From f957beaa3758fe5acd9581cdb7514e73cf8b09be Mon Sep 17 00:00:00 2001 From: Ari Webb Date: Wed, 4 Feb 2026 12:22:32 -0800 Subject: [PATCH] fix: add new json (#9280) --- .../model_prices_and_context_window.json | 1173 +++++++++++++++-- 1 file changed, 1069 insertions(+), 104 deletions(-) diff --git a/letta/model_specs/model_prices_and_context_window.json b/letta/model_specs/model_prices_and_context_window.json index e4081310..81e4729f 100644 --- a/letta/model_specs/model_prices_and_context_window.json +++ b/letta/model_specs/model_prices_and_context_window.json @@ -330,6 +330,25 @@ "supports_video_input": true, "supports_vision": true }, + "amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 2.1875e-6, + "input_cost_per_image_token": 2.1875e-6, + "input_cost_per_audio_token": 2.1875e-6, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.75e-5, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, "apac.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, @@ -347,6 +366,25 @@ "supports_video_input": true, "supports_vision": true }, + "apac.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 2.1875e-6, + "input_cost_per_image_token": 2.1875e-6, + "input_cost_per_audio_token": 2.1875e-6, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.75e-5, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, "eu.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, @@ -364,6 +402,25 @@ "supports_video_input": true, "supports_vision": true }, + "eu.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 2.1875e-6, + "input_cost_per_image_token": 2.1875e-6, + "input_cost_per_audio_token": 2.1875e-6, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.75e-5, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-8, "input_cost_per_token": 3.3e-7, @@ -381,6 +438,25 @@ "supports_video_input": true, "supports_vision": true }, + "us.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 2.1875e-6, + "input_cost_per_image_token": 2.1875e-6, + "input_cost_per_audio_token": 2.1875e-6, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.75e-5, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_video_input": true, + "supports_vision": true + }, "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, @@ -644,12 +720,13 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 346, + "supports_native_streaming": true }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-6, "litellm_provider": "bedrock", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", @@ -658,14 +735,22 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_above_200k_tokens": 6e-6, + "output_cost_per_token_above_200k_tokens": 3e-5, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-6, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "cache_creation_input_token_cost_above_1hr": 7.5e-6, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-5, + "cache_creation_input_token_cost": 3.75e-6, + "cache_read_input_token_cost": 3e-7 }, "anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-6, "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 3e-6, "litellm_provider": "bedrock", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -677,7 +762,13 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "input_cost_per_token_above_200k_tokens": 6e-6, + "output_cost_per_token_above_200k_tokens": 3e-5, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-6, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "cache_creation_input_token_cost_above_1hr": 7.5e-6, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.5e-5 }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-6, @@ -1281,6 +1372,9 @@ "supports_function_calling": true }, "azure_ai/claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-6, + "cache_creation_input_token_cost_above_1hr": 2e-6, + "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 1e-6, "litellm_provider": "azure_ai", "max_input_tokens": 200000, @@ -1299,6 +1393,9 @@ "supports_vision": true }, "azure_ai/claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25e-6, + "cache_creation_input_token_cost_above_1hr": 1e-5, + "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 5e-6, "litellm_provider": "azure_ai", "max_input_tokens": 200000, @@ -1317,6 +1414,9 @@ "supports_vision": true }, "azure_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-5, + "cache_creation_input_token_cost_above_1hr": 3e-5, + "cache_read_input_token_cost": 1.5e-6, "input_cost_per_token": 1.5e-5, "litellm_provider": "azure_ai", "max_input_tokens": 200000, @@ -1335,6 +1435,9 @@ "supports_vision": true }, "azure_ai/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-6, + "cache_creation_input_token_cost_above_1hr": 6e-6, + "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 3e-6, "litellm_provider": "azure_ai", "max_input_tokens": 200000, @@ -1391,6 +1494,14 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "azure_ai/model_router": { + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 0, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", + "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" + }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 1.375e-6, @@ -2861,7 +2972,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, + "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-chat-latest": { @@ -2888,7 +2999,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, + "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-5-codex": { @@ -3281,12 +3392,12 @@ "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 1.75e-6, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", "output_cost_per_token": 1.4e-5, - "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_endpoints": ["/v1/responses"], "supported_modalities": ["text", "image"], "supported_output_modalities": ["text"], "supports_function_calling": true, @@ -6075,13 +6186,13 @@ "supports_tool_choice": true }, "cerebras/gpt-oss-120b": { - "input_cost_per_token": 2.5e-7, + "input_cost_per_token": 3.5e-7, "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6.9e-7, + "output_cost_per_token": 7.5e-7, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -6099,6 +6210,7 @@ "output_cost_per_token": 8e-7, "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true }, "cerebras/zai-glm-4.6": { @@ -9050,6 +9162,7 @@ "supports_tool_choice": true }, "deepinfra/google/gemini-2.0-flash-001": { + "deprecation_date": "2026-03-31", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -9493,6 +9606,48 @@ "mode": "completion", "output_cost_per_token": 5e-7 }, + "deepseek-v3-2-251201": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_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, + "max_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, + "max_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", @@ -11303,6 +11458,7 @@ }, "gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", @@ -11334,7 +11490,7 @@ }, "gemini-2.0-flash-001": { "cache_read_input_token_cost": 3.75e-8, - "deprecation_date": "2026-02-05", + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 1e-6, "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-language-models", @@ -11404,6 +11560,7 @@ }, "gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "vertex_ai-language-models", @@ -11432,7 +11589,7 @@ }, "gemini-2.0-flash-lite-001": { "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-02-25", + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "vertex_ai-language-models", @@ -11793,9 +11950,37 @@ "supports_vision": true, "supports_web_search": true }, + "deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-6, + "input_cost_per_token_batches": 1e-6, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-5, + "output_cost_per_token_batches": 6e-6, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini-2.5-flash-lite": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, @@ -11832,7 +12017,7 @@ "supports_web_search": true }, "gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", @@ -12166,7 +12351,8 @@ "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_native_streaming": true }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-7, @@ -12207,7 +12393,8 @@ "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_native_streaming": true }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-8, @@ -12243,7 +12430,8 @@ "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_native_streaming": true }, "gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 1.25e-7, @@ -12431,6 +12619,59 @@ "supports_vision": true, "supports_web_search": true }, + "gemini-robotics-er-1.5-preview": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 3e-7, + "input_cost_per_audio_token": 1e-6, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 2.5e-6, + "output_cost_per_reasoning_token": 2.5e-6, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true + }, + "gemini/gemini-robotics-er-1.5-preview": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 3e-7, + "input_cost_per_audio_token": 1e-6, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 2.5e-6, + "output_cost_per_reasoning_token": 2.5e-6, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-6, "input_cost_per_token_above_200k_tokens": 2.5e-6, @@ -12879,6 +13120,7 @@ }, "gemini/gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", @@ -12911,6 +13153,7 @@ }, "gemini/gemini-2.0-flash-001": { "cache_read_input_token_cost": 2.5e-8, + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", @@ -12982,6 +13225,7 @@ }, "gemini/gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7.5e-8, "input_cost_per_token": 7.5e-8, "litellm_provider": "gemini", @@ -13390,9 +13634,39 @@ "supports_vision": true, "supports_web_search": true }, + "gemini/deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-6, + "input_cost_per_token_batches": 1e-6, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-5, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 6e-6, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini/gemini-2.5-flash-lite": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, @@ -13431,7 +13705,7 @@ "tpm": 250000 }, "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost": 1e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", @@ -13873,6 +14147,7 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, + "supports_native_streaming": true, "tpm": 800000 }, "gemini-3-flash-preview": { @@ -13911,7 +14186,8 @@ "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_native_streaming": true }, "gemini/gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 0.0, @@ -14752,6 +15028,181 @@ "output_cost_per_token": 