai/Kimi-K3.1-Pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3.6e-06, "input_cost_per_token_batches": 1.8e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.8e-05, "output_cost_per_token_batches": 9e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/us-gov-east-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3.6e-06, "input_cost_per_token_batches": 1.8e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.8e-05, "output_cost_per_token_batches": 9e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 5.04e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 4.8e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, "bedrock_mantle/us-gov-east-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "output_cost_per_token_batches": 3.9e-07, "output_cost_per_token_flex": 3.9e-07, "output_cost_per_token_priority": 1.365e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "input_cost_per_token_flex": 1.2e-07, "input_cost_per_token_priority": 4.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, "output_cost_per_token_flex": 3.6e-07, "output_cost_per_token_priority": 1.26e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 262144, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 5.04e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_native_structured_output": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { "input_cost_per_token": 7.2e-08, "input_cost_per_token_batches": 3.6e-08, "input_cost_per_token_flex": 3.6e-08, "input_cost_per_token_priority": 1.32e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, "output_cost_per_token_batches": 1.44e-07, "output_cost_per_token_flex": 1.44e-07, "output_cost_per_token_priority": 4.8e-07, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, "bedrock_mantle/us-gov-west-1/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.8e-07, "input_cost_per_token_batches": 9e-08, "input_cost_per_token_flex": 9e-08, "input_cost_per_token_priority": 3.15e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "output_cost_per_token_batches": 3.9e-07, "output_cost_per_token_flex": 3.9e-07, "output_cost_per_token_priority": 1.365e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, "gmi/MiniMaxAI/MiniMax-M2": { "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/MiniMaxAI/MiniMax-M2.5": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/MiniMaxAI/MiniMax-M2.7": { "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 2.1e-07, "litellm_provider": "gmi", "max_input_tokens": 196608, "mode": "chat", "output_cost_per_token": 8.4e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 4.8e-08, "input_cost_per_token": 2.4e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 9.6e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/MiniMaxAI/MiniMax-M3.1-Flash": { "cache_read_input_token_cost": 1.125e-08, "input_cost_per_token": 1.125e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-235B-A22B-FP8": { "input_cost_per_token": 1.7e-07, "litellm_provider": "gmi", "max_input_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.09e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8": { "cache_read_input_token_cost": 1.75e-08, "input_cost_per_token": 8.75e-08, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8": { "input_cost_per_token": 3.5e-07, "litellm_provider": "gmi", "max_input_tokens": 262141, "mode": "chat", "output_cost_per_token": 4.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-30B-A3B": { "input_cost_per_token": 8e-08, "litellm_provider": "gmi", "max_input_tokens": 40946, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-32B-FP8": { "input_cost_per_token": 1e-07, "litellm_provider": "gmi", "max_input_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "cache_read_input_token_cost": 1.8e-07, "input_cost_per_token": 9e-07, "litellm_provider": "gmi", "max_input_tokens": 262128, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-Next-80B-A3B-Instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3-Next-80B-A3B-Thinking": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.5-122B-A10B": { "input_cost_per_token": 4e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.5-27B": { "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.5-35B-A3B": { "input_cost_per_token": 2.5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.5-397B-A17B": { "input_cost_per_token": 6e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.6-35B-A3B": { "input_cost_per_token": 2.48e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.485e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.6-Plus": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.6-Plus-2026-04-02": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.7-Max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.8-27B": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 4.5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.8-Flash": { "cache_read_input_token_cost": 1.6e-08, "input_cost_per_token": 1.6e-07, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.8-Max": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/Qwen/Qwen3.8-Max-0902": { "cache_read_input_token_cost": 2.06e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.951e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/XiaomiMiMo/MiMo-V2.5": { "cache_read_input_token_cost": 2.38e-09, "input_cost_per_token": 1.19e-07, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 2.38e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/XiaomiMiMo/MiMo-V2.5-Pro": { "cache_read_input_token_cost": 2.52e-09, "input_cost_per_token": 3.045e-07, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 6.09e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/XiaomiMiMo/MiMo-V2.6-Flash": { "cache_read_input_token_cost": 2.24e-09, "input_cost_per_token": 1.12e-07, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 2.24e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/XiaomiMiMo/MiMo-V2.6-Pro": { "cache_read_input_token_cost": 2.88e-09, "input_cost_per_token": 3.48e-07, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 6.96e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-Prover-V2-671B": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.18e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.18e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-0528": { "cache_read_input_token_cost": 2.3e-07, "input_cost_per_token": 5.7e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.29e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 2.5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { "input_cost_per_token": 1.4e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { "input_cost_per_token": 2e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { "input_cost_per_token": 1e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V3.1": { "input_cost_per_token": 2.7e-07, "litellm_provider": "gmi", "max_input_tokens": 163840, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V3.1-Terminus": { "input_cost_per_token": 2.7e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V3.2-Exp": { "input_cost_per_token": 2.7e-07, "litellm_provider": "gmi", "max_input_tokens": 163840, "mode": "chat", "output_cost_per_token": 4.1e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V3.2-Speciale": { "input_cost_per_token": 2.8e-07, "litellm_provider": "gmi", "max_input_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V4-Flash": { "cache_read_input_token_cost": 1.82e-08, "input_cost_per_token": 9.1e-08, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 1.82e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 9.1e-09, "input_cost_per_token": 2.86e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 8.58e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 3.52e-08, "input_cost_per_token": 1.056e-06, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 3.168e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 3.6e-09, "input_cost_per_token": 1.8e-07, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 4.4e-07, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/deepseek-ai/deepseek-v4.1-flash-1017": { "cache_read_input_token_cost": 3.6e-09, "input_cost_per_token": 1.8e-07, "litellm_provider": "gmi", "max_input_tokens": 1048575, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/gmicloud/Ripple-65B-Preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "gmi", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.1-pro-preview": { "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.5-flash": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 9e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.6-flash": { "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.7-flash": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-3.8-flash": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-4-argon": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemini-4-carbon": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1.3e-07, "litellm_provider": "gmi", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/google/gemma-4-31b-it": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1.4e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/meta-llama/Llama-3.3-70B-Instruct": { "input_cost_per_token": 2.5e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "input_cost_per_token": 2.5e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "input_cost_per_token": 8e-08, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/Kimi-K2-Instruct-0905": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 5.7e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.29e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/Kimi-K2.5": { "input_cost_per_token": 6e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/Kimi-K2.6": { "cache_read_input_token_cost": 1.44e-07, "input_cost_per_token": 8.55e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/kimi-k2.7-code-highspeed": { "cache_read_input_token_cost": 3.8e-07, "input_cost_per_token": 1.9e-06, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/kimi-k3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/moonshotai/kimi-k3.1-pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "gmi", "max_input_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "gmi", "max_input_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/nvidia/nemotron-3-ultra-550b-a55b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 8e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "gmi", "max_input_tokens": 409600, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.4-mini": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 7.5e-07, "litellm_provider": "gmi", "max_input_tokens": 409600, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "gmi", "max_input_tokens": 409600, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.4-pro": { "input_cost_per_token": 3e-05, "litellm_provider": "gmi", "max_input_tokens": 409600, "mode": "chat", "output_cost_per_token": 0.00018, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.5": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.6-luna": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.6-sol": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-5.6-terra": { "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-6-astra": { "cache_read_input_token_cost": 1e-06, "input_cost_per_token": 1e-05, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 5e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-6-luna": { "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-6-sol": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-6.1-sol": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 1050000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-oss-120b": { "input_cost_per_token": 5e-08, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/openai/gpt-oss-20b": { "input_cost_per_token": 4e-08, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/stepfun-ai/Step-3.7-Flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, "litellm_provider": "gmi", "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/stepfun-ai/Step-5-Preview": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.7e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/tencent/HunyuanOCR": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", "max_input_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/tencent/Hy3": { "cache_read_input_token_cost": 3.5e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/tencent/hy3-preview": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 1.8e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/tencent/hy4": { "cache_read_input_token_cost": 2.1e-08, "input_cost_per_token": 4.17e-07, "litellm_provider": "gmi", "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2505e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/tencent/hy4-preview": { "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 8.34e-07, "litellm_provider": "gmi", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.501e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/x-ai/grok-4.5": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 2000000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/xai/grok4.6": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "gmi", "max_input_tokens": 2000000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/xai/grok4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gmi", "max_input_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-4.5-Air-FP8": { "input_cost_per_token": 2e-07, "litellm_provider": "gmi", "max_input_tokens": 131076, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-4.5-FP8": { "input_cost_per_token": 6e-07, "litellm_provider": "gmi", "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, "litellm_provider": "gmi", "max_input_tokens": 204800, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-4.7-Flash": { "input_cost_per_token": 7e-08, "litellm_provider": "gmi", "max_input_tokens": 202752, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-5-FP8": { "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "gmi", "max_input_tokens": 202752, "mode": "chat", "output_cost_per_token": 1.92e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-5.1-FP8": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "gmi", "max_input_tokens": 202752, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-5.2-FP8": { "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 7e-07, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "gmi/zai-org/GLM-5.3-Flash": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "gmi", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, "fireworks_ai/accounts/fireworks/models/kimi-k3p1-pro": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_priority": 3e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 1.5e-05, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "baseten/moonshotai/Kimi-K3.1-Pro": { "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "baseten", "max_input_tokens": 1000000, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://inference.baseten.co/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "gpt-image-2.6-sunburst": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_pdf_input": true, "supports_vision": true }, "gpt-image-2.6-flare": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 3e-05, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_pdf_input": true, "supports_vision": true }, "bedrock/us-gov-east-1/moonshotai.kimi-k3": { "cache_creation_input_token_cost": 4.95e-06, "cache_creation_input_token_cost_flex": 2.475e-06, "cache_creation_input_token_cost_priority": 8.6625e-06, "cache_read_input_token_cost": 3.96e-07, "cache_read_input_token_cost_flex": 1.98e-07, "cache_read_input_token_cost_priority": 6.93e-07, "input_cost_per_token": 3.96e-06, "input_cost_per_token_batches": 1.98e-06, "input_cost_per_token_flex": 1.98e-06, "input_cost_per_token_priority": 6.93e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-05, "output_cost_per_token_batches": 9.9e-06, "output_cost_per_token_flex": 9.9e-06, "output_cost_per_token_priority": 3.465e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 64.0, "token_count_tokenizer": "kimi_k3" }, "bedrock/us-gov-west-1/moonshotai.kimi-k3": { "cache_creation_input_token_cost": 4.95e-06, "cache_creation_input_token_cost_flex": 2.475e-06, "cache_creation_input_token_cost_priority": 8.6625e-06, "cache_read_input_token_cost": 3.96e-07, "cache_read_input_token_cost_flex": 1.98e-07, "cache_read_input_token_cost_priority": 6.93e-07, "input_cost_per_token": 3.96e-06, "input_cost_per_token_batches": 1.98e-06, "input_cost_per_token_flex": 1.98e-06, "input_cost_per_token_priority": 6.93e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-05, "output_cost_per_token_batches": 9.9e-06, "output_cost_per_token_flex": 9.9e-06, "output_cost_per_token_priority": 3.465e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 64.0, "token_count_tokenizer": "kimi_k3" }, "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { "deprecation_date": "2026-09-10", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 195904, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-east-1/index.json", "successor_model": "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-east-1/xai.grok-4.7": { "cache_read_input_token_cost": 6.6e-07, "cache_read_input_token_cost_flex": 3.3e-07, "cache_read_input_token_cost_priority": 1.155e-06, "input_cost_per_token": 2.64e-06, "input_cost_per_token_batches": 1.32e-06, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 7.92e-06, "output_cost_per_token_batches": 3.96e-06, "output_cost_per_token_flex": 3.96e-06, "output_cost_per_token_priority": 1.386e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "use_openai_responses_path": true }, "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { "deprecation_date": "2026-09-10", "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-3-haiku.md", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 195904, "max_output_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/us-gov-west-1/index.json", "successor_model": "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "bedrock_mantle/us-gov-west-1/xai.grok-4.7": { "cache_read_input_token_cost": 6.6e-07, "cache_read_input_token_cost_flex": 3.3e-07, "cache_read_input_token_cost_priority": 1.155e-06, "input_cost_per_token": 2.64e-06, "input_cost_per_token_batches": 1.32e-06, "input_cost_per_token_flex": 1.32e-06, "input_cost_per_token_priority": 4.62e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 7.92e-06, "output_cost_per_token_batches": 3.96e-06, "output_cost_per_token_flex": 3.96e-06, "output_cost_per_token_priority": 1.386e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-gov-west-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "use_openai_responses_path": true }, "bedrock_mantle/xai.grok-4.7": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_flex": 2.75e-07, "cache_read_input_token_cost_priority": 9.625e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "input_cost_per_token_flex": 1.1e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 524288, "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 6.6e-06, "output_cost_per_token_batches": 3.3e-06, "output_cost_per_token_flex": 3.3e-06, "output_cost_per_token_priority": 1.155e-05, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "use_openai_responses_path": true }, "bedrock_mantle/grok-latest": { "alias_of": "bedrock_mantle/xai.grok-4.7" }, "together_ai/ricursive-ai/Ripple-65B-Preview": { "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "vertex_ai/gemini-omni-1.2-flash": { "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 260640, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": false, "supports_audio_output": false, "supports_computer_use": false, "supports_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": false, "supports_tool_choice": false, "supports_url_context": false, "supports_video_input": true, "supports_vision": true, "supports_web_search": false }, "gemini/gemini-omni-1.2-flash": { "input_cost_per_image_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "input_cost_per_video_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "video", "audio" ], "supports_audio_input": false, "supports_audio_output": true, "supports_reasoning": true, "supports_system_messages": false, "supports_video_input": true, "supports_vision": true }, "databricks/databricks-kimi-k3-1-pro": { "cache_creation_input_token_cost": 1.99997e-06, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_token": 1.99997e-06, "input_dbu_cost_per_token": 2.8571e-05, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "metadata": {"notes":"Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference."}, "mode": "chat", "output_cost_per_token": 9.99999e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 100.0 }, "moonshotai.kimi-k3.1": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_flex": 2.75e-06, "cache_creation_input_token_cost_priority": 9.625e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_flex": 1.1e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 4.4e-06, "input_cost_per_token_flex": 2.2e-06, "input_cost_per_token_priority": 7.7e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_flex": 1.1e-05, "output_cost_per_token_priority": 3.85e-05, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", "supports_audio_input": false, "supports_function_calling": true, "supports_none_reasoning_effort": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "us.moonshotai.kimi-k3.1": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_flex": 2.75e-06, "cache_creation_input_token_cost_priority": 9.625e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_flex": 1.1e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 4.4e-06, "input_cost_per_token_flex": 2.2e-06, "input_cost_per_token_priority": 7.7e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_flex": 1.1e-05, "output_cost_per_token_priority": 3.85e-05, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", "supports_audio_input": false, "supports_function_calling": true, "supports_none_reasoning_effort": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "global.moonshotai.kimi-k3.1": { "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 8.75e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_flex": 1e-07, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 4e-06, "input_cost_per_token_flex": 2e-06, "input_cost_per_token_priority": 7e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_flex": 1e-05, "output_cost_per_token_priority": 3.5e-05, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", "supports_audio_input": false, "supports_function_calling": true, "supports_none_reasoning_effort": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "in.moonshotai.kimi-k3.1": { "cache_creation_input_token_cost": 5.5e-06, "cache_creation_input_token_cost_flex": 2.75e-06, "cache_creation_input_token_cost_priority": 9.625e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_flex": 1.1e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 4.4e-06, "input_cost_per_token_flex": 2.2e-06, "input_cost_per_token_priority": 7.7e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 868928, "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_flex": 1.1e-05, "output_cost_per_token_priority": 3.85e-05, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3-1-highspeed.md", "supports_audio_input": false, "supports_function_calling": true, "supports_none_reasoning_effort": true, "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_regex_lookaround": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, "wandb/deepseek-ai/DeepSeek-V4.1-Flash-1017": { "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "azure_ai/cohere-rerank-v5-pro": { "deprecation_date": "2027-02-12", "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_token": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/cohere-rerank-v5-fast": { "deprecation_date": "2027-02-12", "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_token": 2e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-realtime-2.1": { "cache_read_input_audio_token_cost": 4.4e-07, "cache_read_input_image_token_cost": 5.5e-07, "cache_read_input_token_cost": 4.4e-07, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.52e-05, "input_cost_per_image_token": 5.5e-06, "input_cost_per_token": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 7.04e-05, "output_cost_per_token": 2.64e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/us/gpt-realtime-2.1-mini": { "cache_read_input_audio_token_cost": 3.3e-07, "cache_read_input_image_token_cost": 8.8e-08, "cache_read_input_token_cost": 6.6e-08, "deprecation_date": "2027-06-25", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 1.1e-05, "input_cost_per_image_token": 8.8e-07, "input_cost_per_token": 6.6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/us/gpt-realtime-1.5": { "cache_read_input_audio_token_cost": 4.4e-07, "cache_read_input_image_token_cost": 5.5e-07, "cache_read_input_token_cost": 4.4e-07, "deprecation_date": "2027-08-24", "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "input_cost_per_audio_token": 3.52e-05, "input_cost_per_image_token": 5.5e-06, "input_cost_per_token": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 7.04e-05, "output_cost_per_token": 1.76e-05, "provider_specific_entry": { "realtime_ga_only": 1 }, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "eu.anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 1.76e-05, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 8.8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output_by_default": true, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "eu.anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 1.76e-05, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 8.8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "global.anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output_by_default": true, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "global.anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "us-gov.anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "us-gov.anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "us.anthropic.claude-fable-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 1.76e-05, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 8.8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output_by_default": true, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "us.anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.1e-05, "cache_creation_input_token_cost_above_1hr": 1.76e-05, "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 8.8e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "input_cost_per_token_batches": 4e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "output_cost_per_token_batches": 2e-05, "prompt_cache_min_tokens": 512.0, "provider_specific_entry": {"us":1.1,"fast":2}, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "supports_anthropic_compaction": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_fast_mode": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_speed": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "bedrock/claude_platform/claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_creation_input_token_cost_batches": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-06, "input_cost_per_token_batches": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "output_cost_per_token_batches": 2e-05, "prompt_cache_min_tokens": 512.0, "provider_specific_entry": {"us":1.1}, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://platform.claude.com/docs/en/about-claude/pricing#claude-platform-on-aws-pricing", "supports_adaptive_thinking": true, "supports_anthropic_compaction": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "azure_ai/claude-mythos-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "thinking_always_on": true }, "azure_ai/claude-mythos-5-2-fast": { "cache_creation_input_token_cost": 2e-05, "cache_creation_input_token_cost_above_1hr": 3.2e-05, "cache_read_input_token_cost": 4e-07, "input_cost_per_token": 