API Reference
Rate Limits
The API enforces a fixed-window rate limit per API key to ensure fair use.
Default limits
| Limit | Default |
|---|---|
| Requests per window | 100 |
| Window size | 60 seconds |
These values may be adjusted in a future release.
Rate limit headers
Every API response includes headers indicating your current usage:
X-RateLimit-Limit: 100
X-RateLimit-Remaining: 87
X-RateLimit-Reset: 1716912060
| Header | Description |
|---|---|
X-RateLimit-Limit | Maximum requests allowed per window |
X-RateLimit-Remaining | Requests remaining in the current window |
X-RateLimit-Reset | Unix timestamp (seconds) when the window resets |
Handling 429 responses
When you exceed the limit, you receive a 429 Too Many Requests response:
{
"error": {
"code": "RATE_LIMITED",
"message": "Rate limit exceeded. Try again after 1716912060."
}
}Read the X-RateLimit-Reset header and wait until that timestamp before retrying.
Best practices
- Cache responses where possible — model schemas don't change frequently
- Use
X-RateLimit-Remainingto back off proactively before hitting 0 - For bulk operations, add a small delay between requests (e.g. 100ms)