0.0, "output_vector_size": 2560 }, + "gmi/anthropic/claude-opus-4.5": { + "input_cost_per_token": 5e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.5e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/anthropic/claude-sonnet-4.5": { + "input_cost_per_token": 3e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/anthropic/claude-sonnet-4": { + "input_cost_per_token": 3e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/anthropic/claude-opus-4": { + "input_cost_per_token": 1.5e-5, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/openai/gpt-5.2": { + "input_cost_per_token": 1.75e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.4e-5, + "supports_function_calling": true + }, + "gmi/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1e-5, + "supports_function_calling": true + }, + "gmi/openai/gpt-5": { + "input_cost_per_token": 1.25e-6, + "litellm_provider": "gmi", + "max_input_tokens": 409600, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1e-5, + "supports_function_calling": true + }, + "gmi/openai/gpt-4o": { + "input_cost_per_token": 2.5e-6, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "gmi", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/deepseek-ai/DeepSeek-V3.2": { + "input_cost_per_token": 2.8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_function_calling": true + }, + "gmi/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 2.8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "supports_function_calling": true + }, + "gmi/google/gemini-3-pro-preview": { + "input_cost_per_token": 2e-6, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-5, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/google/gemini-3-flash-preview": { + "input_cost_per_token": 5e-7, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-6, + "supports_function_calling": true, + "supports_vision": true + }, + "gmi/moonshotai/Kimi-K2-Thinking": { + "input_cost_per_token": 8e-7, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-6 + }, + "gmi/MiniMaxAI/MiniMax-M2.1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "gmi", + "max_input_tokens": 196608, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-6 + }, + "gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8": { + "input_cost_per_token": 3e-7, + "litellm_provider": "gmi", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-6, + "supports_vision": true + }, + "gmi/zai-org/GLM-4.7-FP8": { + "input_cost_per_token": 4e-7, + "litellm_provider": "gmi", + "max_input_tokens": 202752, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-6 + }, "google.gemma-3-12b-it": { "input_cost_per_token": 9e-8, "litellm_provider": "bedrock_converse", @@ -15491,14 +15942,14 @@ "supports_vision": true }, "gpt-4o-audio-preview": { - "input_cost_per_audio_token": 0.0001, + "input_cost_per_audio_token": 4e-5, "input_cost_per_token": 2.5e-6, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.0002, + "output_cost_per_audio_token": 8e-5, "output_cost_per_token": 1e-5, "supports_audio_input": true, "supports_audio_output": true, @@ -15508,14 +15959,14 @@ "supports_tool_choice": true }, "gpt-4o-audio-preview-2024-10-01": { - "input_cost_per_audio_token": 0.0001, + "input_cost_per_audio_token": 4e-5, "input_cost_per_token": 2.5e-6, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.0002, + "output_cost_per_audio_token": 8e-5, "output_cost_per_token": 1e-5, "supports_audio_input": true, "supports_audio_output": true, @@ -15558,6 +16009,156 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-audio": { + "input_cost_per_audio_token": 3.2e-5, + "input_cost_per_token": 2.5e-6, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-5, + "output_cost_per_token": 1e-5, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gpt-audio-2025-08-28": { + "input_cost_per_audio_token": 3.2e-5, + "input_cost_per_token": 2.5e-6, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-5, + "output_cost_per_token": 1e-5, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gpt-audio-mini": { + "input_cost_per_audio_token": 1e-5, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-5, + "output_cost_per_token": 2.4e-6, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gpt-audio-mini-2025-10-06": { + "input_cost_per_audio_token": 1e-5, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-5, + "output_cost_per_token": 2.4e-6, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gpt-audio-mini-2025-12-15": { + "input_cost_per_audio_token": 1e-5, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-5, + "output_cost_per_token": 2.4e-6, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-8, "cache_read_input_token_cost_priority": 1.25e-7, @@ -16632,7 +17233,7 @@ "input_cost_per_token": 1.75e-6, "input_cost_per_token_priority": 3.5e-6, "litellm_provider": "openai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -18392,6 +18993,7 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 @@ -18406,6 +19008,7 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 1000000, "max_output_tokens": 8192 @@ -18420,6 +19023,7 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_system_messages": true, "max_input_tokens": 200000, "max_output_tokens": 8192 @@ -19111,6 +19715,20 @@ "supports_tool_choice": true, "supports_web_search": true }, + "moonshot/kimi-k2.5": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "moonshot", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-6, + "source": "https://platform.moonshot.ai/docs/pricing/chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "moonshot/kimi-latest": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 2e-6, @@ -20925,6 +21543,7 @@ "supports_tool_choice": true }, "openrouter/google/gemini-2.0-flash-001": { + "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", @@ -21207,7 +21826,7 @@ "mode": "chat", "output_cost_per_token": 1.02e-6, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, @@ -21343,6 +21962,20 @@ "output_cost_per_token": 6.5e-7, "supports_tool_choice": true }, + "openrouter/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-6, + "source": "https://openrouter.ai/moonshotai/kimi-k2.5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "openrouter/nousresearch/nous-hermes-llama2-13b": { "input_cost_per_token": 2e-7, "litellm_provider": "openrouter", @@ -21546,11 +22179,12 @@ "cache_read_input_token_cost": 1.75e-7, "input_cost_per_token": 1.75e-6, "litellm_provider": "openrouter", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.4e-5, + "supported_endpoints": ["/v1/responses"], "supported_modalities": ["text", "image"], "supported_output_modalities": ["text"], "supports_reasoning": true, @@ -21869,6 +22503,7 @@ "output_cost_per_token": 1.75e-6, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, @@ -21882,9 +22517,76 @@ "output_cost_per_token": 1.9e-6, "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/xiaomi/mimo-v2-flash": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 2.9e-7, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": false + }, + "openrouter/z-ai/glm-4.7": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 1.5e-6, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_assistant_prefill": true + }, + "openrouter/z-ai/glm-4.7-flash": { + "input_cost_per_token": 7e-8, + "output_cost_per_token": 4e-7, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false + }, + "openrouter/minimax/minimax-m2.1": { + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 1.2e-6, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 204000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_computer_use": false + }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-7, "litellm_provider": "ovhcloud", @@ -24464,6 +25166,34 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "together_ai/zai-org/GLM-4.7": { + "input_cost_per_token": 4.5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 2e-6, + "source": "https://www.together.ai/models/glm-4-7", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2.5": { + "input_cost_per_token": 5e-7, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.8e-6, + "source": "https://www.together.ai/models/kimi-k2-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, "together_ai/moonshotai/Kimi-K2-Instruct-0905": { "input_cost_per_token": 1e-6, "litellm_provider": "together_ai", @@ -25156,7 +25886,9 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3e-7 + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/alibaba/qwen3-coder": { "input_cost_per_token": 4e-7, @@ -25165,7 +25897,9 @@ "max_output_tokens": 66536, "max_tokens": 66536, "mode": "chat", - "output_cost_per_token": 1.6e-6 + "output_cost_per_token": 1.6e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/amazon/nova-lite": { "input_cost_per_token": 6e-8, @@ -25174,7 +25908,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.4e-7 + "output_cost_per_token": 2.4e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_response_schema": true }, "vercel_ai_gateway/amazon/nova-micro": { "input_cost_per_token": 3.5e-8, @@ -25183,7 +25920,9 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.4e-7 + "output_cost_per_token": 1.4e-7, + "supports_function_calling": true, + "supports_response_schema": true }, "vercel_ai_gateway/amazon/nova-pro": { "input_cost_per_token": 8e-7, @@ -25192,7 +25931,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.2e-6 + "output_cost_per_token": 3.2e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_response_schema": true }, "vercel_ai_gateway/amazon/titan-embed-text-v2": { "input_cost_per_token": 2e-8, @@ -25212,7 +25954,11 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.25e-6 + "output_cost_per_token": 1.25e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3-opus": { "cache_creation_input_token_cost": 1.875e-5, @@ -25223,7 +25969,11 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 7.5e-5 + "output_cost_per_token": 7.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.5-haiku": { "cache_creation_input_token_cost": 1e-6, @@ -25234,7 +25984,11 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4e-6 + "output_cost_per_token": 4e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { "cache_creation_input_token_cost": 3.75e-6, @@ -25245,7 +25999,11 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { "cache_creation_input_token_cost": 3.75e-6, @@ -25256,7 +26014,11 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-4-opus": { "cache_creation_input_token_cost": 1.875e-5, @@ -25267,7 +26029,11 @@ "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 7.5e-5 + "output_cost_per_token": 7.