From 02acdeea787fa5ad34e184336c316a25302b642a Mon Sep 17 00:00:00 2001 From: Dushyant Acharya Date: Fri, 12 Jun 2026 19:18:37 +0530 Subject: [PATCH] fix(tests): resolve failing claude-fable-5 and reasoning tests by safely updating cost map - Pulled the latest cost map from upstream staging - Safely appended deepseek-v4 mapping without deleting duplicate keys or formatting via json.dump --- model_prices_and_context_window.json | 3481 ++++++++++++++++++++++---- 1 file changed, 3016 insertions(+), 465 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index bd44bbc2803..9beb4625be6 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -577,7 +577,10 @@ "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "output_vector_size": 1024 + "output_vector_size": 1024, + "provider_specific_entry": { + "bedrock_invocation_schema": "titan_v2" + } }, "amazon.titan-image-generator-v1": { "input_cost_per_image": 0.0, @@ -731,7 +734,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "anthropic.claude-haiku-4-5@20251001": { @@ -755,7 +757,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_streaming": true, "supports_native_structured_output": true }, @@ -926,8 +927,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -952,8 +952,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -980,8 +979,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1008,10 +1008,10 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, + "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "bedrock_output_config_effort_ceiling": "max" }, "global.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.25e-06, @@ -1038,10 +1038,10 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, + "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "bedrock_output_config_effort_ceiling": "max" }, "us.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, @@ -1068,146 +1068,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, + "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "bedrock_output_config_effort_ceiling": "max" }, "eu.anthropic.claude-opus-4-6-v1": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "au.anthropic.claude-opus-4-6-v1": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_read_input_token_cost": 5.5e-07, - "input_cost_per_token": 5.5e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "anthropic.claude-opus-4-7": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "anthropic.claude-mythos-preview": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "bedrock", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "global.anthropic.claude-opus-4-7": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "us.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, @@ -1232,14 +1098,14 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, + "supports_output_config": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "bedrock_output_config_effort_ceiling": "max" }, - "eu.anthropic.claude-opus-4-7": { + "au.anthropic.claude-opus-4-6-v1": { "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", @@ -1262,13 +1128,484 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max" + }, + "anthropic.claude-opus-4-7": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "anthropic.claude-mythos-preview": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_output_config": true + }, + "global.anthropic.claude-opus-4-7": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "us.anthropic.claude-opus-4-7": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "eu.anthropic.claude-opus-4-7": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" }, "au.anthropic.claude-opus-4-7": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "anthropic.claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "global.anthropic.claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "us.anthropic.claude-fable-5": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "eu.anthropic.claude-fable-5": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "anthropic.claude-opus-4-8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "global.anthropic.claude-opus-4-8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "us.anthropic.claude-opus-4-8": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "eu.anthropic.claude-opus-4-8": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "au.anthropic.claude-opus-4-8": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh" + }, + "jp.anthropic.claude-opus-4-7": { "cache_creation_input_token_cost": 6.875e-06, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, @@ -1290,6 +1627,7 @@ "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, @@ -1321,11 +1659,11 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "global.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.75e-06, @@ -1350,11 +1688,11 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "us.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 4.125e-06, @@ -1379,14 +1717,15 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "eu.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", @@ -1407,14 +1746,15 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "au.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", @@ -1435,11 +1775,40 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true + }, + "jp.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -1468,8 +1837,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -1501,7 +1869,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true }, "anthropic.claude-v1": { @@ -1752,7 +2119,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { @@ -1798,8 +2164,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -1815,11 +2180,13 @@ }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, @@ -1841,7 +2208,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "azure/ada": { @@ -1931,7 +2297,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_output_config": true }, "azure_ai/claude-opus-4-6": { "input_cost_per_token": 5e-06, @@ -1958,9 +2325,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true, + "supports_max_reasoning_effort": true }, "azure_ai/claude-opus-4-7": { "input_cost_per_token": 5e-06, @@ -1985,12 +2351,71 @@ "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, - "tool_use_system_prompt_tokens": 159, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_max_reasoning_effort": true + }, + "azure_ai/claude-fable-5": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true + }, + "azure_ai/claude-opus-4-8": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true }, "azure_ai/claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -2052,10 +2477,10 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "azure/computer-use-preview": { "input_cost_per_token": 3e-06, @@ -2103,6 +2528,380 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "azure_ai/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, + "source": "https://ai.azure.com/catalog/models/gpt-5.4", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true + }, + "azure_ai/gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, + "source": "https://ai.azure.com/catalog/models/gpt-5.4", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true + }, + "azure_ai/gpt-5.4-pro": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 0.00012, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_priority": 0.00036, + "output_cost_per_token_above_272k_tokens_priority": 0.00054, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true + }, + "azure_ai/gpt-5.4-pro-2026-03-05": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 0.00012, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_priority": 0.00036, + "output_cost_per_token_above_272k_tokens_priority": 0.00054, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true + }, + "azure_ai/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.5e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_above_272k_tokens": 1.5e-06, + "input_cost_per_token_priority": 1.5e-06, + "input_cost_per_token_above_272k_tokens_priority": 3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "output_cost_per_token_above_272k_tokens": 6.75e-06, + "output_cost_per_token_priority": 9e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.35e-05, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure_ai/gpt-5.4-mini-2026-03-17": { + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1.5e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_above_272k_tokens": 1.5e-06, + "input_cost_per_token_priority": 1.5e-06, + "input_cost_per_token_above_272k_tokens_priority": 3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "output_cost_per_token_above_272k_tokens": 6.75e-06, + "output_cost_per_token_priority": 9e-06, + "output_cost_per_token_above_272k_tokens_priority": 1.35e-05, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure_ai/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_272k_tokens": 1.875e-06, + "output_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.75e-06, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure_ai/gpt-5.4-nano-2026-03-17": { + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "output_cost_per_token_above_272k_tokens": 1.875e-06, + "output_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.75e-06, + "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/model_router": { "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, @@ -3512,7 +4311,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3587,7 +4386,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3599,7 +4398,7 @@ ] }, "azure/gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -3610,6 +4409,23 @@ "/v1/audio/transcriptions" ] }, + "azure/gpt-realtime-whisper": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, @@ -5642,6 +6458,17 @@ "mode": "audio_speech", "source": "https://azure.microsoft.com/en-us/pricing/calculator/" }, + "azure/speech/azure-stt": { + "audio_transcription_config": "azure_speech", + "input_cost_per_second": 0.0002777778, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, "azure/tts-1": { "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", @@ -6254,6 +7081,43 @@ "/v1/images/generations" ] }, + "azure_ai/MAI-Image-2.5": { + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05, + "output_cost_per_image_token": 4.7e-05, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure_ai/MAI-Image-2.5-Flash": { + "input_cost_per_image_token": 1.75e-06, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0338, + "output_cost_per_image_token": 3.3e-05, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure_ai/MAI-Image-2e": { + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "output_cost_per_image_token": 1.95e-05, + "source": "https://aka.ms/mai-image-2e-foundryblog", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "azure_ai/Llama-3.2-11B-Vision-Instruct": { "input_cost_per_token": 3.7e-07, "litellm_provider": "azure_ai", @@ -6710,6 +7574,45 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "azure_ai/deepseek-v3.1": { + "input_cost_per_token": 1.23e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.94e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v4-pro": { + "input_cost_per_token": 1.74e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v4-flash": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 5.1e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/embed-v-4-0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", @@ -6904,6 +7807,27 @@ "supports_video_input": true, "supports_vision": true }, + "azure_ai/kimi-k2.6": { + "input_cost_per_token": 9.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure_ai/ministral-3b": { "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", @@ -8092,16 +9016,17 @@ }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "output_cost_per_token": 1.2e-06 }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -8311,15 +9236,16 @@ "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_creation_input_token_cost": 4.5e-06, + "cache_creation_input_token_cost_above_1hr": 7.2e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -8332,15 +9258,16 @@ "supports_native_structured_output": true }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_creation_input_token_cost": 4.5e-06, + "cache_creation_input_token_cost_above_1hr": 7.2e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -8484,15 +9411,16 @@ "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_creation_input_token_cost": 4.5e-06, + "cache_creation_input_token_cost_above_1hr": 7.2e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -8505,15 +9433,16 @@ "supports_native_structured_output": true }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_creation_input_token_cost": 4.5e-06, + "cache_creation_input_token_cost_above_1hr": 7.2e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -8709,16 +9638,17 @@ }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "output_cost_per_token": 1.2e-06 }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { "input_cost_per_token": 6e-07, @@ -8963,7 +9893,7 @@ "supports_vision": true }, "gpt-4o-transcribe-diarize": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -9042,8 +9972,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "tool_use_system_prompt_tokens": 159 + "supports_web_search": true }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, @@ -9061,8 +9990,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264 + "supports_vision": true }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, @@ -9081,8 +10009,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395 + "supports_vision": true }, "claude-4-opus-20250514": { "cache_creation_input_token_cost": 1.875e-05, @@ -9107,8 +10034,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-4-sonnet-20250514": { "cache_creation_input_token_cost": 