From 821b2f69712828f07c35f408d3b6749280e81e8d Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sun, 20 Apr 2025 02:29:35 +0000 Subject: [PATCH] Update model_prices_and_context_window.json to version generated on 2025-04-20 --- .../model_prices_and_context_window.json | 894 ++++++++++++++++-- 1 file changed, 830 insertions(+), 64 deletions(-) diff --git a/model_cost_data/model_prices_and_context_window.json b/model_cost_data/model_prices_and_context_window.json index e345815f..91a330b2 100644 --- a/model_cost_data/model_prices_and_context_window.json +++ b/model_cost_data/model_prices_and_context_window.json @@ -5,6 +5,7 @@ "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", "input_cost_per_token": 0.0000, "output_cost_per_token": 0.000, + "output_cost_per_reasoning_token": 0.000, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", "supports_function_calling": true, @@ -15,6 +16,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, + "supports_reasoning": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.0000, @@ -63,6 +65,168 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-4.1": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 0.5e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 30e-3, + "search_context_size_medium": 35e-3, + "search_context_size_high": 50e-3 + } + }, + "gpt-4.1-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 0.5e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 30e-3, + "search_context_size_medium": 35e-3, + "search_context_size_high": 50e-3 + } + }, + "gpt-4.1-mini": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.4e-6, + "output_cost_per_token": 1.6e-6, + "input_cost_per_token_batches": 0.2e-6, + "output_cost_per_token_batches": 0.8e-6, + "cache_read_input_token_cost": 0.1e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 25e-3, + "search_context_size_medium": 27.5e-3, + "search_context_size_high": 30e-3 + } + }, + "gpt-4.1-mini-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.4e-6, + "output_cost_per_token": 1.6e-6, + "input_cost_per_token_batches": 0.2e-6, + "output_cost_per_token_batches": 0.8e-6, + "cache_read_input_token_cost": 0.1e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 25e-3, + "search_context_size_medium": 27.5e-3, + "search_context_size_high": 30e-3 + } + }, + "gpt-4.1-nano": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.1e-6, + "output_cost_per_token": 0.4e-6, + "input_cost_per_token_batches": 0.05e-6, + "output_cost_per_token_batches": 0.2e-6, + "cache_read_input_token_cost": 0.025e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true + }, + "gpt-4.1-nano-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.1e-6, + "output_cost_per_token": 0.4e-6, + "input_cost_per_token_batches": 0.05e-6, + "output_cost_per_token_batches": 0.2e-6, + "cache_read_input_token_cost": 0.025e-6, + "litellm_provider": "openai", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true + }, "gpt-4o": { "max_tokens": 16384, "max_input_tokens": 128000, @@ -379,7 +543,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": false, + "supports_reasoning": true, "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], "supported_endpoints": ["/v1/responses", "/v1/batch"] }, "o1-pro-2025-03-19": { @@ -400,7 +566,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_native_streaming": false, + "supports_reasoning": true, "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], "supported_endpoints": ["/v1/responses", "/v1/batch"] }, "o1": { @@ -418,6 +586,7 @@ "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true }, "o1-mini": { @@ -432,6 +601,40 @@ "supports_vision": true, "supports_prompt_caching": true }, + "o3": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1e-5, + "output_cost_per_token": 4e-5, + "cache_read_input_token_cost": 2.5e-6, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "o3-2025-04-16": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1e-5, + "output_cost_per_token": 4e-5, + "cache_read_input_token_cost": 2.5e-6, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "o3-mini": { "max_tokens": 100000, "max_input_tokens": 200000, @@ -446,6 +649,7 @@ "supports_vision": false, "supports_prompt_caching": true, "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true }, "o3-mini-2025-01-31": { @@ -462,6 +666,41 @@ "supports_vision": false, "supports_prompt_caching": true, "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "o4-mini": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1.1e-6, + "output_cost_per_token": 4.4e-6, + "cache_read_input_token_cost": 2.75e-7, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "o4-mini-2025-04-16": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1.1e-6, + "output_cost_per_token": 4.4e-6, + "cache_read_input_token_cost": 2.75e-7, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true }, "o1-mini-2024-09-12": { @@ -474,6 +713,7 @@ "litellm_provider": "openai", "mode": "chat", "supports_vision": true, + "supports_reasoning": true, "supports_prompt_caching": true }, "o1-preview": { @@ -486,6 +726,7 @@ "litellm_provider": "openai", "mode": "chat", "supports_vision": true, + "supports_reasoning": true, "supports_prompt_caching": true }, "o1-preview-2024-09-12": { @@ -498,6 +739,7 @@ "litellm_provider": "openai", "mode": "chat", "supports_vision": true, + "supports_reasoning": true, "supports_prompt_caching": true }, "o1-2024-12-17": { @@ -515,6 +757,7 @@ "supports_prompt_caching": true, "supports_system_messages": true, "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true }, "chatgpt-4o-latest": { @@ -1229,6 +1472,228 @@ "litellm_provider": "openai", "supported_endpoints": ["/v1/audio/speech"] }, + "azure/gpt-4.1": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 0.5e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 30e-3, + "search_context_size_medium": 35e-3, + "search_context_size_high": 50e-3 + } + }, + "azure/gpt-4.1-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 0.5e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 30e-3, + "search_context_size_medium": 35e-3, + "search_context_size_high": 50e-3 + } + }, + "azure/gpt-4.1-mini": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.4e-6, + "output_cost_per_token": 1.6e-6, + "input_cost_per_token_batches": 0.2e-6, + "output_cost_per_token_batches": 0.8e-6, + "cache_read_input_token_cost": 0.1e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 25e-3, + "search_context_size_medium": 27.5e-3, + "search_context_size_high": 30e-3 + } + }, + "azure/gpt-4.1-mini-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.4e-6, + "output_cost_per_token": 1.6e-6, + "input_cost_per_token_batches": 0.2e-6, + "output_cost_per_token_batches": 0.8e-6, + "cache_read_input_token_cost": 0.1e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 25e-3, + "search_context_size_medium": 27.5e-3, + "search_context_size_high": 30e-3 + } + }, + "azure/gpt-4.1-nano": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.1e-6, + "output_cost_per_token": 0.4e-6, + "input_cost_per_token_batches": 0.05e-6, + "output_cost_per_token_batches": 0.2e-6, + "cache_read_input_token_cost": 0.025e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true + }, + "azure/gpt-4.1-nano-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 0.1e-6, + "output_cost_per_token": 0.4e-6, + "input_cost_per_token_batches": 0.05e-6, + "output_cost_per_token_batches": 0.2e-6, + "cache_read_input_token_cost": 0.025e-6, + "litellm_provider": "azure", + "mode": "chat", + "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": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true + }, + "azure/o3": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1e-5, + "output_cost_per_token": 4e-5, + "cache_read_input_token_cost": 2.5e-6, + "litellm_provider": "azure", + "mode": "chat", + "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_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure/o3-2025-04-16": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1e-5, + "output_cost_per_token": 4e-5, + "cache_read_input_token_cost": 2.5e-6, + "litellm_provider": "azure", + "mode": "chat", + "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_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure/o4-mini": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1.1e-6, + "output_cost_per_token": 4.4e-6, + "cache_read_input_token_cost": 2.75e-7, + "litellm_provider": "azure", + "mode": "chat", + "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_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure/gpt-4o-mini-realtime-preview-2024-12-17": { "max_tokens": 4096, "max_input_tokens": 128000, @@ -1248,18 +1713,78 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { + "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000066, + "input_cost_per_audio_token": 0.000011, + "cache_read_input_token_cost": 0.00000033, + "cache_creation_input_audio_token_cost": 0.00000033, + "output_cost_per_token": 0.00000264, + "output_cost_per_audio_token": 0.000022, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000066, + "input_cost_per_audio_token": 0.000011, + "cache_read_input_token_cost": 0.00000033, + "cache_creation_input_audio_token_cost": 0.00000033, + "output_cost_per_token": 0.00000264, + "output_cost_per_audio_token": 0.000022, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-realtime-preview-2024-12-17": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000005, + "input_cost_per_audio_token": 0.00004, + "cache_read_input_token_cost": 0.0000025, + "output_cost_per_token": 0.00002, + "output_cost_per_audio_token": 0.00008, + "litellm_provider": "azure", + "mode": "chat", + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/us/gpt-4o-realtime-preview-2024-12-17": { "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000066, - "input_cost_per_audio_token": 0.000011, - "cache_read_input_token_cost": 0.00000033, - "cache_creation_input_audio_token_cost": 0.00000033, - "output_cost_per_token": 0.00000264, - "output_cost_per_audio_token": 0.000022, + "input_cost_per_token": 5.5e-6, + "input_cost_per_audio_token": 44e-6, + "cache_read_input_token_cost": 2.75e-6, + "cache_read_input_audio_token_cost": 2.5e-6, + "output_cost_per_token": 22e-6, + "output_cost_per_audio_token": 