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/anthropic/claude-4-sonnet": { "cache_creation_input_token_cost": 3.75e-6, @@ -25278,7 +26044,9 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/cohere/command-a": { "input_cost_per_token": 2.5e-6, @@ -25287,7 +26055,9 @@ "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/cohere/command-r": { "input_cost_per_token": 1.5e-7, @@ -25296,7 +26066,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 6e-7 + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/cohere/command-r-plus": { "input_cost_per_token": 2.5e-6, @@ -25305,7 +26077,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/cohere/embed-v4.0": { "input_cost_per_token": 1.2e-7, @@ -25323,7 +26097,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.19e-6 + "output_cost_per_token": 2.19e-6, + "supports_tool_choice": true }, "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 7.5e-7, @@ -25332,7 +26107,10 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 9.9e-7 + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/deepseek/deepseek-v3": { "input_cost_per_token": 9e-7, @@ -25341,25 +26119,36 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 9e-7 + "output_cost_per_token": 9e-7, + "supports_tool_choice": true }, "vercel_ai_gateway/google/gemini-2.0-flash": { + "deprecation_date": "2026-03-31", "input_cost_per_token": 1.5e-7, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-7 + "output_cost_per_token": 6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "deprecation_date": "2026-03-31", "input_cost_per_token": 7.5e-8, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7 + "output_cost_per_token": 3e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-7, @@ -25368,7 +26157,11 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.5e-6 + "output_cost_per_token": 2.5e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-2.5-pro": { "input_cost_per_token": 2.5e-6, @@ -25377,7 +26170,11 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-embedding-001": { "input_cost_per_token": 1.5e-7, @@ -25395,7 +26192,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 2e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/google/text-embedding-005": { "input_cost_per_token": 2.5e-8, @@ -25431,7 +26231,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.9e-7 + "output_cost_per_token": 7.9e-7, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3-8b": { "input_cost_per_token": 5e-8, @@ -25440,7 +26241,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8e-8 + "output_cost_per_token": 8e-8, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.1-70b": { "input_cost_per_token": 7.2e-7, @@ -25449,7 +26251,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7 + "output_cost_per_token": 7.2e-7, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.1-8b": { "input_cost_per_token": 5e-8, @@ -25458,7 +26261,9 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8e-8 + "output_cost_per_token": 8e-8, + "supports_function_calling": true, + "supports_response_schema": true }, "vercel_ai_gateway/meta/llama-3.2-11b": { "input_cost_per_token": 1.6e-7, @@ -25467,7 +26272,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.6e-7 + "output_cost_per_token": 1.6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.2-1b": { "input_cost_per_token": 1e-7, @@ -25485,7 +26293,9 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.5e-7 + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_response_schema": true }, "vercel_ai_gateway/meta/llama-3.2-90b": { "input_cost_per_token": 7.2e-7, @@ -25494,7 +26304,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7 + "output_cost_per_token": 7.2e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-3.3-70b": { "input_cost_per_token": 7.2e-7, @@ -25503,7 +26316,9 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-7 + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-4-maverick": { "input_cost_per_token": 2e-7, @@ -25512,7 +26327,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-7 + "output_cost_per_token": 6e-7, + "supports_tool_choice": true }, "vercel_ai_gateway/meta/llama-4-scout": { "input_cost_per_token": 1e-7, @@ -25521,7 +26337,10 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3e-7 + "output_cost_per_token": 3e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/mistral/codestral": { "input_cost_per_token": 3e-7, @@ -25530,7 +26349,9 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 9e-7 + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/mistral/codestral-embed": { "input_cost_per_token": 1.5e-7, @@ -25548,7 +26369,10 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.8e-7 + "output_cost_per_token": 2.8e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/mistral/magistral-medium": { "input_cost_per_token": 2e-6, @@ -25557,7 +26381,10 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 5e-6 + "output_cost_per_token": 5e-6, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/mistral/magistral-small": { "input_cost_per_token": 5e-7, @@ -25566,7 +26393,8 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-6 + "output_cost_per_token": 1.5e-6, + "supports_function_calling": true }, "vercel_ai_gateway/mistral/ministral-3b": { "input_cost_per_token": 4e-8, @@ -25575,7 +26403,9 