Docs / Limits & pricing

Rate limits

Limits are per organization and shared by all its keys and the Playground: requests per second and input tokens per second. Each allows a one-second burst. See your current limits under API Keys → Rate limits.

Over a limit the API answers 429 with a Retry-After header (seconds). Back off and retry. Every response carries x-ratelimit-limit-requests and x-ratelimit-limit-tokens.

{
  "detail": "Rate limit exceeded (requests per second). Back off and retry after 1s."
}