1.6e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "thinking_always_on": true }, "azure_ai/claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "thinking_always_on": true }, "azure_ai/claude-fable-5-2-fast": { "cache_creation_input_token_cost": 2e-05, "cache_creation_input_token_cost_above_1hr": 3.2e-05, "cache_read_input_token_cost": 4e-07, "input_cost_per_token": 1.6e-05, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-05, "prompt_cache_min_tokens": 512.0, "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": false, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "thinking_always_on": true }, "bedrock/us-gov-east-1/anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "bedrock/us-gov-west-1/anthropic.claude-mythos-5-2": { "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, "prompt_cache_min_tokens": 512.0, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, "github_copilot/claude-fable-5.2": { "cache_creation_input_token_cost": 1e-05, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 64000, "mode": "chat", "output_cost_per_token": 4e-05, "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", "/v1/messages" ], "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "thinking_always_on": true }, "together_ai/elorian-labs/glimpse-1.0": { "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true }, "gemini/gemini-4-carbon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 4096.0, "rpm": 2000.0, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://aistudio.google.com/docs/pricing#gemini-4-carbon", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": true, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "tpm": 800000.0, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-carbon": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_priority": 1.8e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 2e-06, "input_cost_per_audio_token_batches": 1e-06, "input_cost_per_audio_token_priority": 3.6e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.8e-05, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": true, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-carbon-cyber-permissive": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, "cache_read_input_token_cost_priority": 3.6e-07, "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 4e-06, "input_cost_per_audio_token_batches": 2e-06, "input_cost_per_audio_token_priority": 7.2e-06, "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "input_cost_per_token_priority": 7.2e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_reasoning_token": 2e-05, "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, "output_cost_per_token_priority": 3.6e-05, "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_computer_use": false, "supports_continuation": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, "web_search_billing_unit": "per_query" }, "github_copilot/gemini-4-carbon": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 2e-06, "litellm_provider": "github_copilot", "max_input_tokens": 200000, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://github.blog/changelog/2026-11-09-gemini-4-carbon-in-github-copilot", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_vision": true }, "fal_ai/alibaba/happy-horse/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/happy-horse/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/happy-horse/v1.1/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.18, "output_cost_per_second_1080p": 0.18, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/happy-horse/v1.1/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.18, "output_cost_per_second_1080p": 0.18, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/happy-horse/v1.1/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.18, "output_cost_per_second_1080p": 0.18, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/v1.1/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0-prime/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_480p": 0.068, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/wan-3.0-prime/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0-prime/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_480p": 0.068, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0-prime/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_480p": 0.068, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/wan-3.0-prime/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2, "output_cost_per_second_1080p": 0.2, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/alibaba/wan-3.0/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2, "output_cost_per_second_1080p": 0.2, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/alibaba/wan-3.0/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/wan-3.0/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2, "output_cost_per_second_1080p": 0.2, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/alibaba/wan-3.0/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/draft-enhance": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.29, "output_cost_per_second_1080p": 0.29, "source": "https://fal.ai/models/blackforestlabs/flux-3/draft-enhance", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/edit-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_720p": 0.03, "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/extend-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.41, "output_cost_per_second_1080p": 0.53, "output_cost_per_second_720p": 0.41, "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/extend-video/draft": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.12, "output_cost_per_second_720p": 0.12, "source": "https://fal.ai/models/blackforestlabs/flux-3/extend-video/draft", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_720p": 0.17, "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/first-last-frame-to-video/draft": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/blackforestlabs/flux-3/first-last-frame-to-video/draft", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/image-to-video/draft": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video/draft", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/keyframes-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_720p": 0.17, "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/keyframes-to-video/draft": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/blackforestlabs/flux-3/keyframes-to-video/draft", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/klein/base/edit-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/edit-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/edit-image/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/blackforestlabs/flux-3/klein/base/text-to-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/base/text-to-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/base/text-to-image/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/blackforestlabs/flux-3/klein/edit-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/edit-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.012, "output_cost_per_pixel": 1.1444091796875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/blackforestlabs/flux-3/klein/text-to-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills blackforestlabs/flux-3/klein/text-to-image/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.012, "output_cost_per_pixel": 1.1444091796875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/blackforestlabs/flux-3/text-to-video/draft": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video/draft", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/bria_video_eraser/erase/keypoints": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/bria_video_eraser/erase/keypoints", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/bria_video_eraser/erase/mask": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/bria_video_eraser/erase/mask", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/bria_video_eraser/erase/prompt": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/bria_video_eraser/erase/prompt", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/embed-product": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/embed-product", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/extract-object": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://fal.ai/models/bria/extract-object", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-2/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-bbq-preview/generate": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-bbq-preview/generate", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bria/fibo-edit-1.5/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit-1.5/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit-1.5/expand": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit-1.5/expand", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit-1.5/product-holding": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit-1.5/product-holding", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit-1.5/virtual-try-on": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit-1.5/virtual-try-on", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/add_object_by_text": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/add_object_by_text", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/blend": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/blend", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/colorize": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/colorize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/erase_by_text": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/erase_by_text", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/relight": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/relight", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/replace_object_by_text": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/replace_object_by_text", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/reseason": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/reseason", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/restore": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/restore", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/restyle": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/restyle", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/rewrite_text": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/rewrite_text", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-edit/sketch_to_colored_image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-edit/sketch_to_colored_image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/fibo-gen-1.5/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-gen-1.5/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bria/fibo-lite/generate": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.036, "source": "https://fal.ai/models/bria/fibo-lite/generate", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bria/fibo/generate": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo/generate", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bria/genfill/v2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills bria/genfill/v2 at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, "output_cost_per_pixel": 3.814697265625e-08, "source": "https://fal.ai/models/bria/genfill/v2", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/guided-remove-background": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/bria/guided-remove-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/increase-resolution": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/increase-resolution", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/product-dimensions": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/product-dimensions", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/replace-background": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/replace-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/upscale/creative": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/upscale/creative", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bria/video/background-removal": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/video/background-removal", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/background-removal/green-screen-despill": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/bria/video/background-removal/green-screen-despill", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/background-removal/realtime": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0042, "source": "https://fal.ai/models/bria/video/background-removal/realtime", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/background-removal/v3": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/bria/video/background-removal/v3", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/erase/keypoints": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/video/erase/keypoints", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/erase/mask": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/video/erase/mask", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/erase/prompt": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/video/erase/prompt", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/video/increase-resolution": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/bria/video/increase-resolution", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/omnihuman/v2": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.105, "source": "https://fal.ai/models/bytedance/omnihuman/v2", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/fast/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2419, "output_cost_per_second_720p": 0.2419, "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/fast/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2419, "output_cost_per_second_720p": 0.2419, "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/mini/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.1547, "output_cost_per_second_480p": 0.0721, "output_cost_per_second_720p": 0.1547, "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/mini/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate"}, "mode": "video_generation", "output_cost_per_second": 0.007, "output_cost_per_second_480p": 0.007, "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/mini/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.1547, "output_cost_per_second_480p": 0.0721, "output_cost_per_second_720p": 0.1547, "source": "https://fal.ai/models/bytedance/seedance-2.0/mini/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/us/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.3034, "output_cost_per_second_1080p": 0.682, "output_cost_per_second_720p": 0.3034, "source": "https://fal.ai/models/bytedance/seedance-2.0/us/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/us/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.37, "output_cost_per_second_480p": 0.1731, "output_cost_per_second_720p": 0.37, "source": "https://fal.ai/models/bytedance/seedance-2.0/us/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.5/us/draft/complete": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 1.164, "source": "https://fal.ai/models/bytedance/seedance-2.5/us/draft/complete", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.5/us/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_1080p": 1.164, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/us/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.5/us/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_1080p": 1.164, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/us/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedream/v5/flash/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.027, "source": "https://fal.ai/models/bytedance/seedream/v5/flash/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bytedance/seedream/v5/flash/layerize": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.027, "source": "https://fal.ai/models/bytedance/seedream/v5/flash/layerize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bytedance/seedream/v5/flash/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.027, "source": "https://fal.ai/models/bytedance/seedream/v5/flash/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bytedance/seedream/v5/lite/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/bytedance/seedream/v5/lite/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bytedance/seedream/v5/lite/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/bytedance/seedream/v5/lite/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/clarityai/crystal-upscaler": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills clarityai/crystal-upscaler at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.016, "output_cost_per_pixel": 1.52587890625e-08, "source": "https://fal.ai/models/clarityai/crystal-upscaler", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/decart/lucy-2-5/realtime": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/decart/lucy-2-5/realtime", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/decart/lucy-2-6/realtime": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/decart/lucy-2-6/realtime", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/decart/lucy-restyle": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/decart/lucy-restyle", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/decart/lucy2-vton/realtime": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/decart/lucy2-vton/realtime", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ai-avatar/multi": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/ai-avatar/multi", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ai-avatar/multi-text": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/ai-avatar/multi-text", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ai-avatar/single-text": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/ai-avatar/single-text", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/bagel": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/bagel", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bagel/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/bagel/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ben/v2/image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ben/v2/image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/ben/v2/image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/boogu-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/boogu-image at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, "output_cost_per_pixel": 3.814697265625e-08, "source": "https://fal.ai/models/fal-ai/boogu-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/boogu-image/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/boogu-image/edit at $0.04 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.04, "output_cost_per_pixel": 3.814697265625e-08, "source": "https://fal.ai/models/fal-ai/boogu-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/background/replace": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/background/replace", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/eraser": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/eraser", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/expand": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/expand", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/genfill": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/genfill", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/product-shot": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/product-shot", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/reimagine": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/reimagine", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bria/text-to-image/base": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/text-to-image/base", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bria/text-to-image/fast": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/bria/text-to-image/fast", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bria/text-to-image/hd": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bria/text-to-image/hd", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bytedance/dreamactor/v2": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/bytedance/dreamactor/v2", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/bytedance/omnihuman": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/bytedance/omnihuman/v1.5": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.16, "source": "https://fal.ai/models/fal-ai/bytedance/omnihuman/v1.5", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/bytedance/seedream/v4.5/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bytedance/seedream/v4.5/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/bytedance/seedream/v4/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bytedance/seedream/v4/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/bytedance/seedream/v4/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/clarity-upscaler": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/clarity-upscaler at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/clarity-upscaler", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/codeformer": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/codeformer at $0.0021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0021, "output_cost_per_pixel": 2.002716064453125e-09, "source": "https://fal.ai/models/fal-ai/codeformer", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/control-light": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/control-light at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/control-light", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/davinci-magihuman": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/davinci-magihuman", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ddcolor": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ddcolor at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.001, "output_cost_per_pixel": 9.5367431640625e-10, "source": "https://fal.ai/models/fal-ai/ddcolor", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/depth-anything-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://fal.ai/models/fal-ai/depth-anything-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/echomimic-v3": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/echomimic-v3", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ernie-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ernie-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/ernie-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ernie-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ernie-image/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/ernie-image/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ernie-image/lora/turbo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ernie-image/lora/turbo at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.015, "output_cost_per_pixel": 1.430511474609375e-08, "source": "https://fal.ai/models/fal-ai/ernie-image/lora/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ernie-image/turbo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/ernie-image/turbo at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/ernie-image/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/fashn/tryon/v1.5": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.5", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/fashn/tryon/v1.6": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://fal.ai/models/fal-ai/fashn/tryon/v1.6", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/feynobg": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/feynobg", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ffmpeg-api/compose": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0002, "source": "https://fal.ai/models/fal-ai/ffmpeg-api/compose", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ffmpeg-api/merge-audio-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0002, "source": "https://fal.ai/models/fal-ai/ffmpeg-api/merge-audio-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/finegrain-eraser": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.27, "source": "https://fal.ai/models/fal-ai/finegrain-eraser", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/finegrain-eraser/bbox": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.18, "source": "https://fal.ai/models/fal-ai/finegrain-eraser/bbox", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/finegrain-eraser/mask": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.13, "source": "https://fal.ai/models/fal-ai/finegrain-eraser/mask", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/firered-image-edit-v1.1": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/firered-image-edit-v1.1 at $0.0325 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0325, "output_cost_per_pixel": 3.0994415283203126e-08, "source": "https://fal.ai/models/fal-ai/firered-image-edit-v1.1", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flashhead": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.005, "source": "https://fal.ai/models/fal-ai/flashhead", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/flux-1/dev": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/dev", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-1/dev/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/dev/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/dev/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-1/dev/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/dev/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-1/krea": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/krea", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-1/krea/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/krea/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-1/krea/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/krea/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-1/schnell": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/schnell at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.003, "output_cost_per_pixel": 2.86102294921875e-09, "source": "https://fal.ai/models/fal-ai/flux-1/schnell", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-1/schnell/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/schnell/redux at $0.003 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.003, "output_cost_per_pixel": 2.86102294921875e-09, "source": "https://fal.ai/models/fal-ai/flux-1/schnell/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-1/srpo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/srpo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-1/srpo/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-1/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-1/srpo/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2 at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.012, "output_cost_per_pixel": 1.1444091796875e-08, "source": "https://fal.ai/models/fal-ai/flux-2", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-flex": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-flex at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-flex", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-flex/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-flex/edit at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-flex/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-lora-gallery/add-background": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/add-background at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/add-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-lora-gallery/apartment-staging": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/apartment-staging