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4e-8 + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/mistral/ministral-8b": { "input_cost_per_token": 1e-7, @@ -25584,7 +26414,10 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1e-7 + "output_cost_per_token": 1e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/mistral/mistral-embed": { "input_cost_per_token": 1e-7, @@ -25602,7 +26435,9 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 6e-6 + "output_cost_per_token": 6e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/mistral/mistral-saba-24b": { "input_cost_per_token": 7.9e-7, @@ -25620,7 +26455,10 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 3e-7 + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { "input_cost_per_token": 1.2e-6, @@ -25629,7 +26467,8 @@ "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 1.2e-6 + "output_cost_per_token": 1.2e-6, + "supports_function_calling": true }, "vercel_ai_gateway/mistral/pixtral-12b": { "input_cost_per_token": 1.5e-7, @@ -25638,7 +26477,11 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1.5e-7 + "output_cost_per_token": 1.5e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/mistral/pixtral-large": { "input_cost_per_token": 2e-6, @@ -25647,7 +26490,11 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 6e-6 + "output_cost_per_token": 6e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/moonshotai/kimi-k2": { "input_cost_per_token": 5.5e-7, @@ -25656,7 +26503,9 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.2e-6 + "output_cost_per_token": 2.2e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/morph/morph-v3-fast": { "input_cost_per_token": 8e-7, @@ -25683,7 +26532,9 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.5e-6 + "output_cost_per_token": 1.5e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { "input_cost_per_token": 1.5e-6, @@ -25701,7 +26552,10 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-5 + "output_cost_per_token": 3e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/openai/gpt-4.1": { "cache_creation_input_token_cost": 0.0, @@ -25712,7 +26566,11 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 8e-6 + "output_cost_per_token": 8e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4.1-mini": { "cache_creation_input_token_cost": 0.0, @@ -25723,7 +26581,11 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.6e-6 + "output_cost_per_token": 1.6e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4.1-nano": { "cache_creation_input_token_cost": 0.0, @@ -25734,7 +26596,11 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-7 + "output_cost_per_token": 4e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4o": { "cache_creation_input_token_cost": 0.0, @@ -25745,7 +26611,11 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/gpt-4o-mini": { "cache_creation_input_token_cost": 0.0, @@ -25756,7 +26626,11 @@ "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6e-7 + "output_cost_per_token": 6e-7, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/o1": { "cache_creation_input_token_cost": 0.0, @@ -25767,7 +26641,11 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 6e-5 + "output_cost_per_token": 6e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/o3": { "cache_creation_input_token_cost": 0.0, @@ -25778,7 +26656,11 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 8e-6 + "output_cost_per_token": 8e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/o3-mini": { "cache_creation_input_token_cost": 0.0, @@ -25789,7 +26671,10 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 4.4e-6 + "output_cost_per_token": 4.4e-6, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/o4-mini": { "cache_creation_input_token_cost": 0.0, @@ -25800,7 +26685,11 @@ "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 4.4e-6 + "output_cost_per_token": 4.4e-6, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true }, "vercel_ai_gateway/openai/text-embedding-3-large": { "input_cost_per_token": 1.3e-7, @@ -25872,7 +26761,10 @@ "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/vercel/v0-1.5-md": { "input_cost_per_token": 3e-6, @@ -25881,7 +26773,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-2": { "input_cost_per_token": 2e-6, @@ -25890,7 +26785,9 @@ "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-2-vision": { "input_cost_per_token": 2e-6, @@ -25899,7 +26796,10 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-5 + "output_cost_per_token": 1e-5, + "supports_vision": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3": { "input_cost_per_token": 3e-6, @@ -25908,7 +26808,9 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3-fast": { "input_cost_per_token": 5e-6, @@ -25917,7 +26819,8 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-5 + "output_cost_per_token": 2.5e-5, + "supports_function_calling": true }, "vercel_ai_gateway/xai/grok-3-mini": { "input_cost_per_token": 3e-7, @@ -25926,7 +26829,9 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5e-7 + "output_cost_per_token": 5e-7, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-3-mini-fast": { "input_cost_per_token": 6e-7, @@ -25935,7 +26840,9 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4e-6 + "output_cost_per_token": 4e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/xai/grok-4": { "input_cost_per_token": 