80e-6, "litellm_provider": "azure", "mode": "chat", + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_audio_input": true, @@ -1267,18 +1792,20 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "azure/eu/gpt-4o-realtime-preview-2024-12-17": { "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000066, - "input_cost_per_audio_token": 0.000011, - "cache_read_input_token_cost": 0.00000033, - "cache_creation_input_audio_token_cost": 0.00000033, - "output_cost_per_token": 0.00000264, - "output_cost_per_audio_token": 0.000022, + "input_cost_per_token": 5.5e-6, + "input_cost_per_audio_token": 44e-6, + "cache_read_input_token_cost": 2.75e-6, + "cache_read_input_audio_token_cost": 2.5e-6, + "output_cost_per_token": 22e-6, + "output_cost_per_audio_token": 80e-6, "litellm_provider": "azure", "mode": "chat", + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_audio_input": true, @@ -1343,6 +1870,23 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/o4-mini-2025-04-16": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 1.1e-6, + "output_cost_per_token": 4.4e-6, + "cache_read_input_token_cost": 2.75e-7, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure/o3-mini-2025-01-31": { "max_tokens": 100000, "max_input_tokens": 200000, @@ -1352,6 +1896,7 @@ "cache_read_input_token_cost": 0.00000055, "litellm_provider": "azure", "mode": "chat", + "supports_reasoning": true, "supports_vision": false, "supports_prompt_caching": true, "supports_tool_choice": true @@ -1368,6 +1913,7 @@ "litellm_provider": "azure", "mode": "chat", "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -1383,6 +1929,7 @@ "litellm_provider": "azure", "mode": "chat", "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -1413,6 +1960,7 @@ "mode": "chat", "supports_vision": false, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -1428,6 +1976,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true }, "azure/o1-mini-2024-09-12": { @@ -1442,6 +1991,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true }, "azure/us/o1-mini-2024-09-12": { @@ -1488,6 +2038,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, + "supports_reasoning": true, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -1503,6 +2054,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, + "supports_reasoning": true, "supports_prompt_caching": true, "supports_tool_choice": true }, @@ -1548,6 +2100,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true }, "azure/o1-preview-2024-09-12": { @@ -1562,6 +2115,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, + "supports_reasoning": true, "supports_prompt_caching": true }, "azure/us/o1-preview-2024-09-12": { @@ -2220,6 +2774,7 @@ "litellm_provider": "azure_ai", "mode": "chat", "supports_tool_choice": true, + "supports_reasoning": true, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" }, "azure_ai/deepseek-v3": { @@ -2300,6 +2855,18 @@ "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_tool_choice": true }, + "azure_ai/mistral-large-latest": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "litellm_provider": "azure_ai", + "supports_function_calling": true, + "mode": "chat", + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_tool_choice": true + }, "azure_ai/ministral-3b": { "max_tokens": 4096, "max_input_tokens": 128000, @@ -2397,25 +2964,26 @@ "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "input_cost_per_token": 0.000000075, + "output_cost_per_token": 0.0000003, "litellm_provider": "azure_ai", "mode": "chat", "supports_function_calling": true, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft" + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" }, "azure_ai/Phi-4-multimodal-instruct": { "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "input_cost_per_token": 0.00000008, + "input_cost_per_audio_token": 0.000004, + "output_cost_per_token": 0.00000032, "litellm_provider": "azure_ai", "mode": "chat", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/models-featured#microsoft" + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" }, "azure_ai/Phi-4": { "max_tokens": 16384, @@ -2907,6 +3475,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_prompt_caching": true }, "deepseek/deepseek-chat": { @@ -3020,6 +3589,87 @@ "supports_vision": true, "supports_tool_choice": true }, + "xai/grok-3-beta": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "litellm_provider": "xai", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, + "xai/grok-3-fast-beta": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "litellm_provider": "xai", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, + "xai/grok-3-fast-latest": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "litellm_provider": "xai", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, + "xai/grok-3-mini-beta": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.0000005, + "litellm_provider": "xai", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, + "xai/grok-3-mini-fast-beta": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.000004, + "litellm_provider": "xai", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, + "xai/grok-3-mini-fast-latest": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.000004, + "litellm_provider": "xai", + "mode": "chat", + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": false, + "source": "https://x.ai/api#pricing" + }, "xai/grok-vision-beta": { "max_tokens": 