at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/apartment-staging", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/ballpoint-pen-sketch", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/digital-comic-art": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/digital-comic-art at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/digital-comic-art", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/face-to-full-portrait": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/face-to-full-portrait at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/face-to-full-portrait", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-lora-gallery/hdr-style": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/hdr-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/hdr-style", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/multiple-angles": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/multiple-angles at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/multiple-angles", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-lora-gallery/realism": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/realism at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/realism", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/satellite-view-style": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/satellite-view-style at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/satellite-view-style", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/sepia-vintage": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/sepia-vintage at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/sepia-vintage", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-lora-gallery/virtual-tryon": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2-lora-gallery/virtual-tryon at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2-lora-gallery/virtual-tryon", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/edit at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.012, "output_cost_per_pixel": 1.1444091796875e-08, "source": "https://fal.ai/models/fal-ai/flux-2/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/flash": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/flash at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/flux-2/flash", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/flash/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/flash/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/flux-2/flash/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/4b": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/4b/base": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.009, "output_cost_per_pixel": 8.58306884765625e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/4b/base/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit at $0.009 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.009, "output_cost_per_pixel": 8.58306884765625e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/4b/base/edit/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/edit/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.016, "output_cost_per_pixel": 1.52587890625e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/4b/base/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/base/lora at $0.016 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.016, "output_cost_per_pixel": 1.52587890625e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/base/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/4b/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/4b/edit/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/edit/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/edit/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/4b/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/4b/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/4b/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/9b": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.006, "output_cost_per_pixel": 5.7220458984375e-09, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/9b/base": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.011, "output_cost_per_pixel": 1.049041748046875e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/9b/base/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.011, "output_cost_per_pixel": 1.049041748046875e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/9b/base/edit/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/edit/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/edit/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/9b/base/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/base/lora at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/base/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/klein/9b/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit at $0.011 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.011, "output_cost_per_pixel": 1.049041748046875e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/9b/edit/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/edit/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.015, "output_cost_per_pixel": 1.430511474609375e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/edit/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/klein/9b/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/klein/9b/lora at $0.015 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.015, "output_cost_per_pixel": 1.430511474609375e-08, "source": "https://fal.ai/models/fal-ai/flux-2/klein/9b/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/lora at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/lora/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/lora/edit at $0.021 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.021, "output_cost_per_pixel": 2.002716064453125e-08, "source": "https://fal.ai/models/fal-ai/flux-2/lora/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2/turbo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.008, "output_cost_per_pixel": 7.62939453125e-09, "source": "https://fal.ai/models/fal-ai/flux-2/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2/turbo/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-2/turbo/edit at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries (input megapixels are billed too and are not modeled)"}, "mode": "image_generation", "output_cost_per_image": 0.008, "output_cost_per_pixel": 7.62939453125e-09, "source": "https://fal.ai/models/fal-ai/flux-2/turbo/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-general": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-general at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.075, "output_cost_per_pixel": 7.152557373046875e-08, "source": "https://fal.ai/models/fal-ai/flux-general", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-general/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-general/image-to-image at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.075, "output_cost_per_pixel": 7.152557373046875e-08, "source": "https://fal.ai/models/fal-ai/flux-general/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-general/inpainting": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-general/inpainting at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.075, "output_cost_per_pixel": 7.152557373046875e-08, "source": "https://fal.ai/models/fal-ai/flux-general/inpainting", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-kontext-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-kontext-lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-kontext-lora/inpaint": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/inpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/inpaint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-kontext-lora/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-kontext-lora/text-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-kontext-lora/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-kontext/dev": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-kontext/dev at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux-kontext/dev", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-krea-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-krea-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-krea-lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-krea-lora/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-krea-lora/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-krea-lora/inpainting": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-krea-lora/inpainting", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-krea-lora/stream": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-krea-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-krea-lora/stream", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-lora-canny": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora-canny at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora-canny", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-lora-fill": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora-fill at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora-fill", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-lora/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-lora/inpainting": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora/inpainting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora/inpainting", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-lora/stream": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-lora/stream at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/flux-lora/stream", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/kontext": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/kontext/max": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/kontext/max/multi": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/multi", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/kontext/max/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/max/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/kontext/multi": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/multi", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/kontext/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/flux-pro/kontext/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/v1.1-ultra-finetuned": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.07, "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra-finetuned", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-pro/v1.1-ultra/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1-ultra/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1-ultra/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/v1.1/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pro/v1.1/redux at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/flux-pro/v1.1/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/v1/fill": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/v1/fill-finetuned": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pro/v1/fill-finetuned at $0.06 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.06, "output_cost_per_pixel": 5.7220458984375e-08, "source": "https://fal.ai/models/fal-ai/flux-pro/v1/fill-finetuned", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pulid": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-pulid at $0.0333 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0333, "output_cost_per_pixel": 3.175735473632813e-08, "source": "https://fal.ai/models/fal-ai/flux-pulid", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-vision-upscaler": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux-vision-upscaler at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/flux-vision-upscaler", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/dev/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/dev/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/flux/dev/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/dev/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/dev/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/dev/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/krea": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/krea at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/krea", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux/krea/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/krea/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/krea/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/krea/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/krea/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/krea/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/schnell/redux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/schnell/redux at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/schnell/redux", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux/srpo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/srpo at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/srpo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux/srpo/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/flux/srpo/image-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/flux/srpo/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/framepack": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0333, "source": "https://fal.ai/models/fal-ai/framepack", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/framepack/f1": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0333, "source": "https://fal.ai/models/fal-ai/framepack/f1", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/framepack/flf2v": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0333, "source": "https://fal.ai/models/fal-ai/framepack/flf2v", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/gemini-25-flash-image/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "source": "https://fal.ai/models/fal-ai/gemini-25-flash-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/gemini-3-pro-image-preview": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/gemini-3-pro-image-preview/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/gemini-3-pro-image-preview/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/gemini-3.1-flash-image-preview": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/gemini-3.1-flash-image-preview/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/gemini-3.1-flash-image-preview/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/glm-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/glm-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/glm-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/glm-image/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/glm-image/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/glm-image/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/heygen/avatar3/digital-twin": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.034, "source": "https://fal.ai/models/fal-ai/heygen/avatar3/digital-twin", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/avatar4/digital-twin": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/heygen/avatar4/digital-twin", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/avatar4/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/heygen/avatar4/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/avatar5/digital-twin": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/heygen/avatar5/digital-twin", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v2/translate/precision": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/precision", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v2/translate/speed": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/heygen/v2/translate/speed", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v2/video-agent": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.034, "source": "https://fal.ai/models/fal-ai/heygen/v2/video-agent", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v3/filler-word-removal": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/fal-ai/heygen/v3/filler-word-removal", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v3/lipsync/precision": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/precision", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v3/lipsync/speed": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/heygen/v3/lipsync/speed", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/heygen/v3/video-agent": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.034, "source": "https://fal.ai/models/fal-ai/heygen/v3/video-agent", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/hidream-i1-fast": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-i1-fast at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/hidream-i1-fast", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hidream-i1-full": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-i1-full at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/hidream-i1-full", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hidream-i1-full/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-i1-full/image-to-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/hidream-i1-full/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/hidream-o1-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-o1-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/hidream-o1-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hidream-o1-image/dev": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hidream-o1-image/dev/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/dev/edit at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/hidream-o1-image/dev/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/hidream-o1-image/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hidream-o1-image/edit at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/hidream-o1-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/hunyuan_world": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/hunyuan_world", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/hunyuan-image/v2.1/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v2.1/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/hunyuan-image/v2.1/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hunyuan-image/v3/instruct/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/edit at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.09, "output_cost_per_pixel": 8.58306884765625e-08, "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/hunyuan-image/v3/instruct/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/instruct/text-to-image at $0.09 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.09, "output_cost_per_pixel": 8.58306884765625e-08, "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/instruct/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hunyuan-image/v3/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/hunyuan-image/v3/text-to-image at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/hunyuan-image/v3/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/hunyuan-video-v1.5/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.075, "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/hunyuan-video-v1.5/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.075, "source": "https://fal.ai/models/fal-ai/hunyuan-video-v1.5/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/iclight-v2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/iclight-v2 at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/iclight-v2", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/id-v2v": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/id-v2v", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/id-v2v/relight": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/id-v2v/relight", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ideogram/character": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/ideogram/character", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/character/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/ideogram/character/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/character/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/ideogram/character/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/object-removal": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/ideogram/object-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/remove-background": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/fal-ai/ideogram/remove-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/upscale": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/upscale", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/ideogram/v2", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ideogram/v2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/ideogram/v2/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/ideogram/v2/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2/turbo": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ideogram/v2/turbo/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2/turbo/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/ideogram/v2/turbo/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2a": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/ideogram/v2a", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ideogram/v2a/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/ideogram/v2a/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v2a/turbo": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ideogram/v2a/turbo/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://fal.ai/models/fal-ai/ideogram/v2a/turbo/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v3/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v3/generate-transparent": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3/generate-transparent", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/ideogram/v3/layerize-text": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.09, "source": "https://fal.ai/models/fal-ai/ideogram/v3/layerize-text", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v3/reframe": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3/reframe", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v3/remix": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3/remix", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/ideogram/v3/replace-background": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/ideogram/v3/replace-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/age-modify": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/age-modify", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/city-teleport": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/city-teleport", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/expression-change": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/expression-change", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/hair-change": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/hair-change", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/headshot-photo": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/headshot-photo", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/makeup-application": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/makeup-application", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/object-removal": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/object-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/outpaint": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/image-apps-v2/outpaint at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/image-apps-v2/outpaint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/perspective": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/perspective", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/photo-restoration": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/photo-restoration", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/photography-effects": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.4, "source": "https://fal.ai/models/fal-ai/image-apps-v2/photography-effects", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/portrait-enhance": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.4, "source": "https://fal.ai/models/fal-ai/image-apps-v2/portrait-enhance", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/product-holding": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-holding", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/product-photography": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/product-photography", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/relighting": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/relighting", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/style-transfer": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/style-transfer", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/texture-transform": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/texture-transform", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-apps-v2/virtual-try-on": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-apps-v2/virtual-try-on", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/age-progression": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/age-progression", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/baby-version": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/baby-version", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/background-change": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/background-change", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/broccoli-haircut": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/broccoli-haircut", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/cartoonify": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/cartoonify", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/color-correction": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/color-correction", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/expression-change": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/expression-change", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/face-enhancement": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/face-enhancement", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/hair-change": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/hair-change", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/object-removal": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/object-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/photo-restoration": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/photo-restoration", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/plushie-style": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/plushie-style", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/professional-photo": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/professional-photo", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/realism": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/realism", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/reframe": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/reframe", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/retouch": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/retouch", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/scene-composition": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/scene-composition", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/style-transfer": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/style-transfer", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/text-removal": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/text-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/time-of-day": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/time-of-day", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/weather-effect": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/weather-effect", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/wojak-style": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/wojak-style", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image-editing/youtube-thumbnails": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/image-editing/youtube-thumbnails", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/image2svg": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://fal.ai/models/fal-ai/image2svg", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/instant-character": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/instant-character