Rate limits
Region
Limits are per key, per region.
| Limit | Default |
|---|---|
| Requests per minute | 60 |
| Tokens per minute | 200k |
Default limits. Contact us to raise them.
Every response carries the current state:
Headers
x-ratelimit-limit-requests: 60
x-ratelimit-remaining-requests: 47
x-ratelimit-reset-requests: 12
retry-after: 12 # only on 429 and 503Over the limit, the request returns 429 with the code rate_limited. Wait for retry-after seconds and send it again.