diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ff7b6b36dc8..c7fabb0ed9f 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -15702,7 +15702,8 @@ "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "deepinfra/google/gemini-2.0-flash-001": { "max_tokens": 1000000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index ff7b6b36dc8..c7fabb0ed9f 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -15702,7 +15702,8 @@ "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true }, "deepinfra/google/gemini-2.0-flash-001": { "max_tokens": 1000000, diff --git a/tests/test_litellm/llms/deepinfra/test_deepinfra_chat_transformation.py b/tests/test_litellm/llms/deepinfra/test_deepinfra_chat_transformation.py index b2e9afb0c19..fc8cf6dc60f 100644 --- a/tests/test_litellm/llms/deepinfra/test_deepinfra_chat_transformation.py +++ b/tests/test_litellm/llms/deepinfra/test_deepinfra_chat_transformation.py @@ -17,6 +17,10 @@ def test_deepseek_supported_openai_params(): """ from litellm.llms.deepinfra.chat.transformation import DeepInfraConfig + # Ensure we're using the local model cost map + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + supported_openai_params = DeepInfraConfig().get_supported_openai_params(model="deepinfra/deepseek-ai/DeepSeek-V3.1") print(supported_openai_params) assert "reasoning_effort" in supported_openai_params