Core concepts

Rate limits

Per-key request rate limiting and how to handle 429s.

The limit

Each API key is limited to 10 requests per second.

Handling 429s

Exceeding the limit returns 429 Too Many Requests with error code rate_limit_exceeded and a Retry-After header telling you how many whole seconds to wait.

http
HTTP/1.1 429 Too Many Requests
Retry-After: 1

{ "error": { "message": "Rate limit exceeded. Slow down and retry.", "code": "rate_limit_exceeded" } }

Handle it by backing off and retrying after the Retry-After interval, ideally with exponential backoff and jitter for repeated hits.