diff --git a/model_cost_data/model_prices_and_context_window.json b/model_cost_data/model_prices_and_context_window.json index 91a330b2..fdca26b0 100644 --- a/model_cost_data/model_prices_and_context_window.json +++ b/model_cost_data/model_prices_and_context_window.json @@ -356,7 +356,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-07-14" }, "gpt-4o-audio-preview": { "max_tokens": 16384, @@ -1437,8 +1438,80 @@ "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, + "gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "low/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0490417e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "medium/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "high/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.59263611e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "low/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0172526e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "medium/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "high/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.58945719e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "low/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0172526e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "medium/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, + "high/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.58945719e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "openai", + "supported_endpoints": ["/v1/images/generations"] + }, "gpt-4o-transcribe": { "mode": "audio_transcription", + "max_input_tokens": 16000, + "max_output_tokens": 2000, "input_cost_per_token": 0.0000025, "input_cost_per_audio_token": 0.000006, "output_cost_per_token": 0.00001, @@ -1447,6 +1520,8 @@ }, "gpt-4o-mini-transcribe": { "mode": "audio_transcription", + "max_input_tokens": 16000, + "max_output_tokens": 2000, "input_cost_per_token": 0.00000125, "input_cost_per_audio_token": 0.000003, "output_cost_per_token": 0.000005, @@ -1472,6 +1547,72 @@ "litellm_provider": "openai", "supported_endpoints": ["/v1/audio/speech"] }, + "azure/computer-use-preview": { + "max_tokens": 1024, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000012, + "litellm_provider": "azure", + "mode": "chat", + "supported_endpoints": ["/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": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "output_cost_per_token": 0.00001, + "output_cost_per_audio_token": 0.00008, + "litellm_provider": "azure", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_reasoning": false + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "output_cost_per_token": 0.00001, + "output_cost_per_audio_token": 0.00008, + "litellm_provider": "azure", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_native_streaming": true, + "supports_reasoning": false + }, "azure/gpt-4.1": { "max_tokens": 32768, "max_input_tokens": 1047576, @@ -1983,9 +2124,9 @@ "max_tokens": 65536, "max_input_tokens": 128000, "max_output_tokens": 65536, - "input_cost_per_token": 0.00000121, - "output_cost_per_token": 0.00000484, - "cache_read_input_token_cost": 0.000000605, + "input_cost_per_token": 1.1e-6, + "output_cost_per_token": 4.4e-6, + "cache_read_input_token_cost": 0.55e-6, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -2303,7 +2444,8 @@ "supports_response_schema": true, "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-08-20" }, "azure/us/gpt-4o-2024-08-06": { "max_tokens": 16384, @@ -2343,13 +2485,15 @@ "max_output_tokens": 16384, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000010, + "cache_read_input_token_cost": 0.00000125, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-12-20" }, "azure/global-standard/gpt-4o-mini": { "max_tokens": 16384, @@ -2722,7 +2866,77 @@ "output_cost_per_token": 0.000000, "litellm_provider": "azure", "mode": "embedding" - }, + }, + "azure/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/low/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0490417e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/medium/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/high/1024-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.59263611e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/low/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0172526e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/medium/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/high/1024-x-1536/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.58945719e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/low/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.0172526e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/medium/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 4.0054321e-8, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, + "azure/high/1536-x-1024/gpt-image-1": { + "mode": "image_generation", + "input_cost_per_pixel": 1.58945719e-7, + "output_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "supported_endpoints": ["/v1/images/generations"] + }, "azure/standard/1024-x-1024/dall-e-3": { "input_cost_per_pixel": 0.0000000381469, "output_cost_per_token": 0.0, @@ -5213,14 +5427,14 @@ "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_token": 0.00000015, "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_token": 0.0000006, "output_cost_per_character": 0, "output_cost_per_token_above_128k_tokens": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -5259,7 +5473,8 @@ "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" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "deprecation_date": "2026-02-05" }, "gemini-2.0-flash-thinking-exp": { "max_tokens": 8192, @@ -5333,6 +5548,35 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supports_tool_choice": true }, + "gemini/gemini-2.5-pro-exp-03-25": { + "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_token": 0.0, + "input_cost_per_token_above_200k_tokens": 0.0, + "output_cost_per_token": 0.0, + "output_cost_per_token_above_200k_tokens": 0.0, + "litellm_provider": "gemini", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true, + "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/gemini-2.5-flash-preview-04-17": { "max_tokens": 65536, "max_input_tokens": 1048576, @@ -5463,7 +5707,37 @@ "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 + "supports_tool_choice": true, + "deprecation_date": "2026-02-25" + }, + "gemini-2.5-pro-preview-03-25": { + "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": 0.00000125, + "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_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/gemini-2.0-pro-exp-02-05": { "max_tokens": 8192, @@ -6893,6 +7167,17 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, + "command-a-03-2025": { + "max_tokens": 8000, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.00001, + "litellm_provider": "cohere_chat", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true + }, "command-r": { "max_tokens": 4096, "max_input_tokens": 128000,