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

Rate Limit

Rate Limiting Rules

Dimension
Rule

Scope

Per API Key

Monthly quota

100,000 requests per month

Request frequency

20 requests per minute

Response Headers

Header
Description

X-RateLimit-Limit

Maximum requests allowed in the current minute window

X-RateLimit-Remaining

Remaining requests available in the current minute window

X-RateLimit-Reset

Reset time of the current minute window (Unix millisecond timestamp)

Rate Limit Exceeded

When the rate limit is triggered, a 429 Too Many Requests response is returned:

{
    "code": 42901,
    "message": "Rate limit exceeded",
    "details": {
        "limit": 20,
        "window": "60s",
        "retry_after": 45
    }
}

Last updated