Rate limits

Rate limits cap how many requests the gateway accepts for a model in a minute. Fourier Health sets the limit for each model your organization can call, so limits are per model and per organization. The same limit applies to every key in the organization.

How a limit applies

Limits are in requests per minute, per model, for your whole organization. A request over the limit gets status 429 with code rate_limited and a retry-after header that says how many seconds to wait.

Where to see your limit

Every response that reached the rate limiter carries x-ratelimit-limit, x-ratelimit-remaining, and x-ratelimit-reset headers. For the headers in detail and how to retry, see Rate limits in the API reference. To see your request volume over time, open the Usage page.

Request access or a limit change

To get access to a model, or to change the limit for one, contact Fourier Health. Include your organization’s name, the model, and the request rate you need. A change takes effect immediately for every key in the organization.