Rate Limits
Request rate limits by plan tier.
All API endpoints enforce per-minute rate limits based on your subscription plan. When exceeded, the API returns 429 Too Many Requests.
Limits by Plan
| Operation | Starter | Pro | Enterprise |
|---|---|---|---|
| Agent queries | 20/min | 50/min | 120/min |
| Chat sessions | 20/min | 50/min | 120/min |
| KB operations | 60/min | 150/min | 300/min |
| API key CRUD | 100/min | 100/min | 100/min |
Rate Limit Headers
Every response includes rate limit headers:
| Header | Description |
|---|---|
X-RateLimit-Limit | Maximum requests per window |
X-RateLimit-Remaining | Requests remaining in current window |
X-RateLimit-Reset | Unix timestamp when the window resets |
Handling Rate Limits
When you receive a 429 response, wait until the reset time before retrying. Implement exponential backoff for production integrations.
{
"error": "rate_limit_exceeded",
"message": "Too many requests. Please retry after 2026-03-09T12:01:00Z",
"retry_after": 60
}