Platform

Rate Limits

Rate limits are applied per account, across all API keys and all models. The default is 60 requests per minute, enforced as a sliding 60-second window. There is no token-per-minute cap at launch.

HeaderMeaning
X-RateLimit-LimitMax requests per minute on this account
X-RateLimit-RemainingRequests left in the current 60-second window
X-RateLimit-ResetUnix timestamp when the window resets
Retry-AfterSeconds to wait before retrying (only on 429 responses)

When you exceed the limit, the API returns a 429 with a Retry-After header. Higher limits are available on Enterprise — contact sales to negotiate.