3e-6, @@ -25944,7 +26851,9 @@ "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 1.5e-5 + "output_cost_per_token": 1.5e-5, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.5": { "input_cost_per_token": 6e-7, @@ -25953,7 +26862,9 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.2e-6 + "output_cost_per_token": 2.2e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.5-air": { "input_cost_per_token": 2e-7, @@ -25962,7 +26873,9 @@ "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", - "output_cost_per_token": 1.1e-6 + "output_cost_per_token": 1.1e-6, + "supports_function_calling": true, + "supports_tool_choice": true }, "vercel_ai_gateway/zai/glm-4.6": { "litellm_provider": "vercel_ai_gateway", @@ -26028,7 +26941,9 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_vision": true }, "vertex_ai/claude-3-5-sonnet": { "input_cost_per_token": 3e-6, @@ -26299,7 +27214,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "tool_use_system_prompt_tokens": 159, + "supports_native_streaming": true }, "vertex_ai/claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-6, @@ -26351,7 +27267,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_native_streaming": true }, "vertex_ai/claude-opus-4@20250514": { "cache_creation_input_token_cost": 1.875e-5, @@ -26621,6 +27538,21 @@ "output_cost_per_token_batches": 6e-6, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, + "vertex_ai/deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-6, + "input_cost_per_token_batches": 1e-6, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-5, + "output_cost_per_token_batches": 6e-6, + "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + }, "vertex_ai/imagegeneration@006": { "litellm_provider": "vertex_ai-image-models", "mode": "image_generation", @@ -27084,6 +28016,7 @@ "mode": "chat", "output_cost_per_token": 1e-6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": ["global"], "supports_function_calling": true, "supports_tool_choice": true }, @@ -27096,6 +28029,7 @@ "mode": "chat", "output_cost_per_token": 4e-6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": ["global"], "supports_function_calling": true, "supports_tool_choice": true }, @@ -27108,6 +28042,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": ["global"], "supports_function_calling": true, "supports_tool_choice": true }, @@ -27120,6 +28055,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-6, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_regions": ["global"], "supports_function_calling": true, "supports_tool_choice": true }, @@ -27942,6 +28878,7 @@ "supports_web_search": true }, "xai/grok-3": { + "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 3e-6, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -27956,6 +28893,7 @@ "supports_web_search": true }, "xai/grok-3-beta": { + "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 3e-6, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -27970,6 +28908,7 @@ "supports_web_search": true }, "xai/grok-3-fast-beta": { + "cache_read_input_token_cost": 1.25e-6, "input_cost_per_token": 5e-6, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -27984,6 +28923,7 @@ "supports_web_search": true }, "xai/grok-3-fast-latest": { + "cache_read_input_token_cost": 1.25e-6, "input_cost_per_token": 5e-6, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -27998,6 +28938,7 @@ "supports_web_search": true }, "xai/grok-3-latest": { + "cache_read_input_token_cost": 7.5e-7, "input_cost_per_token": 3e-6, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28012,6 +28953,7 @@ "supports_web_search": true }, "xai/grok-3-mini": { + "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28027,6 +28969,7 @@ "supports_web_search": true }, "xai/grok-3-mini-beta": { + "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28042,6 +28985,7 @@ "supports_web_search": true }, "xai/grok-3-mini-fast": { + "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28057,6 +29001,7 @@ "supports_web_search": true }, "xai/grok-3-mini-fast-beta": { + "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28072,6 +29017,7 @@ "supports_web_search": true }, "xai/grok-3-mini-fast-latest": { + "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 6e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28087,6 +29033,7 @@ "supports_web_search": true }, "xai/grok-3-mini-latest": { + "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 3e-7, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -28353,11 +29300,14 @@ "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, "zai/glm-4.6": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1.1e-7, "input_cost_per_token": 6e-7, "output_cost_per_token": 2.2e-6, "litellm_provider": "zai", @@ -28365,6 +29315,8 @@ "max_output_tokens": 128000, "mode": "chat", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, @@ -31921,5 +32873,18 @@ "output_cost_per_token": 0, "litellm_provider": "llamagate", "mode": "embedding" + }, + "sarvam/sarvam-m": { + "cache_creation_input_token_cost": 0, + "cache_creation_input_token_cost_above_1hr": 0, + "cache_read_input_token_cost": 0, + "input_cost_per_token": 0, + "litellm_provider": "sarvam", + "max_input_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "supports_reasoning": true } }