InferenceRate Limiting

Rate Limiting

The gateway enforces sliding-window rate limits per authentication method.

Per-minute limits

Set by how the request authenticates. Your credit balance does not change them.

Auth methodRate limit
API key60 req/min
Session30 req/min
SpendAuth120 req/min
Anonymous10 req/min

Daily caps

Set by credit balance, independent of the per-minute limit above.

CallerDaily limit
Anonymous (no auth)5 req/day
Authenticated, zero credits20 req/day
Any creditsUnlimited

Response headers

Every response includes rate limit headers:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 42
X-RateLimit-Reset: 1712793600

429 responses

When rate limited:

{
  "error": {
    "message": "Rate limit exceeded for this API key.",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

The X-RateLimit-Reset header indicates when the window resets (Unix timestamp in seconds).