at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/instant-character", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/kling-image/o1": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/kling-image/o1", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/kling-image/o3/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/kling-image/o3/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/kling-image/o3/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/kling-image/o3/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/kling-image/v3/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/kling-image/v3/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/kling-image/v3/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.028, "source": "https://fal.ai/models/fal-ai/kling-image/v3/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/kling-video/ai-avatar/v2/pro": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.115, "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/pro", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/ai-avatar/v2/standard": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0562, "source": "https://fal.ai/models/fal-ai/kling-video/ai-avatar/v2/standard", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.112, "source": "https://fal.ai/models/fal-ai/kling-video/o1/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.112, "source": "https://fal.ai/models/fal-ai/kling-video/o1/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/standard/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.084, "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/standard/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.084, "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/edit": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.126, "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/standard/video-to-video/reference": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.126, "source": "https://fal.ai/models/fal-ai/kling-video/o1/standard/video-to-video/reference", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/video-to-video/edit": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.168, "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o1/video-to-video/reference": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.168, "source": "https://fal.ai/models/fal-ai/kling-video/o1/video-to-video/reference", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/4k/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/4k/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/4k/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/edit": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/4k/video-to-video/reference": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/reference", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/edit": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.168, "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/pro/video-to-video/reference": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.168, "source": "https://fal.ai/models/fal-ai/kling-video/o3/pro/video-to-video/reference", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/edit": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.126, "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/o3/standard/video-to-video/reference": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.126, "source": "https://fal.ai/models/fal-ai/kling-video/o3/standard/video-to-video/reference", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1.5/pro/effects": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/kling-video/v1.5/pro/effects", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1.6/pro/effects": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.098, "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/pro/effects", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1.6/standard/effects": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.056, "source": "https://fal.ai/models/fal-ai/kling-video/v1.6/standard/effects", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1/pro/ai-avatar": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.115, "source": "https://fal.ai/models/fal-ai/kling-video/v1/pro/ai-avatar", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1/standard/ai-avatar": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.0562, "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/ai-avatar", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v1/standard/effects": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.045, "source": "https://fal.ai/models/fal-ai/kling-video/v1/standard/effects", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v2.6/pro/motion-control": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.112, "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/motion-control", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v2.6/standard/motion-control": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.07, "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/standard/motion-control", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/4k/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/4k/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.42, "source": "https://fal.ai/models/fal-ai/kling-video/v3/4k/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/pro/motion-control": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.168, "source": "https://fal.ai/models/fal-ai/kling-video/v3/pro/motion-control", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/standard/motion-control": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.126, "source": "https://fal.ai/models/fal-ai/kling-video/v3/standard/motion-control", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/turbo/pro/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/turbo/pro/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/turbo/standard/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.112, "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v3/turbo/standard/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.112, "source": "https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/krea-2/turbo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/krea-2/turbo at $0.008 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.008, "output_cost_per_pixel": 7.62939453125e-09, "source": "https://fal.ai/models/fal-ai/krea-2/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/krea-2/turbo/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/krea-2/turbo/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/krea-2/turbo/style": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/krea-2/turbo/style at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/krea-2/turbo/style", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/krea-wan-14b/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.025, "source": "https://fal.ai/models/fal-ai/krea-wan-14b/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/krea-wan-14b/video-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.025, "source": "https://fal.ai/models/fal-ai/krea-wan-14b/video-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/latentsync": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.005, "source": "https://fal.ai/models/fal-ai/latentsync", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/leffa/pose-transfer": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/leffa/pose-transfer", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/leffa/virtual-tryon": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/leffa/virtual-tryon", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/lightx/recamera": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/lightx/recamera", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/lightx/relight": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/lightx/relight", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/longcat-image at $0.13 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.13, "output_cost_per_pixel": 1.239776611328125e-07, "source": "https://fal.ai/models/fal-ai/longcat-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/longcat-image/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/longcat-image/edit at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.15, "output_cost_per_pixel": 1.430511474609375e-07, "source": "https://fal.ai/models/fal-ai/longcat-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/longcat-video/distilled/image-to-video/480p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.005, "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/480p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/distilled/image-to-video/720p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/image-to-video/720p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/distilled/text-to-video/480p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.005, "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/480p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/distilled/text-to-video/720p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/fal-ai/longcat-video/distilled/text-to-video/720p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/image-to-video/480p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.025, "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/480p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/image-to-video/720p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://fal.ai/models/fal-ai/longcat-video/image-to-video/720p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/text-to-video/480p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.025, "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/480p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/longcat-video/text-to-video/720p": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://fal.ai/models/fal-ai/longcat-video/text-to-video/720p", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/audio-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/ltx-2.3/audio-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/extend-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/ltx-2.3/extend-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.08, "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/image-to-video/fast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "source": "https://fal.ai/models/fal-ai/ltx-2.3/image-to-video/fast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/reframe": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.2, "output_cost_per_second_1080p": 0.2, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/ltx-2.3/reframe", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/retake-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/ltx-2.3/retake-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.16, 2160p $0.32"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.08, "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltx-2.3/text-to-video/fast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.12, 2160p $0.24"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "source": "https://fal.ai/models/fal-ai/ltx-2.3/text-to-video/fast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltxv-13b-098-distilled": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltxv-13b-098-distilled/extend": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/extend", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltxv-13b-098-distilled/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/ltxv-13b-098-distilled/multiconditioning": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://fal.ai/models/fal-ai/ltxv-13b-098-distilled/multiconditioning", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/lumina-image/v2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/lumina-image/v2 at $0.075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.075, "output_cost_per_pixel": 7.152557373046875e-08, "source": "https://fal.ai/models/fal-ai/lumina-image/v2", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/marigold-v2": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/marigold-v2", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/minimax/hailuo-02-fast/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 512p rate; tiers without a catalog field: 512p $0.017"}, "mode": "video_generation", "output_cost_per_second": 0.017, "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02-fast/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/hailuo-02/pro/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/hailuo-02/pro/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/pro/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/hailuo-02/standard/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.045, "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/image-01/subject-reference": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/fal-ai/minimax/image-01/subject-reference", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/mmaudio-v2": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.001, "source": "https://fal.ai/models/fal-ai/mmaudio-v2", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/moss-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/moss-image at $0.05 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_pixel": 4.76837158203125e-08, "source": "https://fal.ai/models/fal-ai/moss-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/nafnet/deblur": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/nafnet/deblur at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0225, "output_cost_per_pixel": 2.1457672119140624e-08, "source": "https://fal.ai/models/fal-ai/nafnet/deblur", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/nafnet/denoise": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/nafnet/denoise at $0.0225 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0225, "output_cost_per_pixel": 2.1457672119140624e-08, "source": "https://fal.ai/models/fal-ai/nafnet/denoise", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/nano-banana-2/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/nano-banana-2/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/nano-banana-pro/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://fal.ai/models/fal-ai/nano-banana-pro/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/nano-banana/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.0398, "source": "https://fal.ai/models/fal-ai/nano-banana/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/nucleus-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/nucleus-image at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/nucleus-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/omnigen-v2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/omnigen-v2 at $0.15 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.15, "output_cost_per_pixel": 1.430511474609375e-07, "source": "https://fal.ai/models/fal-ai/omnigen-v2", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/one-to-all-animation/1.3b": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.045"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_480p": 0.03, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/fal-ai/one-to-all-animation/1.3b", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/one-to-all-animation/14b": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.09"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_480p": 0.06, "output_cost_per_second_720p": 0.12, "source": "https://fal.ai/models/fal-ai/one-to-all-animation/14b", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/patina": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/patina at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/patina", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/phota/enhance": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.13, "source": "https://fal.ai/models/fal-ai/phota/enhance", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/blur": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/blur", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/chromatic-aberration": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/chromatic-aberration", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/color-correction": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/color-correction", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/color-tint": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/color-tint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/desaturate": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/desaturate", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/dissolve": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/dissolve", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/dodge-burn": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/dodge-burn", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/grain": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/grain", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/parabolize": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/parabolize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/sharpen": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/sharpen", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/solarize": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/solarize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/post-processing/vignette": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://fal.ai/models/fal-ai/post-processing/vignette", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/qwen-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/qwen-image-2512": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-2512 at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-2512", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/qwen-image-2512/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-2512/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-2512/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/qwen-image-edit-2509": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/add-background": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/add-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/face-to-full-portrait", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/group-photo", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/integrate-product", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/multiple-angles", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/next-scene", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-element", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/remove-lighting", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/shirt-design", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2511": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511 at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2511-multiple-angles": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511-multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511-multiple-angles", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-2511/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-2511/lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-2511/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/add-background": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/add-background at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/add-background", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/face-to-full-portrait", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/group-photo at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/group-photo", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/integrate-product", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/multiple-angles", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/next-scene at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/next-scene", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-element at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-element", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/remove-lighting", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit-plus-lora-gallery/shirt-design", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/image-to-image at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-edit/inpaint": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image-edit/inpaint at $0.03 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.03, "output_cost_per_pixel": 2.86102294921875e-08, "source": "https://fal.ai/models/fal-ai/qwen-image-edit/inpaint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-layered": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/qwen-image-layered", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image-layered/lora": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/fal-ai/qwen-image-layered/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/qwen-image/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/qwen-image/image-to-image at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/qwen-image/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/recraft/upscale/creative": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://fal.ai/models/fal-ai/recraft/upscale/creative", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/recraft/upscale/crisp": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.004, "source": "https://fal.ai/models/fal-ai/recraft/upscale/crisp", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/recraft/v4.1/pro/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4.1/pro/text-to-vector": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/pro/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4.1/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4.1/text-to-vector": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4.1/utility/pro/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.21, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/pro/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4.1/utility/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/fal-ai/recraft/v4.1/utility/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4/pro/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4/pro/text-to-vector": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://fal.ai/models/fal-ai/recraft/v4/pro/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/v4/text-to-vector": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/recraft/v4/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/recraft/vectorize": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/fal-ai/recraft/vectorize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/sana": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/sana at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.001, "output_cost_per_pixel": 9.5367431640625e-10, "source": "https://fal.ai/models/fal-ai/sana", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/sana/sprint": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/sana/sprint at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0025, "output_cost_per_pixel": 2.384185791015625e-09, "source": "https://fal.ai/models/fal-ai/sana/sprint", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/sana/v1.5/1.6b": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/sana/v1.5/1.6b at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0075, "output_cost_per_pixel": 7.152557373046875e-09, "source": "https://fal.ai/models/fal-ai/sana/v1.5/1.6b", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/sana/v1.5/4.8b": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/sana/v1.5/4.8b at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/sana/v1.5/4.8b", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/seedvr/upscale/image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image at $0.001 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.001, "output_cost_per_pixel": 9.5367431640625e-10, "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/seedvr/upscale/image/seamless": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/seedvr/upscale/image/seamless at $0.0025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0025, "output_cost_per_pixel": 2.384185791015625e-09, "source": "https://fal.ai/models/fal-ai/seedvr/upscale/image/seamless", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/stable-diffusion-v3-medium": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/fal-ai/stable-diffusion-v3-medium", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/stable-diffusion-v35-large": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/stable-diffusion-v35-large at $0.065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.065, "output_cost_per_pixel": 6.198883056640625e-08, "source": "https://fal.ai/models/fal-ai/stable-diffusion-v35-large", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/stepx-edit2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/stepx-edit2 at $0.2 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.2, "output_cost_per_pixel": 1.9073486328125e-07, "source": "https://fal.ai/models/fal-ai/stepx-edit2", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/telestyle-v2": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/telestyle-v2 at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/fal-ai/telestyle-v2", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/uso": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/uso at $0.1 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.1, "output_cost_per_pixel": 9.5367431640625e-08, "source": "https://fal.ai/models/fal-ai/uso", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/vidu/q2/reference-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/vidu/q2/reference-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/vidu/q2/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/vidu/q2/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/vidu/reference-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/fal-ai/vidu/reference-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/wan-22-vace-fun-a14b/depth": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/depth", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-22-vace-fun-a14b/inpainting": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/inpainting", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-22-vace-fun-a14b/outpainting": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/outpainting", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-22-vace-fun-a14b/reframe": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-22-vace-fun-a14b/reframe", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-25-preview/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/wan-25-preview/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-25-preview/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-25-preview/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan-25-preview/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-25-preview/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b/depth": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b/depth", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b/inpainting": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b/inpainting", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b/outpainting": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b/outpainting", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b/pose": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b/pose", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-14b/reframe": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan-vace-14b/reframe", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-apps/video-edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p); tiers