Limits

Rate limits control how frequently clients can make requests.

Handle request rate limits

Serving requests are subject to rate limits, including per-IP limits and additional limits for individual endpoints. Organization-scoped limits keep other organizations' traffic separate from yours.

A request over an enforced limit returns HTTP 429 with a Retry-After header. Wait for that interval before retrying. Refused requests still count toward the applicable window, so repeated immediate retries do not help.

Request a higher limit

Contact Support if normal traffic regularly reaches a request cap.

For funding and balance controls, see Billing.