Skip to content

One live console to monitor Claude Code and Codex agents across machines, track context and spend, and unblock sessions that need you.

3.3 MB
Raw Blame
{
    "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/"
    },
    "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"
        }
    },
    "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",
        "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,
        "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,
        "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,
        "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,
        "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,
        "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-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",
        "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,
        "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,
        "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,
        "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-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,
        "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",
        "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,
        "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,
        "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",
        "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,
        "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-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-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-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-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-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/<deployment-name> 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": 2.5e-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/azure-openai/",
        "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_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://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure"
    },
    "azure/gpt-realtime-2025-08-28": {
        "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_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://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure"
    },
    "azure/gpt-realtime-1.5-2026-02-23": {
        "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": {
        "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_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://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
        "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-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-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-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-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": "2026-12-02",
        "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://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/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-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": 2.5e-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/azure-openai/",
        "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
        "supported_modalities": [
            "text",
            "image"
        ],
        "supported_output_modalities": [
            "text"
        ],
        "supports_function_calling": true,
        "supports_pdf_input": false,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_vision": true
    },
    "azure_ai/FW-MiniMax-M2.5": {
        "deprecation_date": "2027-07-01",
        "cache_read_input_token_cost": 3.3e-08,
        "input_cost_per_token": 3.3e-07,
        "litellm_provider": "azure_ai",
        "max_input_tokens": 1000000,
        "max_output_tokens": 1000000,
        "mode": "chat",
        "output_cost_per_token": 1.32e-06,
        "source": "https://prices.azure.com/api/retail/prices?$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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
        "supported_modalities": [
            "text",
            "image"
        ],
        "supported_output_modalities": [
            "text"
        ],
        "supports_function_calling": true,
        "supports_pdf_input": false,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_vision": true
    },
    "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": {
        "cache_read_input_token_cost": 1e-08,
        "input_cost_per_token": 6e-08,
        "litellm_provider": "azure_ai",
        "max_input_tokens": 262144,
        "mode": "chat",
        "output_cost_per_token": 2.2e-07,
        "source": "https://prices.azure.com/api/retail/prices?$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": "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": "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-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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
        "supports_function_calling": true,
        "supports_pdf_input": false,
        "supports_reasoning": true,
        "supports_tool_choice": true,
        "cache_read_input_token_cost": 2.8e-08,
        "supports_prompt_caching": true
    },
    "azure_ai/DeepSeek-V4-Flash-0731": {
        "cache_read_input_token_cost": 1.4e-08,
        "deprecation_date": "2026-12-03",
        "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
        "input_cost_per_token": 4.4e-07,
        "litellm_provider": "azure_ai",
        "max_input_tokens": 1000000,
        "max_output_tokens": 384000,
        "mode": "chat",
        "output_cost_per_token": 1.32e-06,
        "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
        "supports_function_calling": true,
        "supports_pdf_input": false,
        "supports_prompt_caching": true,
        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "azure_ai/embed-v-4-0": {
        "deprecation_date": "2027-06-01",
        "deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
        "successor_model": "azure_ai/Cohere-Embed-V5-Fast",
        "input_cost_per_token": 1.2e-07,
        "litellm_provider": "azure_ai",
        "max_input_tokens": 128000,
        "mode": "embedding",
        "output_cost_per_token": 0.0,
        "output_vector_size": 3072,
        "source": "https://prices.azure.com/api/retail/prices?$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": 0.0032,
        "litellm_provider": "azure_ai",
        "max_input_tokens": 8192,
        "max_output_tokens": 8192,
        "mode": "chat",
        "output_cost_per_token": 0.00971,
        "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,
        "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,
        "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": "2027-04-08",
        "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md",
        "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": "2027-04-08",
        "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md",
        "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": "2027-04-08",
        "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md",
        "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": "2027-04-08",
        "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md",
        "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": "2027-03-30",
        "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": 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": "2027-03-30",
        "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": 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-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-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-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": {
        "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/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/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/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/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
    },
    "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/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/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/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/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": 200000,
        "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-<voice>-<lang>), 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-<voice>-<lang>), 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": 1.9e-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": 8e-08,
        "output_cost_per_token": 2e-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"
        }
    },
    "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",
        "sup

File truncated at 1 MB.