without a catalog field: 580p $0.075"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan-vace-apps/video-edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-14b/speech-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; tiers without a catalog field: 580p $0.15"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_480p": 0.1, "output_cost_per_second_720p": 0.2, "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/speech-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-5b/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.016, "source": "https://fal.ai/models/fal-ai/wan/v2.2-5b/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/image-to-video/lora": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video/lora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/text-to-image/lora": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-image/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/text-to-video/lora": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/text-to-video/lora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-a14b/video-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 580p $0.06"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan/v2.2-a14b/video-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.7/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/wan/v2.7/edit-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.7/edit-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.7/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.7/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.7/pro/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/wan/v2.7/pro/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://fal.ai/models/fal-ai/wan/v2.7/pro/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan/v2.7/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.7/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.7/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/wan/v2.7/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/fal-ai/wan/v2.7/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/z-image/base": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/base at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/z-image/base", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/z-image/base/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/base/lora at $0.012 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.012, "output_cost_per_pixel": 1.1444091796875e-08, "source": "https://fal.ai/models/fal-ai/z-image/base/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/z-image/turbo": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/z-image/turbo/controlnet": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet at $0.0065 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0065, "output_cost_per_pixel": 6.198883056640625e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/controlnet/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/controlnet/lora at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/controlnet/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image at $0.005 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.005, "output_cost_per_pixel": 4.76837158203125e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/image-to-image/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/image-to-image/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0085, "output_cost_per_pixel": 8.106231689453126e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/image-to-image/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/inpaint": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint at $0.01 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.01, "output_cost_per_pixel": 9.5367431640625e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/inpaint/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/inpaint/lora at $0.0115 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0115, "output_cost_per_pixel": 1.0967254638671875e-08, "source": "https://fal.ai/models/fal-ai/z-image/turbo/inpaint/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/z-image/turbo/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/lora at $0.0085 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0085, "output_cost_per_pixel": 8.106231689453126e-09, "source": "https://fal.ai/models/fal-ai/z-image/turbo/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/z-image/turbo/tiling": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling at $0.02 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_pixel": 1.9073486328125e-08, "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/z-image/turbo/tiling/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills fal-ai/z-image/turbo/tiling/lora at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/fal-ai/z-image/turbo/tiling/lora", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/google/gemini-omni-flash/v1.1/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.1/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.1/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.1/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 360p $0.03"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.1/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/flash/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.094, "output_cost_per_second_720p": 0.094, "source": "https://fal.ai/models/kling/v4/flash/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/flash/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.094, "output_cost_per_second_720p": 0.094, "source": "https://fal.ai/models/kling/v4/flash/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/flash/video-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.063, "output_cost_per_second_720p": 0.063, "source": "https://fal.ai/models/kling/v4/flash/video-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.235, "output_cost_per_second_1080p": 0.235, "output_cost_per_second_720p": 0.157, "source": "https://fal.ai/models/kling/v4/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.235, "output_cost_per_second_1080p": 0.235, "output_cost_per_second_720p": 0.157, "source": "https://fal.ai/models/kling/v4/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/video-to-video/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.141, "output_cost_per_second_1080p": 0.141, "output_cost_per_second_720p": 0.094, "source": "https://fal.ai/models/kling/v4/video-to-video/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/krea/v3/edit": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills krea/v3/edit at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/krea/v3/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/krea/v3/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills krea/v3/text-to-image at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.025, "output_cost_per_pixel": 2.384185791015625e-08, "source": "https://fal.ai/models/krea/v3/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/luma/agent/uni-1/v1/max": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.102, "source": "https://fal.ai/models/luma/agent/uni-1/v1/max", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/luma/agent/uni-1/v1/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.042, "source": "https://fal.ai/models/luma/agent/uni-1/v1/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/meta/muse-image/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/meta/muse-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/meta/muse-image/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/meta/muse-image/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/minimax/h3-max-turbo/extend-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_1080p": 0.08, "output_cost_per_second_2k": 0.16, "output_cost_per_second_480p": 0.025, "output_cost_per_second_768p": 0.04, "source": "https://fal.ai/models/minimax/h3-max-turbo/extend-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max-turbo/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.16, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max-turbo/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/extend-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.16, "output_cost_per_second_2k": 0.32, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/extend-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/insert-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.06, "source": "https://fal.ai/models/minimax/h3-max/insert-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/lip-sync/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.16, "output_cost_per_second_2k": 0.32, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/lip-sync/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_2k": 0.13, "output_cost_per_second_480p": 0.05, "output_cost_per_second_4k": 0.16, "output_cost_per_second_768p": 0.06, "source": "https://fal.ai/models/minimax/h3/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3/image-to-video/lora": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.1625, "output_cost_per_second_2k": 0.1625, "output_cost_per_second_480p": 0.0625, "output_cost_per_second_4k": 0.2, "output_cost_per_second_768p": 0.075, "source": "https://fal.ai/models/minimax/h3/image-to-video/lora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3/reference-to-video/lora": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.1625, "output_cost_per_second_2k": 0.1625, "output_cost_per_second_480p": 0.0625, "output_cost_per_second_4k": 0.2, "output_cost_per_second_768p": 0.075, "source": "https://fal.ai/models/minimax/h3/reference-to-video/lora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3/text-to-video/lora": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, "mode": "video_generation", "output_cost_per_second": 0.1625, "output_cost_per_second_2k": 0.1625, "output_cost_per_second_480p": 0.0625, "output_cost_per_second_4k": 0.2, "output_cost_per_second_768p": 0.075, "source": "https://fal.ai/models/minimax/h3/text-to-video/lora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/nvidia/cosmos-3-super/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/nvidia/cosmos-3-super/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/pixelcut/background-removal": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.016, "source": "https://fal.ai/models/pixelcut/background-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/pixelcut/looping-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.32, "output_cost_per_second_1080p": 0.32, "output_cost_per_second_480p": 0.08, "output_cost_per_second_768p": 0.16, "source": "https://fal.ai/models/pixelcut/looping-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/pixelcut/product-photo": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.024, "source": "https://fal.ai/models/pixelcut/product-photo", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/pixverse/music-video/vibemv": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.09, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/pixverse/music-video/vibemv", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "video" ] }, "fal_ai/recraft/v4.1/flash/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.007, "source": "https://fal.ai/models/recraft/v4.1/flash/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/rundiffusion-fal/juggernaut-flux/base": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/rundiffusion-fal/juggernaut-flux/base/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/base/image-to-image at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.035, "output_cost_per_pixel": 3.337860107421875e-08, "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/base/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/rundiffusion-fal/juggernaut-flux/lightning": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/lightning at $0.006 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.006, "output_cost_per_pixel": 5.7220458984375e-09, "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/lightning", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/rundiffusion-fal/juggernaut-flux/pro": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.055, "output_cost_per_pixel": 5.245208740234375e-08, "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/rundiffusion-fal/juggernaut-flux/pro/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/juggernaut-flux/pro/image-to-image at $0.055 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.055, "output_cost_per_pixel": 5.245208740234375e-08, "source": "https://fal.ai/models/rundiffusion-fal/juggernaut-flux/pro/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/rundiffusion-fal/rundiffusion-photo-flux": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills rundiffusion-fal/rundiffusion-photo-flux at $0.045 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_pixel": 4.291534423828125e-08, "source": "https://fal.ai/models/rundiffusion-fal/rundiffusion-photo-flux", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/smoretalk-ai/rembg-enhance": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.006, "source": "https://fal.ai/models/smoretalk-ai/rembg-enhance", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/sonilo/v1.1/video-to-video-music": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.009, "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-music", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/sonilo/v1.1/video-to-video-sound-effects": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.009, "source": "https://fal.ai/models/sonilo/v1.1/video-to-video-sound-effects", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/tbc/mischief-1/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.01, "output_cost_per_second_480p": 0.005, "output_cost_per_second_720p": 0.01, "source": "https://fal.ai/models/tbc/mischief-1/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/veed/fabric-1.0": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.15, "source": "https://fal.ai/models/veed/fabric-1.0", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/veed/fabric-1.0/fast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, "mode": "video_generation", "output_cost_per_second": 0.2, "output_cost_per_second_480p": 0.1, "output_cost_per_second_720p": 0.2, "source": "https://fal.ai/models/veed/fabric-1.0/fast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/veed/fabric-1.0/text": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; the page's resolution default is auto or unstated, so output_cost_per_second is the highest tier (720p)"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.15, "source": "https://fal.ai/models/veed/fabric-1.0/text", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/wan/v2.6/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/wan/v2.6/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/wan/v2.6/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/wan/v2.6/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/wan/v2.6/image-to-video/flash": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.075, "output_cost_per_second_1080p": 0.075, "output_cost_per_second_720p": 0.05, "source": "https://fal.ai/models/wan/v2.6/image-to-video/flash", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/wan/v2.6/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/wan/v2.6/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/wan/v2.6/text-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/wan/v2.6/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/wan/v2.6/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/wan/v2.6/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://fal.ai/models/xai/grok-imagine-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/xai/grok-imagine-video/v1.5/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.14, "output_cost_per_second_1080p": 0.25, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/alibaba/happy-horse/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/alibaba/happy-horse/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/creatify/boreal": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.01, "output_cost_per_second_1080p": 0.03, "output_cost_per_second_2k": 0.12, "output_cost_per_second_720p": 0.01, "source": "https://fal.ai/models/creatify/boreal", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/creatify/aurora": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.14, "output_cost_per_second_480p": 0.07, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/fal-ai/creatify/aurora", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/vidu/q4/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, "mode": "video_generation", "output_cost_per_second": 0.0665, "output_cost_per_second_1080p": 0.084, "output_cost_per_second_2k": 0.133, "output_cost_per_second_4k": 0.273, "output_cost_per_second_720p": 0.0665, "source": "https://fal.ai/models/fal-ai/vidu/q4/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/vidu/q4/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; tiers without a catalog field: 540p $0.0315"}, "mode": "video_generation", "output_cost_per_second": 0.0665, "output_cost_per_second_1080p": 0.084, "output_cost_per_second_2k": 0.133, "output_cost_per_second_4k": 0.273, "output_cost_per_second_720p": 0.0665, "source": "https://fal.ai/models/fal-ai/vidu/q4/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/ideogram/v4.5": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/ideogram/v4.5", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/ideogram/v4.5/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://fal.ai/models/ideogram/v4.5/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/ideogram/v4/instant": { "litellm_provider": "fal_ai", "metadata": {"notes":"fal bills ideogram/v4/instant at $0.0075 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries"}, "mode": "image_generation", "output_cost_per_image": 0.0075, "output_cost_per_pixel": 7.152557373046875e-09, "source": "https://fal.ai/models/ideogram/v4/instant", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/lightricks/ltx-2.5/image-to-video/fast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_1080p": 0.13, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.09, "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/fast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/lightricks/ltx-2.5/image-to-video/pro": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.17, "output_cost_per_second_720p": 0.12, "source": "https://fal.ai/models/lightricks/ltx-2.5/image-to-video/pro", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/lightricks/ltx-2.5/text-to-video/fast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate; tiers without a catalog field: 1440p $0.19"}, "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_1080p": 0.13, "output_cost_per_second_4k": 0.3, "output_cost_per_second_720p": 0.09, "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/fast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/lightricks/ltx-2.5/text-to-video/pro": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.17, "output_cost_per_second_720p": 0.12, "source": "https://fal.ai/models/lightricks/ltx-2.5/text-to-video/pro", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/recast": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.45, "output_cost_per_second_1080p": 0.45, "output_cost_per_second_768p": 0.3, "source": "https://fal.ai/models/minimax/h3-max/recast", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/reframe-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/reframe-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/relight": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.16, "output_cost_per_second_2k": 0.32, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/relight", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/wan/v2.6/reference-to-video/flash": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 1080p rate"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://fal.ai/models/wan/v2.6/reference-to-video/flash", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/v1.5/lite/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.14, "output_cost_per_second_480p": 0.02, "output_cost_per_second_720p": 0.03, "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/v1.5/lite/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.14, "output_cost_per_second_480p": 0.02, "output_cost_per_second_720p": 0.03, "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/lite/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3-max/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.085, "output_cost_per_second_1080p": 0.145, "output_cost_per_second_720p": 0.085, "source": "https://fal.ai/models/blackforestlabs/flux-3-max/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3-max/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; promotional 50% off rate through 2026-11-22 23:59 UTC per the page; regular rates $0.17 (720p) and $0.29 (1080p) per second resume 2026-11-23 00:00 UTC (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.085, "output_cost_per_second_1080p": 0.145, "output_cost_per_second_720p": 0.085, "source": "https://fal.ai/models/blackforestlabs/flux-3-max/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3-max/keyframes-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; regular rate; the page's 75% promotion ran October 15 to November 7, 2026 and has ended (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_720p": 0.17, "source": "https://fal.ai/models/blackforestlabs/flux-3-max/keyframes-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/heygen/heygen-video/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.02, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.06, "output_cost_per_second_480p": 0.02, "output_cost_per_second_768p": 0.02, "source": "https://fal.ai/models/heygen/heygen-video/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/heygen/heygen-video/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.02, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.06, "output_cost_per_second_480p": 0.02, "output_cost_per_second_768p": 0.02, "source": "https://fal.ai/models/heygen/heygen-video/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/heygen/heygen-video/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; regular rate; the page's 50% promotion ended October 31, 2026 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.02, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.06, "output_cost_per_second_480p": 0.02, "output_cost_per_second_768p": 0.02, "source": "https://fal.ai/models/heygen/heygen-video/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max-turbo/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.028, "output_cost_per_second_1080p": 0.056, "output_cost_per_second_480p": 0.0175, "output_cost_per_second_768p": 0.028, "source": "https://fal.ai/models/minimax/h3-max-turbo/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max-turbo/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.025 (480p), $0.04 (768p), $0.08 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.028, "output_cost_per_second_1080p": 0.056, "output_cost_per_second_480p": 0.0175, "output_cost_per_second_768p": 0.028, "source": "https://fal.ai/models/minimax/h3-max-turbo/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/camera-controls": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 480p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.035, "output_cost_per_second_1080p": 0.112, "output_cost_per_second_480p": 0.035, "output_cost_per_second_768p": 0.056, "source": "https://fal.ai/models/minimax/h3-max/camera-controls", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.056, "output_cost_per_second_1080p": 0.112, "output_cost_per_second_480p": 0.035, "output_cost_per_second_768p": 0.056, "source": "https://fal.ai/models/minimax/h3-max/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768p rate; promotional 30% off rate through 2026-11-15 per the page; standard rates $0.05 (480p), $0.08 (768p), $0.16 (1080p) per second from 2026-11-16 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10)"}, "mode": "video_generation", "output_cost_per_second": 0.056, "output_cost_per_second_1080p": 0.112, "output_cost_per_second_480p": 0.035, "output_cost_per_second_768p": 0.056, "source": "https://fal.ai/models/minimax/h3-max/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "replicate/alibaba/happyhorse-1.0": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_720p": 0.14, "source": "https://replicate.com/alibaba/happyhorse-1.0" }, "replicate/alibaba/happyhorse-1.1": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.18, "output_cost_per_second_1080p": 0.18, "output_cost_per_second_720p": 0.14, "source": "https://replicate.com/alibaba/happyhorse-1.1" }, "replicate/alibaba/qwen-image-3": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/alibaba/qwen-image-3" }, "replicate/alibaba/qwen-image-3-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/alibaba/qwen-image-3-pro" }, "replicate/alibaba/wan-3": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.14, "output_cost_per_second_1080p": 0.14, "output_cost_per_second_480p": 0.035, "output_cost_per_second_720p": 0.07, "source": "https://replicate.com/alibaba/wan-3" }, "replicate/alibaba/wan-3-prime": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.28, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_480p": 0.068, "output_cost_per_second_720p": 0.14, "source": "https://replicate.com/alibaba/wan-3-prime" }, "replicate/anthropic/claude-fable-5": { "input_cost_per_token": 1e-05, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 5e-05, "source": "https://replicate.com/anthropic/claude-fable-5", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-fable-5.2": { "input_cost_per_token": 8e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 4e-05, "source": "https://replicate.com/anthropic/claude-fable-5.2", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-opus-4.6": { "input_cost_per_token": 5e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://replicate.com/anthropic/claude-opus-4.6", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-opus-4.7": { "input_cost_per_token": 5e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://replicate.com/anthropic/claude-opus-4.7", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-opus-5.5": { "input_cost_per_token": 4e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://replicate.com/anthropic/claude-opus-5.5", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-sonnet-4.6": { "input_cost_per_token": 3e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://replicate.com/anthropic/claude-sonnet-4.6", "supports_system_messages": true, "supports_vision": true }, "replicate/anthropic/claude-sonnet-5": { "input_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://replicate.com/anthropic/claude-sonnet-5", "supports_system_messages": true, "supports_vision": true }, "replicate/black-forest-labs/flux-1.1-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/black-forest-labs/flux-1.1-pro" }, "replicate/black-forest-labs/flux-1.1-pro-ultra": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra" }, "replicate/black-forest-labs/flux-1.1-pro-ultra-finetuned": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.07, "source": "https://replicate.com/black-forest-labs/flux-1.1-pro-ultra-finetuned" }, "replicate/black-forest-labs/flux-2-flex": { "input_cost_per_pixel": 