8192, "max_input_tokens": 8192, @@ -3090,6 +3740,7 @@ "mode": "chat", "supports_system_messages": false, "supports_function_calling": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_tool_choice": true }, @@ -3455,7 +4106,7 @@ "input_cost_per_token": 0.0000008, "output_cost_per_token": 0.000004, "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 0.0000008, + "cache_read_input_token_cost": 0.00000008, "litellm_provider": "anthropic", "mode": "chat", "supports_function_calling": true, @@ -3601,7 +4252,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "deprecation_date": "2025-06-01", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "claude-3-7-sonnet-20250219": { "max_tokens": 128000, @@ -3621,7 +4273,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "deprecation_date": "2026-02-01", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "claude-3-5-sonnet-20241022": { "max_tokens": 8192, @@ -4499,20 +5152,10 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_system_messages": true, @@ -4523,6 +5166,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini-2.0-pro-exp-02-05": { @@ -4535,20 +5181,10 @@ "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_system_messages": true, @@ -4559,6 +5195,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini-2.0-flash-exp": { @@ -4592,6 +5231,8 @@ "supports_vision": true, "supports_response_schema": true, "supports_audio_output": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_tool_choice": true }, @@ -4616,6 +5257,8 @@ "supports_response_schema": true, "supports_audio_output": true, "supports_tool_choice": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini-2.0-flash-thinking-exp": { @@ -4649,6 +5292,8 @@ "supports_vision": true, "supports_response_schema": true, "supports_audio_output": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, @@ -4683,9 +5328,69 @@ "supports_vision": true, "supports_response_schema": false, "supports_audio_output": false, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, + "gemini/gemini-2.5-flash-preview-04-17": { + "max_tokens": 65536, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_images_per_prompt": 3000, + "max_videos_per_prompt": 10, + "max_video_length": 1, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_pdf_size_mb": 30, + "input_cost_per_audio_token": 1e-6, + "input_cost_per_token": 0.15e-6, + "output_cost_per_token": 0.6e-6, + "output_cost_per_reasoning_token": 3.5e-6, + "litellm_provider": "gemini", + "mode": "chat", + "rpm": 10, + "tpm": 250000, + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_audio_output": false, + "supports_tool_choice": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" + }, + "gemini-2.5-flash-preview-04-17": { + "max_tokens": 65536, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_images_per_prompt": 3000, + "max_videos_per_prompt": 10, + "max_video_length": 1, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_pdf_size_mb": 30, + "input_cost_per_audio_token": 1e-6, + "input_cost_per_token": 0.15e-6, + "output_cost_per_token": 0.6e-6, + "output_cost_per_reasoning_token": 3.5e-6, + "litellm_provider": "vertex_ai-language-models", + "mode": "chat", + "supports_reasoning": true, + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_response_schema": true, + "supports_audio_output": false, + "supports_tool_choice": true, + "supported_endpoints": ["/v1/chat/completions", "/v1/completions", "/v1/batch"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview" + }, "gemini-2.0-flash": { "max_tokens": 8192, "max_input_tokens": 1048576, @@ -4708,6 +5413,7 @@ "supports_audio_output": true, "supports_audio_input": true, "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "supports_tool_choice": true, "source": "https://ai.google.dev/pricing#2_0flash" }, @@ -4730,6 +5436,32 @@ "supports_vision": true, "supports_response_schema": true, "supports_audio_output": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supports_tool_choice": true + }, + "gemini-2.0-flash-lite-001": { + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_images_per_prompt": 3000, + "max_videos_per_prompt": 10, + "max_video_length": 1, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_pdf_size_mb": 50, + "input_cost_per_audio_token": 0.000000075, + "input_cost_per_token": 0.000000075, + "output_cost_per_token": 0.0000003, + "litellm_provider": "vertex_ai-language-models", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_response_schema": true, + "supports_audio_output": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, @@ -4795,6 +5527,7 @@ "supports_audio_output": true, "supports_audio_input": true, "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "supports_tool_choice": true, "source": "https://ai.google.dev/pricing#2_0flash" }, @@ -4820,6 +5553,8 @@ "supports_response_schema": true, "supports_audio_output": true, "supports_tool_choice": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite" }, "gemini/gemini-2.0-flash-001": { @@ -4845,6 +5580,8 @@ "supports_response_schema": true, "supports_audio_output": false, "supports_tool_choice": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://ai.google.dev/pricing#2_0flash" }, "gemini/gemini-2.5-pro-preview-03-25": { @@ -4859,9 +5596,9 @@ "max_pdf_size_mb": 30, "input_cost_per_audio_token": 0.0000007, "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_128k_tokens": 0.0000025, - "output_cost_per_token": 0.0000010, - "output_cost_per_token_above_128k_tokens": 0.000015, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, "litellm_provider": "gemini", "mode": "chat", "rpm": 10000, @@ -4872,6 +5609,8 @@ "supports_response_schema": true, "supports_audio_output": false, "supports_tool_choice": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview" }, "gemini/gemini-2.0-flash-exp": { @@ -4907,6 +5646,8 @@ "supports_audio_output": true, "tpm": 4000000, "rpm": 10, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, @@ -4933,6 +5674,8 @@ "supports_response_schema": true, "supports_audio_output": false, "supports_tool_choice": true, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite" }, "gemini/gemini-2.0-flash-thinking-exp": { @@ -4968,6 +5711,8 @@ "supports_audio_output": true, "tpm": 4000000, "rpm": 10, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, @@ -5004,6 +5749,8 @@ "supports_audio_output": true, "tpm": 4000000, "rpm": 10, + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, @@ -5163,6 +5910,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "deprecation_date": "2025-06-01", + "supports_reasoning": true, "supports_tool_choice": true }, "vertex_ai/claude-3-haiku": { @@ -6480,6 +7228,7 @@ "mode": "chat", "supports_function_calling": true, "supports_assistant_prefill": true, + "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true }, @@ -6655,6 +7404,7 @@ "mode": "chat", "supports_function_calling": true, "supports_vision": true, + "supports_reasoning": true, "tool_use_system_prompt_tokens": 159, "supports_assistant_prefill": true, "supports_tool_choice": true @@ -6670,6 +7420,7 @@ "mode": "chat", "supports_function_calling": true, "supports_vision": true, + "supports_reasoning": true, "tool_use_system_prompt_tokens": 159, "supports_tool_choice": true }, @@ -6837,6 +7588,7 @@ "litellm_provider": "openrouter", "mode": "chat", "supports_function_calling": true, + "supports_reasoning": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_tool_choice": true @@ -6850,6 +7602,7 @@ "litellm_provider": "openrouter", "mode": "chat", "supports_function_calling": true, + "supports_reasoning": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_tool_choice": true @@ -7667,6 +8420,7 @@ "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true }, "anthropic.claude-3-5-sonnet-20241022-v2:0": { @@ -7784,7 +8538,8 @@ "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "us.anthropic.claude-3-haiku-20240307-v1:0": { "max_tokens": 4096, @@ -8444,7 +9199,8 @@ "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000020, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { "max_tokens": 4096, @@ -8453,7 +9209,8 @@ "input_cost_per_second": 0.011, "output_cost_per_second": 0.011, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { "max_tokens": 4096, @@ -8462,7 +9219,8 @@ "input_cost_per_second": 0.0066027, "output_cost_per_second": 0.0066027, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "cohere.command-light-text-v14": { "max_tokens": 4096, @@ -8471,7 +9229,8 @@ "input_cost_per_token": 0.0000003, "output_cost_per_token": 0.0000006, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { "max_tokens": 4096, @@ -8480,7 +9239,8 @@ "input_cost_per_second": 0.001902, "output_cost_per_second": 0.001902, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { "max_tokens": 4096, @@ -8489,7 +9249,8 @@ "input_cost_per_second": 0.0011416, "output_cost_per_second": 0.0011416, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "cohere.command-r-plus-v1:0": { "max_tokens": 4096, @@ -8498,7 +9259,8 @@ "input_cost_per_token": 0.0000030, "output_cost_per_token": 0.000015, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "cohere.command-r-v1:0": { "max_tokens": 4096, @@ -8507,7 +9269,8 @@ "input_cost_per_token": 0.0000005, "output_cost_per_token": 0.0000015, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_tool_choice": true }, "cohere.embed-english-v3": { "max_tokens": 512, @@ -8535,6 +9298,7 @@ "output_cost_per_token": 0.0000054, "litellm_provider": "bedrock_converse", "mode": "chat", + "supports_reasoning": true, "supports_function_calling": false, "supports_tool_choice": false @@ -10361,7 +11125,8 @@ "metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."}, "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "databricks/databricks-meta-llama-3-1-405b-instruct": { "max_tokens": 128000, @@ -10619,6 +11384,7 @@ "max_input_tokens": 32768, "max_output_tokens": 8192, "litellm_provider": "snowflake", + "supports_reasoning": true, "mode": "chat" }, "snowflake/snowflake-arctic": {