## Documentation Index

Fetch the complete documentation index at: [/docs/llms.txt](/content/docs/llms.txt)

Use this file to discover all available pages before exploring further.

Requests are rate-limited **per API key** on a fixed one-minute window.

##  Budget headers

Every `/v1` response carries your current budget:

| Header | Meaning |
| --- | --- |
| `X-RateLimit-Limit-Minute` | Your ceiling for the current one-minute window. |
| `X-RateLimit-Remaining-Minute` | Requests remaining in the current window. |
| `X-RateLimit-Reset` | Unix epoch seconds when the window resets. |

##  Exceeding the limit

When you exceed the limit, the API returns `429` with a `Retry-After` header (integer seconds to wait) and the standard error envelope:

```
{
  "error": {
    "code": "rate_limited",
    "message": "Per-minute rate limit exceeded."
  }
}
```

Build for back-off: when you receive a `429`, pause for `Retry-After` seconds before retrying. Watch `X-RateLimit-Remaining-Minute` to slow down before you hit the ceiling.