For the complete documentation index, see llms.txt. This page is also available as Markdown.

Rate Limiting

The API uses a leaky bucket algorithm to control request rates. Each authenticated user has a bucket with a capacity of 60 requests. The bucket leaks at a rate of 4 requests per second.

When a request is made, it is added to the bucket. If the bucket is full, the API responds with a 429 Too Many Requests status.

Response Headers

Every response includes rate limit headers:

Header
Description

X-RateLimit-Limit

Maximum number of requests (bucket capacity)

X-RateLimit-Remaining

Number of requests remaining in the bucket

When rate limited (429), additional headers are included:

Header
Description

Retry-After

Seconds to wait before retrying

X-RateLimit-Reset

Unix timestamp when the bucket resets

Last updated