diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 28dec7cce90..f9acea81a1c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -11432,9 +11432,9 @@ }, "openrouter/anthropic/claude-sonnet-4": { "supports_computer_use": true, - "max_tokens": 8192, + "max_tokens": 64000, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "input_cost_per_image": 0.0048, diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml index b48fe5be1c3..c7bf8cdb0ab 100644 --- a/litellm/proxy/_new_secret_config.yaml +++ b/litellm/proxy/_new_secret_config.yaml @@ -4,6 +4,15 @@ model_list: model: openai/fake api_key: fake-key api_base: https://exampleopenaiendpoint-production.up.railway.app/ + - model_name: gpt-5-mini + litellm_params: + model: azure/gpt-5-mini + api_base: os.environ/AZURE_GPT_5_MINI_API_BASE # runs os.getenv("AZURE_API_BASE") + api_key: os.environ/AZURE_GPT_5_MINI_API_KEY # runs os.getenv("AZURE_API_KEY") + stream_timeout: 60 + merge_reasoning_content_in_choices: true + model_info: + mode: chat litellm_settings: cache: true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 28dec7cce90..f9acea81a1c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -11432,9 +11432,9 @@ }, "openrouter/anthropic/claude-sonnet-4": { "supports_computer_use": true, - "max_tokens": 8192, + "max_tokens": 64000, "max_input_tokens": 200000, - "max_output_tokens": 8192, + "max_output_tokens": 64000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "input_cost_per_image": 0.0048,