6e-08, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 6e-08, "source": "https://replicate.com/black-forest-labs/flux-2-flex" }, "replicate/black-forest-labs/flux-2-klein-4b": { "input_cost_per_pixel": 1e-09, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 1e-09, "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b" }, "replicate/black-forest-labs/flux-2-klein-4b-base": { "input_cost_per_pixel": 9e-09, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 9e-09, "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base" }, "replicate/black-forest-labs/flux-2-klein-4b-base-lora": { "input_cost_per_pixel": 9e-09, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 1.9e-08, "source": "https://replicate.com/black-forest-labs/flux-2-klein-4b-base-lora" }, "replicate/black-forest-labs/flux-2-klein-9b": { "input_cost_per_pixel": 2e-09, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 1.5e-08, "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b" }, "replicate/black-forest-labs/flux-2-klein-9b-base": { "input_cost_per_pixel": 1.1e-08, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 1.1e-08, "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base" }, "replicate/black-forest-labs/flux-2-klein-9b-base-lora": { "input_cost_per_pixel": 1.1e-08, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 2.1e-08, "source": "https://replicate.com/black-forest-labs/flux-2-klein-9b-base-lora" }, "replicate/black-forest-labs/flux-canny-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-canny-dev" }, "replicate/black-forest-labs/flux-canny-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://replicate.com/black-forest-labs/flux-canny-pro" }, "replicate/black-forest-labs/flux-depth-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-depth-dev" }, "replicate/black-forest-labs/flux-depth-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://replicate.com/black-forest-labs/flux-depth-pro" }, "replicate/black-forest-labs/flux-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-dev" }, "replicate/black-forest-labs/flux-dev-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.032, "source": "https://replicate.com/black-forest-labs/flux-dev-lora" }, "replicate/black-forest-labs/flux-fill-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/black-forest-labs/flux-fill-dev" }, "replicate/black-forest-labs/flux-fill-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://replicate.com/black-forest-labs/flux-fill-pro" }, "replicate/black-forest-labs/flux-kontext-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-kontext-dev" }, "replicate/black-forest-labs/flux-kontext-dev-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.032, "source": "https://replicate.com/black-forest-labs/flux-kontext-dev-lora" }, "replicate/black-forest-labs/flux-kontext-max": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/black-forest-labs/flux-kontext-max" }, "replicate/black-forest-labs/flux-kontext-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/black-forest-labs/flux-kontext-pro" }, "replicate/black-forest-labs/flux-krea-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-krea-dev" }, "replicate/black-forest-labs/flux-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.055, "source": "https://replicate.com/black-forest-labs/flux-pro" }, "replicate/black-forest-labs/flux-pro-finetuned": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://replicate.com/black-forest-labs/flux-pro-finetuned" }, "replicate/black-forest-labs/flux-redux-dev": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/black-forest-labs/flux-redux-dev" }, "replicate/black-forest-labs/flux-redux-schnell": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.003, "source": "https://replicate.com/black-forest-labs/flux-redux-schnell" }, "replicate/black-forest-labs/flux-schnell": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.003, "source": "https://replicate.com/black-forest-labs/flux-schnell" }, "replicate/black-forest-labs/flux-schnell-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://replicate.com/black-forest-labs/flux-schnell-lora" }, "replicate/bria/eraser": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/eraser" }, "replicate/bria/expand-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/expand-image" }, "replicate/bria/fibo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/fibo" }, "replicate/bria/fibo-edit": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/fibo-edit" }, "replicate/bria/generate-background": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/generate-background" }, "replicate/bria/genfill": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/genfill" }, "replicate/bria/image-3.2": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/image-3.2" }, "replicate/bria/increase-resolution": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/increase-resolution" }, "replicate/bria/product-cutout": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/product-cutout" }, "replicate/bria/product-packshot": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/product-packshot" }, "replicate/bria/product-shadow": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bria/product-shadow" }, "replicate/bria/remove-background": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.018, "source": "https://replicate.com/bria/remove-background" }, "replicate/bria/video-erase-object": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/bria/video-erase-object" }, "replicate/bria/video-increase-resolution": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/bria/video-increase-resolution" }, "replicate/bria/video-remove-background": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/bria/video-remove-background" }, "replicate/bytedance/dreamactor-m2.0": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/bytedance/dreamactor-m2.0" }, "replicate/bytedance/dreamina-3.1": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/bytedance/dreamina-3.1" }, "replicate/bytedance/omni-human": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://replicate.com/bytedance/omni-human" }, "replicate/bytedance/omni-human-1.5": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.16, "source": "https://replicate.com/bytedance/omni-human-1.5" }, "replicate/bytedance/seedance-1-lite": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.036, "output_cost_per_second_1080p": 0.072, "output_cost_per_second_480p": 0.018, "output_cost_per_second_720p": 0.036, "source": "https://replicate.com/bytedance/seedance-1-lite" }, "replicate/bytedance/seedance-1-pro": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_480p": 0.03, "output_cost_per_second_720p": 0.06, "source": "https://replicate.com/bytedance/seedance-1-pro" }, "replicate/bytedance/seedance-1-pro-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_480p": 0.015, "output_cost_per_second_720p": 0.025, "source": "https://replicate.com/bytedance/seedance-1-pro-fast" }, "replicate/bytedance/seedream-3": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/bytedance/seedream-3" }, "replicate/bytedance/seedream-4": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/bytedance/seedream-4" }, "replicate/bytedance/seedream-4.5": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/bytedance/seedream-4.5" }, "replicate/bytedance/seedream-5-lite": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://replicate.com/bytedance/seedream-5-lite" }, "replicate/datalab-to/ocr": { "litellm_provider": "replicate", "mode": "ocr", "ocr_cost_per_page": 0.002, "source": "https://replicate.com/datalab-to/ocr" }, "replicate/decart/lucy-edit-2": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://replicate.com/decart/lucy-edit-2" }, "replicate/easel/ai-avatars": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://replicate.com/easel/ai-avatars" }, "replicate/elevenlabs/dubbing": { "litellm_provider": "replicate", "mode": "audio_speech", "output_cost_per_second": 0.0366667, "source": "https://replicate.com/elevenlabs/dubbing" }, "replicate/elevenlabs/flash-v2.5": { "input_cost_per_character": 5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/elevenlabs/flash-v2.5" }, "replicate/elevenlabs/turbo-v2.5": { "input_cost_per_character": 5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/elevenlabs/turbo-v2.5" }, "replicate/elevenlabs/v2-multilingual": { "input_cost_per_character": 0.0001, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/elevenlabs/v2-multilingual" }, "replicate/elevenlabs/v3": { "input_cost_per_character": 0.0001, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/elevenlabs/v3" }, "replicate/flux-kontext-apps/cartoonify": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/cartoonify" }, "replicate/flux-kontext-apps/change-haircut": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/change-haircut" }, "replicate/flux-kontext-apps/depth-of-field": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/depth-of-field" }, "replicate/flux-kontext-apps/face-to-many-kontext": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/face-to-many-kontext" }, "replicate/flux-kontext-apps/filters": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/filters" }, "replicate/flux-kontext-apps/iconic-locations": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/iconic-locations" }, "replicate/flux-kontext-apps/impossible-scenarios": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/impossible-scenarios" }, "replicate/flux-kontext-apps/multi-image-kontext-max": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-max" }, "replicate/flux-kontext-apps/multi-image-kontext-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/multi-image-kontext-pro" }, "replicate/flux-kontext-apps/multi-image-list": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/flux-kontext-apps/multi-image-list" }, "replicate/flux-kontext-apps/portrait-series": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/portrait-series" }, "replicate/flux-kontext-apps/professional-headshot": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/professional-headshot" }, "replicate/flux-kontext-apps/restore-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/restore-image" }, "replicate/flux-kontext-apps/restyle-video-frame": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/restyle-video-frame" }, "replicate/flux-kontext-apps/text-removal": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/flux-kontext-apps/text-removal" }, "replicate/google/gemini-2.5-flash-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.039, "source": "https://replicate.com/google/gemini-2.5-flash-image" }, "replicate/google/gemini-3-flash": { "input_cost_per_token": 5e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://replicate.com/google/gemini-3-flash", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/google/gemini-3.1-flash-tts": { "input_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "audio_speech", "output_cost_per_token": 4e-05, "source": "https://replicate.com/google/gemini-3.1-flash-tts" }, "replicate/google/gemini-3.1-pro": { "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, "source": "https://replicate.com/google/gemini-3.1-pro", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/google/gemini-3.5-flash": { "input_cost_per_token": 1.5e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 9e-06, "source": "https://replicate.com/google/gemini-3.5-flash", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/google/gemini-3.8-flash-lite-tts": { "input_cost_per_token": 5e-07, "litellm_provider": "replicate", "mode": "audio_speech", "output_cost_per_token": 6e-06, "source": "https://replicate.com/google/gemini-3.8-flash-lite-tts" }, "replicate/google/gemini-3.8-flash-tts": { "input_cost_per_token": 5e-07, "litellm_provider": "replicate", "mode": "audio_speech", "output_cost_per_token": 9e-06, "source": "https://replicate.com/google/gemini-3.8-flash-tts" }, "replicate/google/nano-banana": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.039, "source": "https://replicate.com/google/nano-banana" }, "replicate/google/nano-banana-2": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.067, "output_cost_per_image_1K": 0.067, "output_cost_per_image_2K": 0.101, "output_cost_per_image_4K": 0.151, "source": "https://replicate.com/google/nano-banana-2" }, "replicate/google/nano-banana-2-lite": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.034, "source": "https://replicate.com/google/nano-banana-2-lite" }, "replicate/google/nano-banana-2.1": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_1K": 0.0336, "output_cost_per_image_2K": 0.0504, "output_cost_per_image_4K": 0.1134, "source": "https://replicate.com/google/nano-banana-2.1" }, "replicate/google/nano-banana-latest": { "alias_of": "replicate/google/nano-banana-2.1" }, "replicate/heygen/avatar-iv": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.075, "source": "https://replicate.com/heygen/avatar-iv" }, "replicate/heygen/avatar-v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.075, "source": "https://replicate.com/heygen/avatar-v" }, "replicate/heygen/lipsync-precision": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.0667, "source": "https://replicate.com/heygen/lipsync-precision" }, "replicate/heygen/lipsync-speed": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.0333, "source": "https://replicate.com/heygen/lipsync-speed" }, "replicate/heygen/video-agent": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.0333, "source": "https://replicate.com/heygen/video-agent" }, "replicate/ibm-granite/granite-20b-code-instruct-8k": { "input_cost_per_token": 1e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://replicate.com/ibm-granite/granite-20b-code-instruct-8k", "supports_system_messages": true }, "replicate/ibm-granite/granite-3.0-2b-instruct": { "input_cost_per_token": 3e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-3.0-2b-instruct", "supports_system_messages": true }, "replicate/ibm-granite/granite-3.0-8b-instruct": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-3.0-8b-instruct", "supports_system_messages": true }, "replicate/ibm-granite/granite-3.1-2b-instruct": { "input_cost_per_token": 3e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-3.1-2b-instruct", "supports_system_messages": true }, "replicate/ibm-granite/granite-3.1-8b-instruct": { "input_cost_per_token": 3e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-3.1-8b-instruct", "supports_system_messages": true }, "replicate/ibm-granite/granite-3.2-8b-instruct": { "input_cost_per_token": 3e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-3.2-8b-instruct", "supports_system_messages": true }, "replicate/ibm-granite/granite-4.0-h-small": { "input_cost_per_token": 6e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-4.0-h-small", "supports_function_calling": true, "supports_system_messages": true }, "replicate/ibm-granite/granite-4.1-8b": { "input_cost_per_token": 6e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-4.1-8b", "supports_function_calling": true, "supports_system_messages": true }, "replicate/ibm-granite/granite-4.2-8b": { "input_cost_per_token": 6e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-4.2-8b", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true }, "replicate/ibm-granite/granite-8b-code-instruct-128k": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-8b-code-instruct-128k", "supports_system_messages": true }, "replicate/ibm-granite/granite-speech-3.3-8b": { "litellm_provider": "replicate", "mode": "audio_transcription", "output_cost_per_token": 4.9e-06, "source": "https://replicate.com/ibm-granite/granite-speech-3.3-8b" }, "replicate/ibm-granite/granite-speech-4.1-2b": { "input_cost_per_token": 3e-08, "litellm_provider": "replicate", "mode": "audio_transcription", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-speech-4.1-2b" }, "replicate/ibm-granite/granite-vision-3.3-2b": { "input_cost_per_token": 0.0, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-vision-3.3-2b", "supports_system_messages": true, "supports_vision": true }, "replicate/ibm-granite/granite-vision-4.1-4b": { "input_cost_per_token": 6e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/ibm-granite/granite-vision-4.1-4b", "supports_system_messages": true, "supports_vision": true }, "replicate/ideogram-ai/ideogram-v2": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/ideogram-ai/ideogram-v2" }, "replicate/ideogram-ai/ideogram-v2-turbo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://replicate.com/ideogram-ai/ideogram-v2-turbo" }, "replicate/ideogram-ai/ideogram-v2a": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/ideogram-ai/ideogram-v2a" }, "replicate/ideogram-ai/ideogram-v2a-turbo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/ideogram-ai/ideogram-v2a-turbo" }, "replicate/ideogram-ai/ideogram-v3-balanced": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://replicate.com/ideogram-ai/ideogram-v3-balanced" }, "replicate/ideogram-ai/ideogram-v3-quality": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.09, "source": "https://replicate.com/ideogram-ai/ideogram-v3-quality" }, "replicate/ideogram-ai/ideogram-v3-turbo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/ideogram-ai/ideogram-v3-turbo" }, "replicate/ideogram-ai/ideogram-v4-balanced": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.06, "source": "https://replicate.com/ideogram-ai/ideogram-v4-balanced" }, "replicate/ideogram-ai/ideogram-v4-quality": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://replicate.com/ideogram-ai/ideogram-v4-quality" }, "replicate/ideogram-ai/layerize": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.09, "source": "https://replicate.com/ideogram-ai/layerize" }, "replicate/intelligent-utilities/html-to-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.001, "source": "https://replicate.com/intelligent-utilities/html-to-image" }, "replicate/inworld/realtime-tts-1.5-max": { "input_cost_per_character": 3.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/inworld/realtime-tts-1.5-max" }, "replicate/inworld/realtime-tts-1.5-mini": { "input_cost_per_character": 1.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/inworld/realtime-tts-1.5-mini" }, "replicate/inworld/realtime-tts-2": { "input_cost_per_character": 2.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/inworld/realtime-tts-2" }, "replicate/kwaivgi/kling-lip-sync": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.014, "source": "https://replicate.com/kwaivgi/kling-lip-sync" }, "replicate/kwaivgi/kling-v2.1-master": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.28, "source": "https://replicate.com/kwaivgi/kling-v2.1-master" }, "replicate/kwaivgi/kling-v2.5-turbo-pro": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.07, "source": "https://replicate.com/kwaivgi/kling-v2.5-turbo-pro" }, "replicate/lightricks/audio-to-video": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://replicate.com/lightricks/audio-to-video" }, "replicate/lightricks/ltx-2-distilled": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://replicate.com/lightricks/ltx-2-distilled" }, "replicate/lightricks/ltx-2-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_1080p": 0.04, "output_cost_per_second_2k": 0.08, "output_cost_per_second_4k": 0.16, "source": "https://replicate.com/lightricks/ltx-2-fast" }, "replicate/lightricks/ltx-2-pro": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.12, "output_cost_per_second_4k": 0.24, "source": "https://replicate.com/lightricks/ltx-2-pro" }, "replicate/lightricks/ltx-2-retake": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://replicate.com/lightricks/ltx-2-retake" }, "replicate/lightricks/ltx-2.3-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.12, "output_cost_per_second_4k": 0.24, "source": "https://replicate.com/lightricks/ltx-2.3-fast" }, "replicate/lightricks/ltx-2.3-pro": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.08, "output_cost_per_second_2k": 0.16, "output_cost_per_second_4k": 0.32, "source": "https://replicate.com/lightricks/ltx-2.3-pro" }, "replicate/lightricks/ltx-2.5-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.12, "output_cost_per_second_4k": 0.24, "output_cost_per_second_720p": 0.03, "source": "https://replicate.com/lightricks/ltx-2.5-fast" }, "replicate/luma/photon": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/luma/photon" }, "replicate/luma/photon-flash": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/luma/photon-flash" }, "replicate/luma/reframe-video": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.06, "source": "https://replicate.com/luma/reframe-video" }, "replicate/meta/llama-4-maverick-instruct": { "input_cost_per_token": 2.5e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 9.5e-07, "source": "https://replicate.com/meta/llama-4-maverick-instruct", "supports_system_messages": true }, "replicate/meta/llama-4-scout-instruct": { "input_cost_per_token": 1.7e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://replicate.com/meta/llama-4-scout-instruct", "supports_system_messages": true }, "replicate/meta/llama-guard-4-12b": { "input_cost_per_token": 2e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://replicate.com/meta/llama-guard-4-12b", "supports_system_messages": true, "supports_vision": true }, "replicate/meta/meta-llama-3-70b": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.75e-06, "source": "https://replicate.com/meta/meta-llama-3-70b" }, "replicate/meta/meta-llama-3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.75e-06, "source": "https://replicate.com/meta/meta-llama-3-70b-instruct", "supports_system_messages": true }, "replicate/meta/meta-llama-3-8b": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/meta/meta-llama-3-8b" }, "replicate/meta/meta-llama-3-8b-instruct": { "input_cost_per_token": 5e-08, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://replicate.com/meta/meta-llama-3-8b-instruct", "supports_system_messages": true }, "replicate/minimax/h3": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.13, "output_cost_per_second_2k": 0.13, "output_cost_per_second_768p": 0.08, "source": "https://replicate.com/minimax/h3" }, "replicate/minimax/h3-highspeed": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.03, "source": "https://replicate.com/minimax/h3-highspeed" }, "replicate/minimax/h3-lite": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.02, "output_cost_per_second_480p": 0.0125, "output_cost_per_second_768p": 0.02, "source": "https://replicate.com/minimax/h3-lite" }, "replicate/minimax/image-01": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/minimax/image-01" }, "replicate/minimax/speech-02-hd": { "input_cost_per_token": 0.0001, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-02-hd" }, "replicate/minimax/speech-02-turbo": { "input_cost_per_token": 6e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-02-turbo" }, "replicate/minimax/speech-2.6-hd": { "input_cost_per_token": 0.0001, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-2.6-hd" }, "replicate/minimax/speech-2.6-turbo": { "input_cost_per_token": 6e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-2.6-turbo" }, "replicate/minimax/speech-2.8-hd": { "input_cost_per_token": 0.0001, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-2.8-hd" }, "replicate/minimax/speech-2.8-turbo": { "input_cost_per_token": 6e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/minimax/speech-2.8-turbo" }, "replicate/moonshotai/kimi-k2-thinking": { "input_cost_per_token": 6.6e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.7e-06, "source": "https://replicate.com/moonshotai/kimi-k2-thinking" }, "replicate/moonshotai/kimi-k2.5": { "input_cost_per_token": 7.2e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://replicate.com/moonshotai/kimi-k2.5", "supports_vision": true }, "replicate/moonshotai/kimi-k2.6": { "input_cost_per_token": 9.5e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://replicate.com/moonshotai/kimi-k2.6", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/nightmareai/real-esrgan": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.002, "source": "https://replicate.com/nightmareai/real-esrgan" }, "replicate/openai/gpt-4o-mini-transcribe": { "input_cost_per_token": 3e-06, "litellm_provider": "replicate", "mode": "audio_transcription", "output_cost_per_token": 5e-06, "source": "https://replicate.com/openai/gpt-4o-mini-transcribe" }, "replicate/openai/gpt-4o-transcribe": { "input_cost_per_token": 6e-06, "litellm_provider": "replicate", "mode": "audio_transcription", "output_cost_per_token": 1e-05, "source": "https://replicate.com/openai/gpt-4o-transcribe" }, "replicate/openai/gpt-5-pro": { "input_cost_per_token": 1.5e-05, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 0.00012, "source": "https://replicate.com/openai/gpt-5-pro", "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.1": { "input_cost_per_token": 1.25e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://replicate.com/openai/gpt-5.1", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.2": { "input_cost_per_token": 1.75e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://replicate.com/openai/gpt-5.2", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.4": { "input_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://replicate.com/openai/gpt-5.4", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.6-luna": { "input_cost_per_token": 1e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://replicate.com/openai/gpt-5.6-luna", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.6-sol": { "input_cost_per_token": 2e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://replicate.com/openai/gpt-5.6-sol", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/openai/gpt-5.6-terra": { "input_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://replicate.com/openai/gpt-5.6-terra", "supports_reasoning": true, "supports_system_messages": true, "supports_vision": true }, "replicate/perceptron-ai-inc/isaac-0.1": { "input_cost_per_token": 2.6e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2.17e-06, "source": "https://replicate.com/perceptron-ai-inc/isaac-0.1", "supports_vision": true }, "replicate/philz1337x/clarity-pro-upscaler": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_pixel": 3e-08, "source": "https://replicate.com/philz1337x/clarity-pro-upscaler" }, "replicate/pixverse/lipsync": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://replicate.com/pixverse/lipsync" }, "replicate/playht/play-dialog": { "litellm_provider": "replicate", "mode": "audio_speech", "output_cost_per_second": 0.001, "source": "https://replicate.com/playht/play-dialog" }, "replicate/prunaai/flux-fast": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://replicate.com/prunaai/flux-fast" }, "replicate/prunaai/flux-kontext-fast": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/prunaai/flux-kontext-fast" }, "replicate/prunaai/hidream-l1-fast": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://replicate.com/prunaai/hidream-l1-fast" }, "replicate/prunaai/p-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://replicate.com/prunaai/p-image" }, "replicate/prunaai/p-image-edit": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/prunaai/p-image-edit" }, "replicate/prunaai/p-image-edit-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/prunaai/p-image-edit-lora" }, "replicate/prunaai/p-image-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.005, "source": "https://replicate.com/prunaai/p-image-lora" }, "replicate/prunaai/p-video-2-pro-avatar": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.08, "output_cost_per_second_480p": 0.02, "output_cost_per_second_4k": 0.12, "output_cost_per_second_768p": 0.04, "source": "https://replicate.com/prunaai/p-video-2-pro-avatar" }, "replicate/prunaai/p-video-2-pro-replace": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_2k": 0.07, "output_cost_per_second_480p": 0.025, "output_cost_per_second_4k": 0.09, "output_cost_per_second_768p": 