3.75e-06, @@ -9138,8 +10064,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "tool_use_system_prompt_tokens": 159 + "supports_web_search": true }, "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, @@ -9168,8 +10093,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": true }, "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, @@ -9199,8 +10123,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "tool_use_system_prompt_tokens": 346 + "supports_web_search": true }, "claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.75e-06, @@ -9217,6 +10140,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -9224,10 +10148,10 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -9251,8 +10175,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -9278,8 +10201,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-opus-4-1-20250805": { "cache_creation_input_token_cost": 1.875e-05, @@ -9306,8 +10228,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-opus-4-20250514": { "cache_creation_input_token_cost": 1.875e-05, @@ -9334,8 +10255,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, @@ -9362,7 +10282,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_output_config": true }, "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, @@ -9389,7 +10309,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_output_config": true }, "claude-opus-4-6": { "cache_creation_input_token_cost": 6.25e-06, @@ -9407,6 +10327,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9416,13 +10337,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6.0 }, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true, + "supports_max_reasoning_effort": true }, "claude-opus-4-6-20260205": { "cache_creation_input_token_cost": 6.25e-06, @@ -9440,6 +10360,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9449,13 +10370,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6.0 }, "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "claude-opus-4-7": { "cache_creation_input_token_cost": 6.25e-06, @@ -9473,6 +10393,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9480,16 +10401,16 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6.0 }, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "claude-opus-4-7-20260416": { "cache_creation_input_token_cost": 6.25e-06, @@ -9507,6 +10428,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9514,16 +10436,85 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6.0 }, - "supports_minimal_reasoning_effort": true + "supports_output_config": true + }, + "claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true + }, + "claude-opus-4-8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1, + "fast": 2.0 + }, + "supports_output_config": true }, "claude-sonnet-4-20250514": { "deprecation_date": "2026-05-14", @@ -9554,8 +10545,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, @@ -10800,7 +11790,8 @@ "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_output_config": true }, "databricks/databricks-claude-sonnet-4": { "input_cost_per_token": 2.9999900000000002e-06, @@ -12062,7 +13053,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "supports_image_size": false }, "deepinfra/google/gemini-2.5-pro": { "max_tokens": 1000000, @@ -12767,6 +13759,22 @@ "notes": "Serper Google Search API. Pricing: $1.00/1k queries (Starter), $0.75/1k (Standard), $0.50/1k (Scale), $0.30/1k (Ultimate)." } }, + "apiserpent/search": { + "input_cost_per_query": 0.0006, + "litellm_provider": "apiserpent", + "mode": "search", + "metadata": { + "notes": "APISerpent quick search (/api/search/quick), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." + } + }, + "apiserpent/deep_search": { + "input_cost_per_query": 0.0006, + "litellm_provider": "apiserpent", + "mode": "search", + "metadata": { + "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." + } + }, "elevenlabs/scribe_v1": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", @@ -12947,6 +13955,7 @@ }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "deprecation_date": "2026-10-15", @@ -12966,7 +13975,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { @@ -13094,8 +14102,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -13120,8 +14127,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -13150,16 +14156,17 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, @@ -13181,7 +14188,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "eu.meta.llama3-2-1b-instruct-v1:0": { @@ -13313,6 +14319,22 @@ "/v1/images/generations" ] }, + "fal_ai/fal-ai/nano-banana": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/gemini-25-flash-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.039, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "featherless_ai/featherless-ai/Qwerky-72B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, @@ -13559,6 +14581,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "fireworks_ai/accounts/fireworks/models/glm-5p1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://fireworks.ai/models/fireworks/glm-5p1", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "fireworks_ai", @@ -13825,6 +14862,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "fireworks_ai/glm-5p1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://fireworks.ai/models/fireworks/glm-5p1", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fireworks_ai/kimi-k2p5": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 6e-07, @@ -14345,7 +15397,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, @@ -14395,7 +15448,8 @@ "supports_vision": true, "supports_web_search": false, "tpm": 8000000, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -14534,6 +15588,73 @@ "web_search_billing_unit": "per_query", "supports_service_tier": true }, + "gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -14617,7 +15738,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini-2.5-flash-lite-preview-09-2025": { "cache_read_input_token_cost": 1e-08, @@ -14667,7 +15789,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini-2.5-flash-preview-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -14717,7 +15840,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -14868,7 +15992,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, @@ -15222,6 +16347,64 @@ }, "web_search_billing_unit": "per_query" }, + "vertex_ai/gemini-3.5-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "input_cost_per_audio_token": 1e-06, + "litellm_provider": "vertex_ai", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 2.7e-06, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 1.62e-05, + "cache_read_input_token_cost_priority": 2.7e-07, + "supports_service_tier": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, "vertex_ai/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, @@ -15536,14 +16719,17 @@ "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_audio_per_second": 0.00016, + "input_cost_per_image": 0.00012, + "input_cost_per_token": 2e-07, + "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true }, @@ -15558,7 +16744,7 @@ "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true }, @@ -15817,7 +17003,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, @@ -15873,7 +17060,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -16052,7 +17240,8 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "supports_service_tier": true + "supports_service_tier": true, + "supports_image_size": false }, "gemini/gemini-2.5-flash-lite-preview-09-2025": { "cache_read_input_token_cost": 1e-08, @@ -16104,7 +17293,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini/gemini-2.5-flash-preview-09-2025": { "cache_read_input_token_cost": 7.5e-08, @@ -16156,7 +17346,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, @@ -16313,7 +17504,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_image_size": false }, "gemini/gemini-2.5-flash-preview-tts": { "input_cost_per_token": 3e-07, @@ -16537,6 +17729,75 @@ "web_search_billing_unit": "per_query", "supports_service_tier": true }, + "gemini/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, @@ -16596,6 +17857,67 @@ }, "web_search_billing_unit": "per_query" }, + "gemini/gemini-3.5-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "rpm": 2000, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 2.7e-06, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 1.62e-05, + "cache_read_input_token_cost_priority": 2.7e-07, + "supports_service_tier": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, "gemini/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, @@ -16781,6 +18103,65 @@ }, "web_search_billing_unit": "per_query" }, + "gemini-3.5-flash": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://ai.google.dev/pricing/gemini-3", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 2.7e-06, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 1.62e-05, + "cache_read_input_token_cost_priority": 2.7e-07, + "supports_service_tier": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -17160,7 +18541,8 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true + "supports_vision": true, + "supports_output_config": true }, "github_copilot/claude-opus-4.6-fast": { "litellm_provider": "github_copilot", @@ -17673,7 +19055,8 @@ "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, - "supports_vision": true + "supports_vision": true, + "supports_output_config": true }, "gmi/anthropic/claude-sonnet-4.5": { "input_cost_per_token": 3e-06, @@ -17973,7 +19356,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { @@ -18003,8 +19385,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -18027,7 +19408,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "global.amazon.nova-2-lite-v1:0": { @@ -18249,6 +19629,8 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -18322,6 +19704,8 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -18395,6 +19779,8 @@ "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 8e-07, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -18466,6 +19852,8 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.7e-05, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -18507,6 +19895,8 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -18528,6 +19918,8 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -18816,6 +20208,8 @@ "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1e-06, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -18971,7 +20365,7 @@ "supports_vision": true }, "gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -19101,7 +20495,7 @@ "supports_vision": true }, "gpt-4o-transcribe": { - "input_cost_per_audio_token": 6e-06, + "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -19519,6 +20913,8 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20441,6 +21837,8 @@ "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -20847,6 +22245,8 @@ "output_cost_per_token": 2e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20928,6 +22328,8 @@ "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, + "regional_processing_uplift_multiplier_eu": 1.10, + "regional_processing_uplift_multiplier_us": 1.10, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_flex": 2e-07, @@ -21087,6 +22489,38 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-realtime-2": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, @@ -22055,11 +23489,13 @@ }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "input_cost_per_token_above_200k_tokens": 6.6e-06, "output_cost_per_token_above_200k_tokens": 2.475e-05, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, @@ -22081,11 +23517,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", @@ -22104,7 +23540,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { @@ -22199,6 +23634,31 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "inception/mercury-2": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "inception", + "max_input_tokens": 128000, + "max_output_tokens": 50000, + "max_tokens": 50000, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "text-completion-inception/mercury-edit-2": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "text-completion-inception", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 7.5e-07 + }, "lambda_ai/deepseek-llama3.3-70b": { "input_cost_per_token": 2e-07, "litellm_provider": "lambda_ai", @@ -22868,13 +24328,14 @@ }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, + "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -22986,6 +24447,24 @@ "max_input_tokens": 200000, "max_output_tokens": 8192 }, + "minimax/MiniMax-M3": { + "input_cost_per_token": 3e-07, + "input_cost_per_token_above_512k_tokens": 6e-07, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_512k_tokens": 2.4e-06, + "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_above_512k_tokens": 1.2e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000 + }, "mistral.devstral-2-123b": { "input_cost_per_token": 4e-07, "litellm_provider": "bedrock_converse", @@ -23680,6 +25159,36 @@ "supports_tool_choice": true, "supports_vision": true }, + "mistral/ministral-8b-2512": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-8b-latest": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/mistral-tiny": { "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", @@ -23838,6 +25347,7 @@ }, "moonshot/kimi-k2-0711-preview": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-05-25", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23852,6 +25362,7 @@ }, "moonshot/kimi-k2-0905-preview": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-05-25", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -23866,6 +25377,7 @@ }, "moonshot/kimi-k2-turbo-preview": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-05-25", "input_cost_per_token": 