Request IDs and error tracing in production

Tip for anyone running OpenAI API calls in production: always log the request ID from response headers.

response = client.chat.completions.with_raw_response.create(
    model="gpt-4o",
    messages=[...]
)
request_id = response.headers.get("x-request-id")
print(f"Request ID: {request_id}")
parsed = response.parse()

When you contact OpenAI support about an issue, they can look up exactly what happened with this ID. Saved us hours of debugging.