0.05, "source": "https://replicate.com/prunaai/p-video-2-pro-replace" }, "replicate/prunaai/p-video-animate": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_720p": 0.03, "source": "https://replicate.com/prunaai/p-video-animate" }, "replicate/prunaai/p-video-avatar": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.025, "output_cost_per_second_1080p": 0.045, "output_cost_per_second_720p": 0.025, "source": "https://replicate.com/prunaai/p-video-avatar" }, "replicate/prunaai/p-video-replace": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.06, "output_cost_per_second_720p": 0.03, "source": "https://replicate.com/prunaai/p-video-replace" }, "replicate/prunaai/wan-2.2-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://replicate.com/prunaai/wan-2.2-image" }, "replicate/quiverai/arrow-1.1": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.2, "source": "https://replicate.com/quiverai/arrow-1.1" }, "replicate/quiverai/arrow-1.1-max": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://replicate.com/quiverai/arrow-1.1-max" }, "replicate/quiverai/arrow-1.1-max-vectorize": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.2, "source": "https://replicate.com/quiverai/arrow-1.1-max-vectorize" }, "replicate/quiverai/arrow-1.1-vectorize": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.15, "source": "https://replicate.com/quiverai/arrow-1.1-vectorize" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-fusion": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-fusion" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-next-scene" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-photo-to-anime" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-relight": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-relight" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-skin": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-skin" }, "replicate/qwen-edit-apps/qwen-image-edit-plus-lora-upscale": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen-edit-apps/qwen-image-edit-plus-lora-upscale" }, "replicate/qwen/qwen-edit-multiangle": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen/qwen-edit-multiangle" }, "replicate/qwen/qwen-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/qwen/qwen-image" }, "replicate/qwen/qwen-image-2": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://replicate.com/qwen/qwen-image-2" }, "replicate/qwen/qwen-image-2-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://replicate.com/qwen/qwen-image-2-pro" }, "replicate/qwen/qwen-image-2512": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://replicate.com/qwen/qwen-image-2512" }, "replicate/qwen/qwen-image-edit": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen/qwen-image-edit" }, "replicate/qwen/qwen-image-edit-2511": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen/qwen-image-edit-2511" }, "replicate/qwen/qwen-image-edit-plus": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen/qwen-image-edit-plus" }, "replicate/qwen/qwen-image-edit-plus-lora": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/qwen/qwen-image-edit-plus-lora" }, "replicate/qwen/qwen3-7-plus": { "input_cost_per_token": 2.76e-07, "input_cost_per_token_above_256k_tokens": 8.26e-07, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 1.101e-06, "output_cost_per_token_above_256k_tokens": 3.301e-06, "source": "https://replicate.com/qwen/qwen3-7-plus", "supports_system_messages": true, "supports_vision": true }, "replicate/qwen/qwen3-tts": { "input_cost_per_character": 2e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/qwen/qwen3-tts" }, "replicate/recraft-ai/recraft-20b": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.022, "source": "https://replicate.com/recraft-ai/recraft-20b" }, "replicate/recraft-ai/recraft-20b-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.044, "source": "https://replicate.com/recraft-ai/recraft-20b-svg" }, "replicate/recraft-ai/recraft-creative-upscale": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://replicate.com/recraft-ai/recraft-creative-upscale" }, "replicate/recraft-ai/recraft-crisp-upscale": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.006, "source": "https://replicate.com/recraft-ai/recraft-crisp-upscale" }, "replicate/recraft-ai/recraft-remove-background": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/recraft-ai/recraft-remove-background" }, "replicate/recraft-ai/recraft-v3": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/recraft-ai/recraft-v3" }, "replicate/recraft-ai/recraft-v3-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/recraft-ai/recraft-v3-svg" }, "replicate/recraft-ai/recraft-v4": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/recraft-ai/recraft-v4" }, "replicate/recraft-ai/recraft-v4-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://replicate.com/recraft-ai/recraft-v4-pro" }, "replicate/recraft-ai/recraft-v4-pro-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://replicate.com/recraft-ai/recraft-v4-pro-svg" }, "replicate/recraft-ai/recraft-v4-styles-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro" }, "replicate/recraft-ai/recraft-v4-styles-pro-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.12, "source": "https://replicate.com/recraft-ai/recraft-v4-styles-pro-svg" }, "replicate/recraft-ai/recraft-v4-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/recraft-ai/recraft-v4-svg" }, "replicate/recraft-ai/recraft-v4.1": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/recraft-ai/recraft-v4.1" }, "replicate/recraft-ai/recraft-v4.1-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro" }, "replicate/recraft-ai/recraft-v4.1-pro-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://replicate.com/recraft-ai/recraft-v4.1-pro-svg" }, "replicate/recraft-ai/recraft-v4.1-svg": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/recraft-ai/recraft-v4.1-svg" }, "replicate/recraft-ai/recraft-v4.1-utility": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility" }, "replicate/recraft-ai/recraft-v4.1-utility-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.25, "source": "https://replicate.com/recraft-ai/recraft-v4.1-utility-pro" }, "replicate/recraft-ai/recraft-vectorize": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://replicate.com/recraft-ai/recraft-vectorize" }, "replicate/resemble-ai/chatterbox": { "input_cost_per_character": 2.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/resemble-ai/chatterbox" }, "replicate/resemble-ai/chatterbox-pro": { "input_cost_per_character": 4e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/resemble-ai/chatterbox-pro" }, "replicate/resemble-ai/chatterbox-turbo": { "input_cost_per_character": 2.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/resemble-ai/chatterbox-turbo" }, "replicate/retro-diffusion/rd-animation": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.07, "source": "https://replicate.com/retro-diffusion/rd-animation" }, "replicate/runwayml/aleph-2": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.336, "source": "https://replicate.com/runwayml/aleph-2" }, "replicate/runwayml/gen-4.5": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.12, "source": "https://replicate.com/runwayml/gen-4.5" }, "replicate/runwayml/gen4-image-turbo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/runwayml/gen4-image-turbo" }, "replicate/runwayml/gen4-turbo": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/runwayml/gen4-turbo" }, "replicate/snowflake/snowflake-arctic-instruct": { "input_cost_per_token": 2e-05, "litellm_provider": "replicate", "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://replicate.com/snowflake/snowflake-arctic-instruct", "supports_system_messages": true }, "replicate/stability-ai/stable-diffusion-3": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://replicate.com/stability-ai/stable-diffusion-3" }, "replicate/stability-ai/stable-diffusion-3.5-large": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.065, "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large" }, "replicate/stability-ai/stable-diffusion-3.5-large-turbo": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-large-turbo" }, "replicate/stability-ai/stable-diffusion-3.5-medium": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://replicate.com/stability-ai/stable-diffusion-3.5-medium" }, "replicate/sync/lipsync-2": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/sync/lipsync-2" }, "replicate/sync/lipsync-2-pro": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.08325, "source": "https://replicate.com/sync/lipsync-2-pro" }, "replicate/sync/react-1": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.167, "source": "https://replicate.com/sync/react-1" }, "replicate/tencent/hunyuan-image-2.1": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://replicate.com/tencent/hunyuan-image-2.1" }, "replicate/tencent/hunyuan-image-3": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://replicate.com/tencent/hunyuan-image-3" }, "replicate/veed/fabric-1.0": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.15, "source": "https://replicate.com/veed/fabric-1.0" }, "replicate/wan-video/wan-2.2-s2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.02, "source": "https://replicate.com/wan-video/wan-2.2-s2v" }, "replicate/wan-video/wan-2.5-i2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://replicate.com/wan-video/wan-2.5-i2v" }, "replicate/wan-video/wan-2.5-i2v-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.068, "output_cost_per_second_1080p": 0.102, "output_cost_per_second_720p": 0.068, "source": "https://replicate.com/wan-video/wan-2.5-i2v-fast" }, "replicate/wan-video/wan-2.5-t2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.1, "source": "https://replicate.com/wan-video/wan-2.5-t2v" }, "replicate/wan-video/wan-2.5-t2v-fast": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.068, "output_cost_per_second_1080p": 0.102, "output_cost_per_second_720p": 0.068, "source": "https://replicate.com/wan-video/wan-2.5-t2v-fast" }, "replicate/wan-video/wan-2.6-i2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://replicate.com/wan-video/wan-2.6-i2v" }, "replicate/wan-video/wan-2.6-t2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://replicate.com/wan-video/wan-2.6-t2v" }, "replicate/wan-video/wan-2.7-i2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_720p": 0.1, "source": "https://replicate.com/wan-video/wan-2.7-i2v" }, "replicate/wan-video/wan-2.7-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/wan-video/wan-2.7-image" }, "replicate/wan-video/wan-2.7-image-pro": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://replicate.com/wan-video/wan-2.7-image-pro" }, "replicate/wan-video/wan-2.7-r2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://replicate.com/wan-video/wan-2.7-r2v" }, "replicate/wan-video/wan-2.7-t2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://replicate.com/wan-video/wan-2.7-t2v" }, "replicate/wan-video/wan-2.7-videoedit": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://replicate.com/wan-video/wan-2.7-videoedit" }, "replicate/wan-video/wan2.6-i2v-flash": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.075, "output_cost_per_second_720p": 0.05, "source": "https://replicate.com/wan-video/wan2.6-i2v-flash" }, "replicate/wavespeedai/qwen-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.025, "source": "https://replicate.com/wavespeedai/qwen-image" }, "replicate/wavespeedai/wan-2.1-i2v-480p": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.09, "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-480p" }, "replicate/wavespeedai/wan-2.1-i2v-720p": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.25, "source": "https://replicate.com/wavespeedai/wan-2.1-i2v-720p" }, "replicate/wavespeedai/wan-2.1-t2v-480p": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.07, "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-480p" }, "replicate/wavespeedai/wan-2.1-t2v-720p": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.24, "source": "https://replicate.com/wavespeedai/wan-2.1-t2v-720p" }, "replicate/xai/grok-imagine-image": { "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://replicate.com/xai/grok-imagine-image" }, "replicate/xai/grok-imagine-image-quality": { "input_cost_per_pixel": 1e-08, "litellm_provider": "replicate", "mode": "image_generation", "output_cost_per_image": 0.06, "output_cost_per_image_1K": 0.04, "output_cost_per_image_2K": 0.06, "source": "https://replicate.com/xai/grok-imagine-image-quality" }, "replicate/xai/grok-imagine-r2v": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/xai/grok-imagine-r2v" }, "replicate/xai/grok-imagine-video": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://replicate.com/xai/grok-imagine-video" }, "replicate/xai/grok-imagine-video-1.5": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.08, "source": "https://replicate.com/xai/grok-imagine-video-1.5" }, "replicate/xai/grok-imagine-video-extension": { "litellm_provider": "replicate", "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://replicate.com/xai/grok-imagine-video-extension" }, "replicate/xai/grok-text-to-speech": { "input_cost_per_character": 1.5e-05, "litellm_provider": "replicate", "mode": "audio_speech", "source": "https://replicate.com/xai/grok-text-to-speech" }, "fal_ai/blackforestlabs/flux-3/edit-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, "mode": "image_generation", "output_cost_per_image": 0.048, "output_cost_per_pixel": 4.57763671875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/edit-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/blackforestlabs/flux-3/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_2k": 0.32, "output_cost_per_second_4k": 0.47, "output_cost_per_second_720p": 0.17, "source": "https://fal.ai/models/blackforestlabs/flux-3/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-3/klein/edit-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (image_size defaults to the input size, 1K is the page example); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.009, "output_cost_per_image_1K": 0.009, "output_cost_per_image_2K": 0.014, "output_cost_per_image_4K": 0.036, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/edit-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/blackforestlabs/flux-3/klein/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per output image by resolution; output_cost_per_image is the 1K rate (default image_size square_hd); 768 x 768 is $0.008 and 1.5K is $0.011 per image, no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.009, "output_cost_per_image_1K": 0.009, "output_cost_per_image_2K": 0.014, "output_cost_per_image_4K": 0.036, "source": "https://fal.ai/models/blackforestlabs/flux-3/klein/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/blackforestlabs/flux-3/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"the page states only the 1K (1 MP) price of $0.048 and the pricing API bills in megapixels at $0.048, so the per-pixel rate is $0.048 per megapixel and the per-image price is the default 1k output; 768sq, 1.5k, 2k and 4k outputs are priced by the per-pixel rate"}, "mode": "image_generation", "output_cost_per_image": 0.048, "output_cost_per_pixel": 4.57763671875e-08, "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/blackforestlabs/flux-3/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; the pricing API reports a $0.085 per second base price that the page does not state"}, "mode": "video_generation", "output_cost_per_second": 0.17, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_2k": 0.32, "output_cost_per_second_4k": 0.47, "output_cost_per_second_720p": 0.17, "source": "https://fal.ai/models/blackforestlabs/flux-3/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/blackforestlabs/flux-video-upscale": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution in the default creative mode (creativity=1); output_cost_per_second is the highest tier (4K) because the output resolution depends on the source and upscale_factor; precise mode (creativity=0) is $0.084 (1080p), $0.15 (2K) and $0.33 (4K) per second and has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.474, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_2k": 0.21, "output_cost_per_second_4k": 0.474, "source": "https://fal.ai/models/blackforestlabs/flux-video-upscale", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bria/fibo-2/generate": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image at the default 1MP output; the 4MP output is $0.06 per image and has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/bria/fibo-2/generate", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bytedance/seedance-2.0/fast/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video at the default resolution 720p, the only per-second rate the page states; fal bills tokens at $0.0112 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, "mode": "video_generation", "output_cost_per_second": 0.2419, "output_cost_per_second_720p": 0.2419, "source": "https://fal.ai/models/bytedance/seedance-2.0/fast/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.0/us/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; 1080p and 4k are not priced on the page; fal bills tokens at $0.0168 per 1000 tokens, counts input video duration, and multiplies by 0.6 with video inputs"}, "mode": "video_generation", "output_cost_per_second": 0.37, "output_cost_per_second_480p": 0.1731, "output_cost_per_second_720p": 0.37, "source": "https://fal.ai/models/bytedance/seedance-2.0/us/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedance-2.5/us/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 720p rate; with video references fal bills input and output duration and multiplies by 0.6"}, "mode": "video_generation", "output_cost_per_second": 0.473, "output_cost_per_second_1080p": 1.164, "output_cost_per_second_480p": 0.2205, "output_cost_per_second_720p": 0.473, "source": "https://fal.ai/models/bytedance/seedance-2.5/us/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/bria/background/remove": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image without a prompt (prompt is optional); $0.03 per image when a prompt is given has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.018, "source": "https://fal.ai/models/fal-ai/bria/background/remove", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/bytedance-upscaler/upscale/video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by target_resolution at 30fps in normal mode; output_cost_per_second is the default target_resolution 1080p rate; 6k $0.0574 and 8k $0.1148 per second have no catalog field; 30-60fps doubles, over 60fps quadruples and pro mode multiplies by 10, none of which is modeled"}, "mode": "video_generation", "output_cost_per_second": 0.0072, "output_cost_per_second_1080p": 0.0072, "output_cost_per_second_2k": 0.0144, "output_cost_per_second_4k": 0.0288, "source": "https://fal.ai/models/fal-ai/bytedance-upscaler/upscale/video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/emu-3.5-image/edit-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://fal.ai/models/fal-ai/emu-3.5-image/edit-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/emu-3.5-image/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default 720p resolution; 480p is $0.15 per image and has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.3, "source": "https://fal.ai/models/fal-ai/emu-3.5-image/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.07, "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v2.5-turbo/pro/text-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.07, "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/pro/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/kling-video/v2.5-turbo/standard/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.042, "source": "https://fal.ai/models/fal-ai/kling-video/v2.5-turbo/standard/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/hailuo-02/standard/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 768P rate; 512P is roughly $0.017 per second and has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.045, "output_cost_per_second_768p": 0.045, "source": "https://fal.ai/models/fal-ai/minimax/hailuo-02/standard/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/minimax/image-01": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://fal.ai/models/fal-ai/minimax/image-01", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/object-removal": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.024, "source": "https://fal.ai/models/fal-ai/object-removal", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/object-removal/bbox": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.024, "source": "https://fal.ai/models/fal-ai/object-removal/bbox", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/object-removal/mask": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default model best_quality; low_quality $0.006, medium_quality $0.012 and high_quality $0.018 per image have no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.024, "source": "https://fal.ai/models/fal-ai/object-removal/mask", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/recraft/v3/image-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default realistic_image style; vector styles are $0.08 per image and have no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/fal-ai/recraft/v3/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/scail-2": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.2, "source": "https://fal.ai/models/fal-ai/scail-2", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan-vace-apps/long-reframe": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution, converted from the page rate per 2 seconds ($0.08 per 2s at 720p, $0.04 per 2s at 480p); output_cost_per_second is the 720p rate because the default resolution is auto; 580p ($0.06 per 2s) has no catalog field, 240p and 360p are not priced on the page; seconds are rounded up to a multiple of 2"}, "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_480p": 0.02, "output_cost_per_second_720p": 0.04, "source": "https://fal.ai/models/fal-ai/wan-vace-apps/long-reframe", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-14b/animate/move": { "litellm_provider": "fal_ai", "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/move", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/wan/v2.2-14b/animate/replace": { "litellm_provider": "fal_ai", "metadata": {"comment":"per video second of output by resolution, where a video second is 16 frames; output_cost_per_second is the default resolution 480p rate; 580p is $0.06 per video second and has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.04, "output_cost_per_second_480p": 0.04, "output_cost_per_second_720p": 0.08, "source": "https://fal.ai/models/fal-ai/wan/v2.2-14b/animate/replace", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.2/edit": { "input_cost_per_token": 1.5e-06, "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, "mode": "video_generation", "output_cost_per_second": 0.0819, "output_cost_per_second_1080p": 0.1229, "output_cost_per_second_4k": 0.2457, "output_cost_per_second_720p": 0.0819, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/edit", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.2/extend": { "input_cost_per_token": 1.5e-06, "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, "mode": "video_generation", "output_cost_per_second": 0.0819, "output_cost_per_second_1080p": 0.1229, "output_cost_per_second_4k": 0.2457, "output_cost_per_second_720p": 0.0819, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/extend", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.2/image-to-video": { "input_cost_per_token": 1.5e-06, "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, "mode": "video_generation", "output_cost_per_second": 0.0819, "output_cost_per_second_1080p": 0.1229, "output_cost_per_second_4k": 0.2457, "output_cost_per_second_720p": 0.0819, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.2/reference-to-video": { "input_cost_per_token": 1.5e-06, "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, "mode": "video_generation", "output_cost_per_second": 0.0819, "output_cost_per_second_1080p": 0.1229, "output_cost_per_second_4k": 0.2457, "output_cost_per_second_720p": 0.0819, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/gemini-omni-flash/v1.2/text-to-video": { "input_cost_per_token": 1.5e-06, "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; 360p is $0.0273 per second and has no catalog field; input tokens (text, image, video) are billed at $1.50 per million"}, "mode": "video_generation", "output_cost_per_second": 0.0819, "output_cost_per_second_1080p": 0.1229, "output_cost_per_second_4k": 0.2457, "output_cost_per_second_720p": 0.0819, "source": "https://fal.ai/models/google/gemini-omni-flash/v1.2/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/google/virtual-try-on": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.075, "source": "https://fal.ai/models/google/virtual-try-on", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/ideogram/v4/tiling": { "litellm_provider": "fal_ai", "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03 and QUALITY is $0.10 per megapixel, no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.06, "output_cost_per_pixel": 5.7220458984375e-08, "source": "https://fal.ai/models/ideogram/v4/tiling", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/ideogram/v4/tiling/lora": { "litellm_provider": "fal_ai", "metadata": {"notes":"per megapixel at the default rendering_speed BALANCED; TURBO is $0.03375 and QUALITY is $0.1125 per megapixel, no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.0675, "output_cost_per_pixel": 6.437301635742188e-08, "source": "https://fal.ai/models/ideogram/v4/tiling/lora", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/kling/v4/flash/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video at 720p (the only resolution) with image references; with video references fal bills $0.063 per second on the output duration plus the greater of the input and output durations, which has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.094, "output_cost_per_second_720p": 0.094, "source": "https://fal.ai/models/kling/v4/flash/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/kling/v4/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution with image references; output_cost_per_second is the default resolution 1080p rate; with video references or video elements fal bills $0.094 (720p) or $0.141 (1080p) per second on the input plus output length, which has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.235, "output_cost_per_second_1080p": 0.235, "output_cost_per_second_720p": 0.157, "source": "https://fal.ai/models/kling/v4/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/luma/agent/ray/v3.2/reframe": { "litellm_provider": "fal_ai", "metadata": {"comment":"per started source second by resolution; output_cost_per_second is the default resolution 540p rate ($0.06), which has no tier field"}, "mode": "video_generation", "output_cost_per_second": 0.06, "output_cost_per_second_1080p": 0.36, "output_cost_per_second_720p": 0.12, "source": "https://fal.ai/models/luma/agent/ray/v3.2/reframe", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of requested output duration by resolution; output_cost_per_second is the default resolution 768P rate; the page states no promotion for this endpoint; reference tokens above the 4,096 included per request are $0.02 per 1,000 tokens and are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_1080p": 0.16, "output_cost_per_second_480p": 0.05, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/styles/16bit-pixel": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/styles/16bit-pixel", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/styles/hand-drawn": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/styles/hand-drawn", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/styles/low-poly": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/styles/low-poly", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/styles/retro-toon-70s": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/styles/retro-toon-70s", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/minimax/h3-max/styles/vhs": { "litellm_provider": "fal_ai", "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_768p": 