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

Rate Limiting

Parameter
Value

Max Requests

60 per minute

Window

60 seconds

Idempotency Window

10-second deduplication window

Rate Limit Response:

{
  "status": 429,
  "message": "Too many request"
}

Idempotency Violation Response:

{
  "status": 429,
  "message": "Too Many Requests",
  "retryAfter": 5
}

Last updated