From b2d38a1323016c1898d2633a49e7c7305fd7bad3 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Mon, 14 Apr 2025 12:06:23 -0700 Subject: [PATCH] build(model_prices_and_context_window.json): add gpt-4.1 pricing --- ...odel_prices_and_context_window_backup.json | 44 +++++++++++++++++++ model_prices_and_context_window.json | 44 +++++++++++++++++++ 2 files changed, 88 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4795c6d862..762984dec9 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -64,6 +64,50 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-4.1": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 1e-6, + "litellm_provider": "openai", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4.1-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 1e-6, + "litellm_provider": "openai", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gpt-4o": { "max_tokens": 16384, "max_input_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 4795c6d862..762984dec9 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -64,6 +64,50 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-4.1": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 1e-6, + "litellm_provider": "openai", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4.1-2025-04-14": { + "max_tokens": 32768, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "input_cost_per_token": 2e-6, + "output_cost_per_token": 8e-6, + "input_cost_per_token_batches": 1e-6, + "output_cost_per_token_batches": 4e-6, + "cache_read_input_token_cost": 1e-6, + "litellm_provider": "openai", + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gpt-4o": { "max_tokens": 16384, "max_input_tokens": 128000,