Rate limits
The default is 60 requests per minute and 5 concurrent requests per key. An administrator can set different limits for each key.
Response headers
Every /v1 response carries these headers:
| Header | Meaning |
|---|---|
X-RateLimit-Limit | Request limit per minute for this key. |
X-RateLimit-Remaining | Requests left in the current window. |
X-RateLimit-Reset | Reset time in epoch seconds. |
X-RateLimit-Concurrency | Concurrent request limit. |
429 codes
| Code | Meaning |
|---|---|
RATE_LIMIT_EXCEEDED | Requests per minute exceeded the limit. The body also carries limit, remaining, and retry_after. |
RATE_LIMIT_CONCURRENCY_EXCEEDED | Concurrent requests exceeded the limit. |
RATE_LIMIT_IP_EXCEEDED | The per-IP limit was exceeded. The response carries a Retry-After header. |
Still haven't found the answer? Try it directly in Playground or view the list of active models.