/v1/responses endpoint, you can calibrate model reasoning depth using the reasoning parameter through the official OpenAI SDK.
Configuring Reasoning Effort
Use thereasoning parameter (or extra_body={"reasoning": ...} in Python) to specify the model thinking budget.
Accessing Reasoning Trace and Token Accounting
When routing to dedicated reasoning models such asdeepseek-r1, inspect internal reasoning token usage via usage.completion_tokens_details.