0.08, "source": "https://fal.ai/models/minimax/h3-max/styles/vhs", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/mirelo-ai/sfx2.0/video-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated audio per sample; promotional 33% off rate through 2026-12-13 per the page; the standard rate of $0.015 per second applies from 2026-12-14 (ruling fal-ai-promotional-rates-apply-until-promotion-ends, 2026-11-10); mode and endpoint follow fal_ai/sonilo/v1.1/video-to-video-sound-effects"}, "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/mirelo-ai/sfx2.0/video-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/nvidia/cosmos-3-super/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image; the optional $0.02 per request prompt expansion surcharge is not modeled, and agentic generation bills every candidate image"}, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://fal.ai/models/nvidia/cosmos-3-super/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/recraft/v4/style/pro/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.1, "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/recraft/v4/style/pro/text-to-vector": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.12, "source": "https://fal.ai/models/recraft/v4/style/pro/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/recraft/v4/style/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://fal.ai/models/recraft/v4/style/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/recraft/v4/style/text-to-vector": { "litellm_provider": "fal_ai", "metadata": {"notes":"per generated image when a style_id is provided; the one-time $0.005 style creation surcharge when no style_id is given is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://fal.ai/models/recraft/v4/style/text-to-vector", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/vast/eden-live-14b-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.10) minimum per session is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.01, "source": "https://fal.ai/models/vast/eden-live-14b-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/vast/eden-live-5b-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of video generated in a live session; the 10 billable second ($0.035) minimum per session is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.0035, "source": "https://fal.ai/models/vast/eden-live-5b-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-image/edit": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.022, "source": "https://fal.ai/models/xai/grok-imagine-image/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/xai/grok-imagine-video/edit-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the default resolution is auto; the $0.01 per second of input video charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://fal.ai/models/xai/grok-imagine-video/edit-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/extend-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the 720p rate because the endpoint has no resolution field; the $0.01 per second of input video charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://fal.ai/models/xai/grok-imagine-video/extend-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.002 per request image input charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://fal.ai/models/xai/grok-imagine-video/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.002 per request image input charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://fal.ai/models/xai/grok-imagine-video/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate"}, "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_480p": 0.05, "output_cost_per_second_720p": 0.07, "source": "https://fal.ai/models/xai/grok-imagine-video/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/v1.5/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 720p rate; the $0.01 per reference image charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.14, "output_cost_per_second_1080p": 0.25, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/xai/grok-imagine-video/v1.5/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video by resolution; output_cost_per_second is the default resolution 480p rate; the $0.01 per reference image charge is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.08, "output_cost_per_second_720p": 0.14, "source": "https://fal.ai/models/xai/grok-imagine-video/v1.5/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "databricks/databricks-claude-fable-5-2": { "cache_creation_input_token_cost": 9.99999e-06, "cache_creation_input_token_cost_above_1hr": 1.599997e-05, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_token": 8.00002e-06, "input_dbu_cost_per_token": 0.000114286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": {"notes":"Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, "mode": "chat", "output_cost_per_token": 4.000003e-05, "output_dbu_cost_per_token": 0.000571429, "prompt_cache_min_tokens": 512.0, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true }, "databricks/system.ai.claude-fable-5-2": { "cache_creation_input_token_cost": 9.99999e-06, "cache_creation_input_token_cost_above_1hr": 1.599997e-05, "cache_read_input_token_cost": 1.9999e-07, "input_cost_per_token": 8.00002e-06, "input_dbu_cost_per_token": 0.000114286, "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, "metadata": {"notes":"Claude Fable 5.2 on Databricks is served through Unity Gateway with the model service name system.ai.claude-fable-5-2, hosted through Amazon Bedrock. Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."}, "mode": "chat", "output_cost_per_token": 4.000003e-05, "output_dbu_cost_per_token": 0.000571429, "prompt_cache_min_tokens": 512.0, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_anthropic_thinking_payload": true, "supports_assistant_prefill": false, "supports_forced_tool_use": false, "supports_function_calling": true, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "thinking_always_on": true }, "replicate/google/gemini-4-carbon": { "input_cost_per_token": 2e-06, "litellm_provider": "replicate", "max_input_tokens": 1048576, "max_output_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 1e-05, "output_cost_per_token": 1e-05, "source": "https://replicate.com/google/gemini-4-carbon", "supports_audio_input": true, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_video_input": true, "supports_vision": true }, "azure_ai/mistral-large-4-latest": { "deprecation_date": "2027-10-27", "deprecation_source": "https://management.azure.com/subscriptions/{subscriptionId}/providers/Microsoft.CognitiveServices/locations/eastus/models?api-version=2024-10-01", "input_cost_per_token": 7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.1e-06, "source": "https://docs.mistral.ai/models/mistral-large-4-0", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "fal_ai/fal-ai/recraft-20b": { "litellm_provider": "fal_ai", "metadata": {"notes":"per image at the default realistic_image style, from the fal pricing API; vector styles cost 2x and have no catalog field; the fal.ai page for this id redirects to fal-ai/recraft/v2/text-to-image, which rounds the rate to $0.022"}, "mode": "image_generation", "output_cost_per_image": 0.0219, "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/recraft-20b", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/stable-diffusion-v3-medium/image-to-image": { "litellm_provider": "fal_ai", "mode": "image_generation", "output_cost_per_image": 0.035, "source": "https://api.fal.ai/v1/models/pricing?endpoint_id=fal-ai/stable-diffusion-v3-medium/image-to-image", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/pixverse/lipsync": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of output video; when audio_url is not provided the text is spoken with TTS at $0.24 per 100 characters, which is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.04, "source": "https://fal.ai/models/fal-ai/pixverse/lipsync", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.6-cyber": { "cache_creation_input_token_cost": 2.109375e-05, "cache_read_input_token_cost": 1.6875e-06, "input_cost_per_token": 1.6875e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00010125, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": false, "supports_xhigh_reasoning_effort": true, "use_openai_responses_path": true }, "fal_ai/fal-ai/kling-video/v2.6/pro/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video with the default generate_audio=true ($0.14); videos without audio are $0.07 per second and videos with audio and voice control are $0.168 per second, which have no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.14, "source": "https://fal.ai/models/fal-ai/kling-video/v2.6/pro/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/vidu/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/vidu/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/vidu/start-end-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.20 per video"}, "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/vidu/start-end-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/vidu/reference-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the fixed 4s clip price of $0.40 per video"}, "mode": "video_generation", "output_cost_per_second": 0.1, "source": "https://fal.ai/models/fal-ai/vidu/reference-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/luma/agent/ray/v3.2/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the 5s clip prices by resolution ($0.15 at 540p, $0.30 at 720p, $1.20 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR ($0.60 at 720p, $2.40 at 1080p per 5s) and HDR+EXR ($0.90, $3.60) are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.24, "output_cost_per_second_720p": 0.06, "source": "https://fal.ai/models/luma/agent/ray/v3.2/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/luma/agent/ray/v3.2/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.50/$1.00 at 540p, $1.00/$2.00 at 720p, $2.00/$4.00 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.4, "output_cost_per_second_720p": 0.2, "source": "https://fal.ai/models/luma/agent/ray/v3.2/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/luma/agent/ray/v3.2/video-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the 5s and 10s clip prices by resolution ($0.72/$1.44 at 540p, $1.08/$2.16 at 720p, $2.16/$4.32 at 1080p); output_cost_per_second is the default resolution 540p rate, which has no tier field; HDR and HDR+EXR prices are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.144, "output_cost_per_second_1080p": 0.432, "output_cost_per_second_720p": 0.216, "source": "https://fal.ai/models/luma/agent/ray/v3.2/video-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/pixverse/v6/max/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.099, "output_cost_per_second_1080p": 0.198, "output_cost_per_second_720p": 0.099, "source": "https://fal.ai/models/pixverse/v6/max/text-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ] }, "fal_ai/pixverse/v6/max/image-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution without audio (the default generate_audio_switch=false); output_cost_per_second is the default resolution 720p rate; 360p $0.054 and 540p $0.081 have no catalog field; with audio the rates are $0.081/$0.099/$0.135/$0.252 per second, which is not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.099, "output_cost_per_second_1080p": 0.198, "output_cost_per_second_720p": 0.099, "source": "https://fal.ai/models/pixverse/v6/max/image-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "fal_ai/fal-ai/flux-2-pro": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/flux-2-pro", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-pro/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/flux-2-pro/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-pro/outpaint": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.03 for the first output megapixel plus $0.015 per additional input or output megapixel, rounded up, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/flux-2-pro/outpaint", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-2-max": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.07, "source": "https://fal.ai/models/fal-ai/flux-2-max", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/fal-ai/flux-2-max/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the default 1 MP output; fal bills $0.07 for the first processed megapixel plus $0.03 per additional megapixel, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.07, "source": "https://fal.ai/models/fal-ai/flux-2-max/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/v1/erase": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image for the first generated megapixel; fal bills $0.004 for each subsequent generated megapixel and $0.004 per reference megapixel with a 3 MP minimum, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.03, "source": "https://fal.ai/models/fal-ai/flux-pro/v1/erase", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/smart-resize": { "litellm_provider": "fal_ai", "metadata": {"comment":"per single-image request at standard resolution: $0.15 per output image plus the $0.05 minimum vision analysis fee per request; additional output images in one request ($0.15 each) and 4K outputs (charged double) are not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.2, "source": "https://fal.ai/models/fal-ai/smart-resize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bytedance/seedream/v5/pro/layerize": { "litellm_provider": "fal_ai", "metadata": {"comment":"per generated layer for total pixel area under 1536x1536; layers for a base image over 1536x1536 are $0.0675 each, which has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.03375, "source": "https://fal.ai/models/bytedance/seedream/v5/pro/layerize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/luma/agent/uni-1/v1/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per edit with one source image ($0.042 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.045, "source": "https://fal.ai/models/luma/agent/uni-1/v1/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/luma/agent/uni-1/v1/max/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per edit with one source image ($0.102 per edit plus $0.003 per reference or source image); each additional reference image adds $0.003, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.105, "source": "https://fal.ai/models/luma/agent/uni-1/v1/max/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "databricks/databricks-gemini-4-carbon": { "cache_creation_input_token_cost": 2e-06, "cache_read_input_token_cost": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "databricks/system.ai.gemini-4-carbon": { "cache_creation_input_token_cost": 2e-06, "cache_read_input_token_cost": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "metadata": {"notes":"Gemini 4 Carbon on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-carbon on a global endpoint. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Carbon (listed there through November 30, 2026), no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."}, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "runwayml/kling2.5_turbo_pro": { "litellm_provider": "runwayml", "metadata": {"comment":"12 credits per second @ $0.01 per credit = $0.12 per second"}, "mode": "video_generation", "output_cost_per_second": 0.12, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/kling3.0_standard": { "litellm_provider": "runwayml", "metadata": {"comment":"13 credits per second with audio, 9 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, "mode": "video_generation", "output_cost_per_second": 0.13, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/kling3.0_pro": { "litellm_provider": "runwayml", "metadata": {"comment":"17 credits per second with audio, 12 without @ $0.01 per credit; priced at the with-audio rate (audio defaults to true)"}, "mode": "video_generation", "output_cost_per_second": 0.17, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/kling3.0_4k": { "litellm_provider": "runwayml", "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second, with or without audio"}, "mode": "video_generation", "output_cost_per_second": 0.43, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/klingO3_standard": { "litellm_provider": "runwayml", "metadata": {"comment":"13 credits per second @ $0.01 per credit = $0.13 per second; video-to-video is billed per second of the input video, not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.13, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/klingO3_pro": { "litellm_provider": "runwayml", "metadata": {"comment":"17 credits per second @ $0.01 per credit = $0.17 per second; video-to-video is billed per second of the input video, not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.17, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/klingO3_4k": { "litellm_provider": "runwayml", "metadata": {"comment":"43 credits per second @ $0.01 per credit = $0.43 per second; video-to-video is billed per second of the input video, not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.43, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/kling_4_flash": { "litellm_provider": "runwayml", "metadata": {"comment":"9.4 credits per second (720p) without input video @ $0.01 per credit = $0.094 per second; the with-input-video rate (6.3 credits per output second plus 6.3 per second of the greater of input and output duration), rounding up to the next credit and the 29 credit minimum are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.094, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/wan3": { "litellm_provider": "runwayml", "metadata": {"comment":"5/10/20 credits per second at 480p/720p/1080p @ $0.01 per credit"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.2, "output_cost_per_second_480p": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/wan3_prime": { "litellm_provider": "runwayml", "metadata": {"comment":"6.8/14/28 credits per second at 480p/720p/1080p @ $0.01 per credit"}, "mode": "video_generation", "output_cost_per_second": 0.14, "output_cost_per_second_1080p": 0.28, "output_cost_per_second_480p": 0.068, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/grok_imagine_1_5": { "litellm_provider": "runwayml", "metadata": {"comment":"10/16/29 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit per image or audio reference not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.16, "output_cost_per_second_1080p": 0.29, "output_cost_per_second_480p": 0.1, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/grok_imagine_1_5_lite": { "litellm_provider": "runwayml", "metadata": {"comment":"2/3/14 credits per second at 480p/720p/1080p @ $0.01 per credit; 1 credit for an image-to-video start frame not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.03, "output_cost_per_second_1080p": 0.14, "output_cost_per_second_480p": 0.02, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/h3_max": { "litellm_provider": "runwayml", "metadata": {"comment":"8 credits per second at 768p, 5 at 480p @ $0.01 per credit"}, "mode": "video_generation", "output_cost_per_second": 0.08, "output_cost_per_second_480p": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/happyhorse_1_0": { "litellm_provider": "runwayml", "metadata": {"comment":"15 credits per second at 720p, 30 at 1080p @ $0.01 per credit"}, "mode": "video_generation", "output_cost_per_second": 0.15, "output_cost_per_second_1080p": 0.3, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] }, "runwayml/gemini_omni_flash_1.2": { "litellm_provider": "runwayml", "metadata": {"comment":"7/10/21 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (2 credits per second), 1 credit per reference image or keyframe, 1 credit per second of input video and the 6 credit minimum per request are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.07, "output_cost_per_second_1080p": 0.1, "output_cost_per_second_4k": 0.21, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/gemini_omni_flash_1.1": { "litellm_provider": "runwayml", "metadata": {"comment":"10/15/30 credits per second at 720p/1080p/4K @ $0.01 per credit; the 360p rate (3.4 credits per second), 1 credit per reference image and 1 credit per second of input video are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.15, "output_cost_per_second_4k": 0.3, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "runwayml/muse_image": { "litellm_provider": "runwayml", "metadata": {"comment":"1 credit per image (any resolution) @ $0.01 per credit = $0.01 per image"}, "mode": "image_generation", "output_cost_per_image": 0.01, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/seedream5_lite": { "litellm_provider": "runwayml", "metadata": {"comment":"4 credits per image (any resolution) @ $0.01 per credit = $0.04 per image"}, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/seedream5_flash": { "litellm_provider": "runwayml", "metadata": {"comment":"2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image"}, "mode": "image_generation", "output_cost_per_image": 0.02, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/gemini_image3.1_flash_lite": { "litellm_provider": "runwayml", "metadata": {"comment":"4 credits per 1K image @ $0.01 per credit = $0.04 per image"}, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/bria_fibo_edit_1_5": { "litellm_provider": "runwayml", "metadata": {"comment":"5 credits per image @ $0.01 per credit = $0.05 per image"}, "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/gemini_2.5_flash": { "litellm_provider": "runwayml", "metadata": {"comment":"5 credits per image (any resolution) @ $0.01 per credit = $0.05 per image"}, "mode": "image_generation", "output_cost_per_image": 0.05, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "image" ] }, "runwayml/eleven_v3": { "input_cost_per_character": 0.0002, "litellm_provider": "runwayml", "metadata": {"comment":"1 credit per 50 characters @ $0.01 per credit = $0.0002 per character; 1 credit minimum not modeled"}, "mode": "audio_speech", "source": "https://docs.dev.runwayml.com/guides/pricing/" }, "runwayml/eleven_v4": { "input_cost_per_character": 5e-05, "litellm_provider": "runwayml", "metadata": {"comment":"5 credits per 1,000 characters @ $0.01 per credit = $0.00005 per character; 1 credit minimum not modeled"}, "mode": "audio_speech", "source": "https://docs.dev.runwayml.com/guides/pricing/" }, "gemini/gemini-decision-1": { "input_cost_per_token": 1e-07, "litellm_provider": "gemini", "max_input_tokens": 262144, "mode": "decisions", "output_cost_per_token": 0.0, "rpm": 1500, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/decisions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supports_audio_input": true, "supports_audio_output": false, "supports_computer_use": false, "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_tool_choice": false, "supports_url_context": false, "supports_video_input": true, "supports_vision": true, "supports_web_search": false, "tpm": 1000000 }, "runwayml/kling_4": { "litellm_provider": "runwayml", "metadata": {"comment":"Promo rate through 2026-11-30 UTC: 12.56 credits per second (720p) and 18.8 (1080p) without input video @ $0.01 per credit = $0.1256 and $0.188 per second; list rate 15.7/23.5 credits per second applies from 2026-12-01 UTC (ruling runwayml-kling-4-promo-rate). The with-input-video rate (7.52/11.28 credits per output second plus the same per second of the greater of input and output duration) and rounding up to the next credit are not modeled"}, "mode": "video_generation", "output_cost_per_second": 0.1256, "output_cost_per_second_1080p": 0.188, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "video" ] }, "fal_ai/bytedance/seedream/v5.5/text-to-image": { "litellm_provider": "fal_ai", "metadata": {"comment":"per image at the default image_size auto_2K; 1K and 1.5K outputs are $0.03 and custom dimensions are $0.03 up to and including 2,610,000 pixels and $0.0405 above, so 1.5K has no catalog field"}, "mode": "image_generation", "output_cost_per_image": 0.0405, "output_cost_per_image_1K": 0.03, "output_cost_per_image_2K": 0.0405, "source": "https://fal.ai/models/bytedance/seedream/v5.5/text-to-image", "supported_endpoints": [ "/v1/images/generations" ] }, "fal_ai/bytedance/seedream/v5.5/edit": { "litellm_provider": "fal_ai", "metadata": {"comment":"per output image with one input image at the default image_size auto_2K ($0.0405 per output plus $0.012 per input image per output); 1K and 1.5K outputs are $0.03 plus the input fee and each additional input image adds $0.012 per output, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.0525, "output_cost_per_image_1K": 0.042, "output_cost_per_image_2K": 0.0525, "source": "https://fal.ai/models/bytedance/seedream/v5.5/edit", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/bytedance/seedream/v5.5/layerize": { "litellm_provider": "fal_ai", "metadata": {"comment":"per returned output image (the base image and every separated layer) at the default image_size auto, where a base image above 2,610,000 pixels bills $0.0405 per output and one at or under that area bills $0.03; fal also bills $0.012 for the input image once per request and returns up to max_images (default 30) outputs, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.0405, "output_cost_per_image_1K": 0.03, "output_cost_per_image_2K": 0.0405, "source": "https://fal.ai/models/bytedance/seedream/v5.5/layerize", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/flux-pro/v1/vto": { "litellm_provider": "fal_ai", "metadata": {"comment":"per try-on with one 1 MP input image and one 1 MP output ($0.0375 for the first input megapixel plus $0.005 per output megapixel); fal bills $0.005 per additional input megapixel and rounds each input image and the output up to whole megapixels separately, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.0425, "source": "https://fal.ai/models/fal-ai/flux-pro/v1/vto", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/patina/material": { "litellm_provider": "fal_ai", "metadata": {"comment":"per request at the schema defaults (1024x1024 square_hd, all 5 maps, no upscaling), the page's own example; fal bills $0.01 per request plus $0.02 per megapixel plus $0.01 per megapixel per map type, and 2x or 4x upscaling adds $0.004 or $0.016 per pre-upscaling megapixel per map, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.08, "source": "https://fal.ai/models/fal-ai/patina/material", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/patina/material/extract": { "litellm_provider": "fal_ai", "metadata": {"comment":"per request at the schema defaults (1024x1024 input, all 5 maps, no upscaling), the page's own example; fal bills $0.10 per request plus $0.02 per megapixel plus $0.01 per megapixel per map type, and 2x or 4x upscaling adds $0.004 or $0.016 per pre-upscaling megapixel per map, which is not modeled"}, "mode": "image_generation", "output_cost_per_image": 0.17, "source": "https://fal.ai/models/fal-ai/patina/material/extract", "supported_endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "supports_vision": true }, "fal_ai/fal-ai/vidu/template-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second derived from the $0.20 Standard template price over the fixed 4s clip the sibling vidu endpoints state; Premium templates are $0.30 and Advanced templates $0.50 per video, which has no catalog field"}, "mode": "video_generation", "output_cost_per_second": 0.05, "source": "https://fal.ai/models/fal-ai/vidu/template-to-video", "supported_endpoints": [ "/v1/videos" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "video" ] } }