To protect against abuse and ensure fair access to the API, we enforce rate-limiting restrictions on all of the resources. We measure rate limits in two ways: RPS (requests per second). Limits are measured per organization (account), not for the models.
If you hit a rate limit, the API will refuse to fulfill further requests until a short amount of time has passed.
We are currently working on our infrastructure to increase the default rate limits. If you're interested in increasing the limits faster or need even more, don't hesitate to contact us at [[email protected]]().
| Default Rate Limits | |
|---|---|
| RPS - requests per second | 5 |