diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index b0997982e16..92b6ae6c469 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -5343,7 +5343,7 @@ "supports_tool_choice": true }, "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, @@ -5353,7 +5353,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -6691,6 +6691,7 @@ "supports_tool_choice": true }, "azure/gpt-realtime": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6726,9 +6727,11 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-2025-08-28": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6766,6 +6769,7 @@ "supports_tool_choice": true }, "azure/gpt-realtime-1.5": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6802,9 +6806,11 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-1.5-2026-02-23": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6925,6 +6931,8 @@ "supports_tool_choice": true }, "azure/gpt-realtime-mini": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 8e-08, "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, @@ -7033,6 +7041,7 @@ ] }, "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, @@ -7042,7 +7051,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -12430,7 +12439,7 @@ "supports_tool_choice": true }, "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, @@ -12440,7 +12449,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -29363,52 +29372,6 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/deepseek-ai/DeepSeek-V3.2": { - "litellm_provider": "friendliai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "DeepSeek chat model for instruction following, coding, and analysis", - "source": "https://api.friendli.ai/serverless/v1/models" - }, - "friendliai/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "friendliai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", "max_input_tokens": 202752, @@ -30575,7 +30538,6 @@ "successor_model": "gemini-3.8-flash", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, @@ -30634,7 +30596,6 @@ "output_cost_per_token_priority": 1.8e-05 }, "gemini-3.1-pro-preview": { - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, @@ -30698,7 +30659,6 @@ "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -30750,7 +30710,6 @@ "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -31194,7 +31153,6 @@ "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, @@ -31258,7 +31216,6 @@ "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -67761,7 +67718,7 @@ "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 8.5e-08, + "input_cost_per_token": 7.5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", @@ -72924,6 +72881,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-realtime-2": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -72942,7 +72900,7 @@ "provider_specific_entry": { "realtime_ga_only": 1 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], @@ -87353,6 +87311,343 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index b0997982e16..92b6ae6c469 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -5343,7 +5343,7 @@ "supports_tool_choice": true }, "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, @@ -5353,7 +5353,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -6691,6 +6691,7 @@ "supports_tool_choice": true }, "azure/gpt-realtime": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6726,9 +6727,11 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-2025-08-28": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6766,6 +6769,7 @@ "supports_tool_choice": true }, "azure/gpt-realtime-1.5": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6802,9 +6806,11 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure/gpt-realtime-1.5-2026-02-23": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-06, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -6925,6 +6931,8 @@ "supports_tool_choice": true }, "azure/gpt-realtime-mini": { + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "cache_read_input_image_token_cost": 8e-08, "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, @@ -7033,6 +7041,7 @@ ] }, "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, "cache_read_input_token_cost": 2.5e-06, "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, @@ -7042,7 +7051,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -12430,7 +12439,7 @@ "supports_tool_choice": true }, "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_audio_token_cost": 2.75e-06, "cache_read_input_token_cost": 2.75e-06, "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, @@ -12440,7 +12449,7 @@ "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_modalities": [ "text", "audio" @@ -29363,52 +29372,6 @@ "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/deepseek-ai/DeepSeek-V3.2": { - "litellm_provider": "friendliai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "DeepSeek chat model for instruction following, coding, and analysis", - "source": "https://api.friendli.ai/serverless/v1/models" - }, - "friendliai/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "friendliai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "supports_prompt_caching": true, - "supports_reasoning": true, - "reasoning_effort_levels": [], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_image_input": false, - "supports_video_input": false, - "mode": "chat", - "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", - "source": "https://api.friendli.ai/serverless/v1/models" - }, "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", "max_input_tokens": 202752, @@ -30575,7 +30538,6 @@ "successor_model": "gemini-3.8-flash", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, "cache_read_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost_priority": 2.25e-07, @@ -30634,7 +30596,6 @@ "output_cost_per_token_priority": 1.8e-05 }, "gemini-3.1-pro-preview": { - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, @@ -30698,7 +30659,6 @@ "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -30750,7 +30710,6 @@ "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -31194,7 +31153,6 @@ "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, @@ -31258,7 +31216,6 @@ "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "input_cost_per_token_batches": 1e-06, @@ -67761,7 +67718,7 @@ "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { "max_output_tokens": 262144, "max_input_tokens": 262144, - "input_cost_per_token": 8.5e-08, + "input_cost_per_token": 7.5e-08, "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", @@ -72924,6 +72881,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-realtime-2": { + "cache_read_input_image_token_cost": 5e-07, "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, @@ -72942,7 +72900,7 @@ "provider_specific_entry": { "realtime_ga_only": 1 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/realtime" ], @@ -87353,6 +87311,343 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "eu.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "global.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us-gov.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.2e-05, + "cache_creation_input_token_cost_above_1hr": 1.92e-05, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 9.6e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output_by_default": true, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, + "us.anthropic.claude-mythos-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 1.76e-05, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 8.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_utils.py index 1d2a5e4cc9b..f007d3740aa 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_utils.py @@ -1,4 +1,5 @@ import asyncio +import math import uuid from collections.abc import Mapping from types import MappingProxyType @@ -483,3 +484,42 @@ async def test_router_prices_balanced_columns_by_the_same_rules_as_flex( assert balanced_cost == pytest.approx(flex_cost) if not overridden_columns: assert balanced_cost == pytest.approx(_cost_at(PARITY_ROW, "_balanced")) + + +def _vertex_cost_with_cache_writes(model: str, prompt_tokens: int, cache_creation_tokens: int) -> float: + response: Final = ModelResponse( + model=model, + usage=Usage( + prompt_tokens=prompt_tokens, + completion_tokens=100, + total_tokens=prompt_tokens + 100, + cache_creation_input_tokens=cache_creation_tokens, + ), + ) + return litellm.completion_cost(completion_response=response, model=model, custom_llm_provider="vertex_ai") + + +@pytest.mark.parametrize( + "model", + ( + "gemini-2.5-pro", + "gemini-3.1-pro-preview", + "gemini-3.1-pro-preview-customtools", + "vertex_ai/gemini-3-pro-preview", + "vertex_ai/gemini-3.1-pro-preview", + "vertex_ai/gemini-3.1-pro-preview-customtools", + ), +) +def test_vertex_gemini_pro_bills_cache_writes_above_200k_at_the_above_200k_input_rate( + local_model_cost_map: None, model: str +) -> None: + rates: Final = litellm.get_model_info(model=model, custom_llm_provider="vertex_ai") + input_rate_above_200k: Final = rates.get("input_cost_per_token_above_200k_tokens") + output_rate_above_200k: Final = rates.get("output_cost_per_token_above_200k_tokens") + cache_creation_tokens: Final = 150_000 + below: Final = _vertex_cost_with_cache_writes(model, 190_000, cache_creation_tokens) + above: Final = _vertex_cost_with_cache_writes(model, 210_000, cache_creation_tokens) + + assert input_rate_above_200k is not None and output_rate_above_200k is not None + assert above > below + assert math.isclose(above, 210_000 * input_rate_above_200k + 100 * output_rate_above_200k)