1.15e-06, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -23890,6 +25402,7 @@ "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true @@ -23906,12 +25419,14 @@ "source": "https://platform.kimi.ai/docs/pricing/chat-k26", "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "moonshot/kimi-latest": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-01-28", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23926,6 +25441,7 @@ }, "moonshot/kimi-latest-128k": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-01-28", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23940,6 +25456,7 @@ }, "moonshot/kimi-latest-32k": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-01-28", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -23954,6 +25471,7 @@ }, "moonshot/kimi-latest-8k": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-01-28", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -23968,6 +25486,7 @@ }, "moonshot/kimi-thinking-preview": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2025-11-11", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -23980,6 +25499,7 @@ }, "moonshot/kimi-k2-thinking": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-05-25", "input_cost_per_token": 6e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -23995,6 +25515,7 @@ }, "moonshot/kimi-k2-thinking-turbo": { "cache_read_input_token_cost": 1.5e-07, + "deprecation_date": "2026-05-25", "input_cost_per_token": 1.15e-06, "litellm_provider": "moonshot", "max_input_tokens": 262144, @@ -24018,9 +25539,11 @@ "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-128k-0430": { + "deprecation_date": "2024-04-30", "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -24042,6 +25565,7 @@ "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, @@ -24055,9 +25579,11 @@ "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-32k-0430": { + "deprecation_date": "2024-04-30", "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -24079,6 +25605,7 @@ "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, @@ -24092,9 +25619,11 @@ "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "moonshot/moonshot-v1-8k-0430": { + "deprecation_date": "2024-04-30", "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", "max_input_tokens": 8192, @@ -24116,6 +25645,7 @@ "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, @@ -24129,6 +25659,7 @@ "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, "morph/morph-v3-fast": { @@ -25180,6 +26711,32 @@ "supports_vision": true, "supports_web_search": true }, + "oci/meta.llama-3.1-8b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/meta.llama-3.1-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true + }, "oci/meta.llama-3.1-405b-instruct": { "input_cost_per_token": 1.068e-05, "litellm_provider": "oci", @@ -25190,7 +26747,8 @@ "output_cost_per_token": 1.068e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/meta.llama-3.2-90b-vision-instruct": { "input_cost_per_token": 2e-06, @@ -25203,6 +26761,7 @@ "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false, + "supports_native_streaming": true, "supports_vision": true }, "oci/meta.llama-3.3-70b-instruct": { @@ -25215,31 +26774,35 @@ "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", - "max_input_tokens": 512000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true, + "supports_vision": true }, "oci/meta.llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", - "max_input_tokens": 192000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_input_tokens": 10485760, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/xai.grok-3": { "input_cost_per_token": 3e-06, @@ -25251,7 +26814,8 @@ "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/xai.grok-3-fast": { "input_cost_per_token": 5e-06, @@ -25263,7 +26827,8 @@ "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/xai.grok-3-mini": { "input_cost_per_token": 3e-07, @@ -25275,7 +26840,8 @@ "output_cost_per_token": 5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/xai.grok-3-mini-fast": { "input_cost_per_token": 6e-07, @@ -25287,7 +26853,8 @@ "output_cost_per_token": 4e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/xai.grok-4": { "input_cost_per_token": 3e-06, @@ -25299,7 +26866,8 @@ "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/cohere.command-latest": { "input_cost_per_token": 1.56e-06, @@ -25311,7 +26879,8 @@ "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/cohere.command-a-03-2025": { "input_cost_per_token": 1.56e-06, @@ -25323,7 +26892,8 @@ "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true }, "oci/cohere.command-plus-latest": { "input_cost_per_token": 1.56e-06, @@ -25335,7 +26905,88 @@ "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_function_calling": true, - "supports_response_schema": false + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/google.gemini-2.5-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_native_streaming": true, + "supports_image_size": false + }, + "oci/google.gemini-2.5-pro": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "oci", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_native_streaming": true + }, + "oci/google.gemini-2.5-flash-lite": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "oci", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_native_streaming": true, + "supports_image_size": false + }, + "oci/cohere.command-a-vision": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_native_streaming": true, + "supports_vision": true + }, + "oci/cohere.command-a-reasoning": { + "input_cost_per_token": 1.56e-06, + "litellm_provider": "oci", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_native_streaming": true + }, + "oci/cohere.embed-multilingual-image-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "oci", + "max_input_tokens": 512, + "mode": "embedding", + "output_vector_size": 1024, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_vision": true }, "oci/cohere.command-a-reasoning-08-2025": { "input_cost_per_token": 1.56e-06, @@ -25411,18 +27062,6 @@ "supports_response_schema": false, "supports_vision": true }, - "oci/meta.llama-3.1-70b-instruct": { - "input_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 7.2e-07, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", - "supports_function_calling": true, - "supports_response_schema": false - }, "oci/meta.llama-3.3-70b-instruct-fp8-dynamic": { "input_cost_per_token": 7.2e-07, "litellm_provider": "oci", @@ -25495,42 +27134,48 @@ "supports_function_calling": true, "supports_response_schema": false }, - "oci/google.gemini-2.5-pro": { + "oci/openai.gpt-5": { "input_cost_per_token": 1.25e-06, "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "oci/google.gemini-2.5-flash": { - "input_cost_per_token": 1.5e-07, + "oci/openai.gpt-5-mini": { + "input_cost_per_token": 