> ## Documentation Index
> Fetch the complete documentation index at: https://docs.icelake.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Errors & rate limits

> OpenAI-style error envelopes, status codes, and response headers.

## Error shape

```json theme={null}
{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": "invalid_api_key",
    "param": null
  }
}
```

## Status codes

| Status | Meaning                               |
| ------ | ------------------------------------- |
| `401`  | Missing or invalid API key / session  |
| `402`  | Insufficient credits or plan required |
| `403`  | Key missing required scope            |
| `404`  | Model not found                       |
| `429`  | Rate limited                          |
| `502`  | Upstream inference failure            |

## Response headers

| Header                           | Meaning                             |
| -------------------------------- | ----------------------------------- |
| `x-request-id`                   | Correlation id for support          |
| `x-ratelimit-limit-requests`     | Configured RPM                      |
| `x-ratelimit-remaining-requests` | Remaining in window (when enforced) |
| `x-icelake-balance-credits`      | Credit balance                      |
| `x-icelake-model-id`             | Resolved public model id            |

Log `x-request-id` on failures when contacting support.