2.5e-07, "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, - "oci/google.gemini-2.5-flash-lite": { - "input_cost_per_token": 7.5e-08, + "oci/openai.gpt-5-nano": { + "input_cost_per_token": 5e-08, "litellm_provider": "oci", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 4e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true }, @@ -25985,8 +27630,7 @@ "supports_computer_use": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-3.7-sonnet": { "input_cost_per_image": 0.0048, @@ -26002,8 +27646,7 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-opus-4": { "input_cost_per_image": 0.0048, @@ -26022,8 +27665,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-opus-4.1": { "input_cost_per_image": 0.0048, @@ -26043,8 +27685,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-sonnet-4": { "input_cost_per_image": 0.0048, @@ -26067,8 +27708,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-sonnet-4.6": { "cache_creation_input_token_cost": 3.75e-06, @@ -26090,10 +27730,9 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_minimal_reasoning_effort": true + "supports_vision": true }, "openrouter/anthropic/claude-opus-4.5": { "cache_creation_input_token_cost": 6.25e-06, @@ -26112,7 +27751,7 @@ "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_output_config": true }, "openrouter/anthropic/claude-opus-4.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -26129,10 +27768,9 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_minimal_reasoning_effort": true + "supports_vision": true }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, @@ -26155,8 +27793,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "openrouter/anthropic/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, @@ -26174,8 +27811,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "supports_vision": true }, "openrouter/anthropic/claude-opus-4.7": { "cache_creation_input_token_cost": 6.25e-06, @@ -26194,10 +27830,10 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "tool_use_system_prompt_tokens": 346 + "supports_xhigh_reasoning_effort": true }, "openrouter/bytedance/ui-tars-1.5-7b": { "input_cost_per_token": 1e-07, @@ -26350,7 +27986,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_image_size": false }, "openrouter/google/gemini-2.5-pro": { "input_cost_per_audio_token": 7e-07, @@ -26520,6 +28157,58 @@ "supports_web_search": true, "tpm": 800000 }, + "openrouter/google/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 + }, "openrouter/google/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, @@ -27165,6 +28854,20 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/qwen/qwen3.6-plus": { + "input_cost_per_token": 3.25e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.95e-06, + "source": "https://openrouter.ai/qwen/qwen3.6-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "openrouter/qwen/qwen3.5-35b-a3b": { "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", @@ -27315,10 +29018,10 @@ "supports_tool_choice": true }, "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 2.9e-07, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -27328,7 +29031,43 @@ "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, - "supports_prompt_caching": false + "supports_prompt_caching": true + }, + "openrouter/xiaomi/mimo-v2.5-pro": { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_response_schema": true, + "supports_prompt_caching": true + }, + "openrouter/xiaomi/mimo-v2.5": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 8e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true, + "supports_response_schema": true, + "supports_prompt_caching": true }, "openrouter/z-ai/glm-4.7": { "input_cost_per_token": 4e-07, @@ -28059,21 +29798,24 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "supports_output_config": true }, "perplexity/anthropic/claude-opus-4-7": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "supports_output_config": true }, "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "supports_output_config": true }, "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", @@ -28115,7 +29857,8 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "supports_image_size": false }, "perplexity/xai/grok-4-1-fast-non-reasoning": { "litellm_provider": "perplexity", @@ -28279,6 +30022,24 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "reducto/parse-legacy": { + "litellm_provider": "reducto", + "mode": "ocr", + "ocr_cost_per_credit": 0.015, + "source": "https://reducto.ai/pricing", + "supported_endpoints": [ + "/v1/ocr" + ] + }, + "reducto/parse-v3": { + "litellm_provider": "reducto", + "mode": "ocr", + "ocr_cost_per_credit": 0.015, + "source": "https://reducto.ai/pricing", + "supported_endpoints": [ + "/v1/ocr" + ] + }, "recraft/recraftv2": { "litellm_provider": "recraft", "mode": "image_generation", @@ -28679,7 +30440,8 @@ "supports_vision": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_image_size": false }, "replicate/openai/gpt-oss-120b": { "input_cost_per_token": 1.8e-07, @@ -28851,6 +30613,19 @@ "mode": "chat", "output_cost_per_token": 0.0 }, + "sambanova/MiniMax-M2.7": { + "input_cost_per_token": 3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "sambanova/DeepSeek-R1": { "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", @@ -29046,21 +30821,32 @@ "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "snowflake/claude-3-5-sonnet": { + "snowflake/claude-3-5-sonnet": { "litellm_provider": "snowflake", - "max_input_tokens": 18000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "supports_computer_use": true + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true }, - "snowflake/deepseek-r1": { + "snowflake/deepseek-r1": { "litellm_provider": "snowflake", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "supports_reasoning": true + "input_cost_per_token": 0.00000135, + "output_cost_per_token": 0.0000054, + "supports_reasoning": true, + "supports_system_messages": true }, "snowflake/gemma-7b": { "litellm_provider": "snowflake", @@ -29114,23 +30900,34 @@ "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true }, "snowflake/llama3.1-70b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, + "supports_function_calling": true, + "supports_system_messages": true }, "snowflake/llama3.1-8b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.00000024, + "output_cost_per_token": 0.00000024, + "supports_system_messages": true }, "snowflake/llama3.2-1b": { "litellm_provider": "snowflake", @@ -29146,13 +30943,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/llama3.3-70b": { - "litellm_provider": "snowflake", + "snowflake/llama3.3-70b": { + "max_tokens": 16384, "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, "snowflake/mistral-7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, @@ -29167,12 +30968,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/mistral-large2": { + "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true }, "snowflake/mixtral-8x7b": { "litellm_provider": "snowflake", @@ -29209,13 +31015,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/snowflake-llama-3.3-70b": { + "snowflake/snowflake-llama-3.3-70b": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, "stability/sd3": { "litellm_provider": "stability", "mode": "image_generation", @@ -29558,6 +31368,11 @@ "litellm_provider": "tavily", "mode": "search" }, + "you_com/search": { + "input_cost_per_query": 0.0, + "litellm_provider": "you_com", + "mode": "search" + }, "text-completion-codestral/codestral-2405": { "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", @@ -30295,7 +32110,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { @@ -30423,8 +32237,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -30456,23 +32269,24 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, - "input_cost_per_token_above_200k_tokens": 6.6e-06, - "output_cost_per_token_above_200k_tokens": 2.475e-05, - "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "cache_creation_input_token_cost": 4.5e-06, + "cache_creation_input_token_cost_above_1hr": 7.2e-06, + "cache_read_input_token_cost": 3.6e-07, + "input_cost_per_token": 3.6e-06, + "input_cost_per_token_above_200k_tokens": 7.2e-06, + "output_cost_per_token_above_200k_tokens": 2.7e-05, + "cache_creation_input_token_cost_above_200k_tokens": 9.0e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, + "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -30482,11 +32296,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, + "cache_creation_input_token_cost_above_1hr": 2.2e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", @@ -30504,7 +32318,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true }, "us.anthropic.claude-opus-4-20250514-v1:0": { @@ -30530,8 +32343,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, @@ -30558,8 +32370,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -30586,8 +32399,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -30613,8 +32427,9 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high" }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -30643,8 +32458,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "us.deepseek.r1-v1:0": { "input_cost_per_token": 1.35e-06, @@ -31192,7 +33006,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_output_config": true }, "vercel_ai_gateway/anthropic/claude-opus-4.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -31212,7 +33027,7 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "vercel_ai_gateway/anthropic/claude-sonnet-4": { "cache_creation_input_token_cost": 3.75e-06, @@ -31365,7 +33180,8 @@ "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_image_size": false }, "vercel_ai_gateway/google/gemini-2.5-pro": { "input_cost_per_token": 2.5e-06, @@ -32132,6 +33948,7 @@ }, "vertex_ai/claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32153,6 +33970,7 @@ }, "vertex_ai/claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32203,6 +34021,7 @@ }, "vertex_ai/claude-3-7-sonnet@20250219": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-05-11", "input_cost_per_token": 3e-06, @@ -32220,8 +34039,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "vertex_ai/claude-3-haiku": { "input_cost_per_token": 2.5e-07, @@ -32303,6 +34121,7 @@ }, "vertex_ai/claude-opus-4": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", @@ -32324,11 +34143,11 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "vertex_ai/claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, @@ -32346,6 +34165,7 @@ }, "vertex_ai/claude-opus-4-1@20250805": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, @@ -32363,6 +34183,7 @@ }, "vertex_ai/claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32385,10 +34206,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_output_config": true }, "vertex_ai/claude-opus-4-5@20251101": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32411,11 +34233,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_native_streaming": true + "supports_native_streaming": true, + "supports_output_config": true }, "vertex_ai/claude-opus-4-6": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32438,12 +34261,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true, + "supports_max_reasoning_effort": true }, "vertex_ai/claude-opus-4-6@default": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32466,12 +34289,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_output_config": true, + "supports_max_reasoning_effort": true }, "vertex_ai/claude-opus-4-7": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32492,15 +34315,15 @@ "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, - "tool_use_system_prompt_tokens": 346, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_max_reasoning_effort": true }, "vertex_ai/claude-opus-4-7@default": { "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32521,15 +34344,135 @@ "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, - "tool_use_system_prompt_tokens": 346, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_max_reasoning_effort": true + }, + "vertex_ai/claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true + }, + "vertex_ai/claude-fable-5@default": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true + }, + "vertex_ai/claude-opus-4-8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true + }, + "vertex_ai/claude-opus-4-8@default": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true }, "vertex_ai/claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, @@ -32556,6 +34499,7 @@ }, "vertex_ai/claude-sonnet-4-6": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -32571,18 +34515,19 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "vertex_ai/claude-sonnet-4-5@20250929": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, @@ -32610,6 +34555,7 @@ }, "vertex_ai/claude-opus-4@20250514": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", @@ -32631,11 +34577,11 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "vertex_ai/claude-sonnet-4": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, @@ -32661,11 +34607,11 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "vertex_ai/claude-sonnet-4@20250514": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, @@ -32691,8 +34637,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159 + "supports_vision": true }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -32874,7 +34819,8 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": false, - "tpm": 8000000 + "tpm": 8000000, + "supports_image_size": false }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -32961,6 +34907,73 @@ }, "web_search_billing_unit": "per_query" }, + "vertex_ai/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -33458,6 +35471,22 @@ "us-central1" ] }, + "vertex_ai/google/gemma-4-26b-a4b-it-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", + "supported_regions": [ + "global" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "vertex_ai/openai/gpt-oss-120b-maas": { "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", @@ -34478,7 +36507,8 @@ "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-3-beta": { "cache_read_input_token_cost": 7.5e-07, @@ -34677,7 +36707,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -34694,7 +36725,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-0709": { "input_cost_per_token": 3e-06, @@ -34710,7 +36742,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-latest": { "input_cost_per_token": 3e-06, @@ -34768,7 +36801,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-1-fast-reasoning-latest": { "cache_read_input_token_cost": 5e-08, @@ -34789,7 +36823,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-1-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -34809,7 +36844,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-1-fast-non-reasoning-latest": { "cache_read_input_token_cost": 5e-08, @@ -34829,7 +36865,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4.20-multi-agent-beta-0309": { "cache_read_input_token_cost": 2e-07, @@ -34897,6 +36934,48 @@ "supports_vision": true, "supports_web_search": true }, + "xai/grok-4.3": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4.3-latest": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "xai/grok-beta": { "input_cost_per_token": 5e-06, "litellm_provider": "xai", @@ -34938,7 +37017,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2026-05-15" }, "xai/grok-code-fast-1-0825": { "cache_read_input_token_cost": 2e-08, @@ -34953,7 +37033,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2026-05-15" }, "xai/grok-vision-beta": { "input_cost_per_image": 5e-06, @@ -34985,12 +37066,12 @@ }, "zai.glm-5": { "input_cost_per_token": 1e-06, - "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 3.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -35011,6 +37092,20 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "zai.glm-5": { + "input_cost_per_token": 1e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "zai/glm-5": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2e-07, @@ -38785,7 +40880,7 @@ ] }, "gpt-4o-mini-transcribe-2025-03-20": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38797,7 +40892,7 @@ ] }, "gpt-4o-mini-transcribe-2025-12-15": { - "input_cost_per_audio_token": 3e-06, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, @@ -38917,6 +41012,23 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-realtime-whisper": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "openai", + "mode": "audio_transcription", + "source": "https://platform.openai.com/docs/models/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "sora-2": { "litellm_provider": "openai", "mode": "video_generation", @@ -39553,6 +41665,7 @@ }, "vertex_ai/claude-sonnet-4-6@default": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", @@ -39568,15 +41681,15 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_minimal_reasoning_effort": true + "supports_output_config": true }, "duckduckgo/search": { "litellm_provider": "duckduckgo", @@ -39640,6 +41753,46 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/openai.gpt-5.5": { + "input_cost_per_token": 5.5e-06, + "cache_read_input_token_cost": 5.5e-07, + "output_cost_per_token": 3.3e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/openai.gpt-5.4": { + "input_cost_per_token": 2.75e-06, + "cache_read_input_token_cost": 2.75e-07, + "output_cost_per_token": 1.65e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-pro-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, @@ -39792,6 +41945,20 @@ } ] }, + "zai.glm-5": { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, @@ -39820,8 +41987,48 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "minimax.minimax-m2.5": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-east-1/minimax.minimax-m2.5": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-west-2/minimax.minimax-m2.5": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_1hr": 2.4e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", @@ -39839,12 +42046,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost_above_1hr": 2.4e-06, "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", @@ -39862,10 +42069,354 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true }, + "snowflake/claude-sonnet-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-sonnet-4-6": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-opus": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "cache_read_input_token_cost": 0.0000005, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/claude-haiku-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "cache_read_input_token_cost": 0.0000001, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-3-7-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-4.1": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000008, + "cache_read_input_token_cost": 0.0000005, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 0.000000125, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-mini": { + "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.0000012, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-nano": { + "max_tokens": 16384, + "max_input_tokens": 5000000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.0000006, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/llama4-maverick": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000024, + "output_cost_per_token": 0.00000097, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, + "snowflake/snowflake-arctic-embed-l-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 0.00000007, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "snowflake/snowflake-arctic-embed-m-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 0.00000007, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "soniox/stt-async-v4": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 0.0000277778, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "supports_audio_input": true + }, + "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3.6-27B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/moonshotai/Kimi-K2.6": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 9.6e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/MiniMaxAI/MiniMax-M2.5": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/google/gemma-4-31B-it": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-120b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-20b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + } + , "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 1.4e-08, @@ -39916,4 +42467,4 @@ "supports_tool_choice": true, "supports_vision": false } -} \ No newline at end of file +}