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

# Rate Limits

> Quota mechanism + client pacing.

Mirobody counts requests per **account × path × minute**. On overflow you get HTTP `429` with a `Retry-After` header (seconds).

```text theme={null}
HTTP/1.1 429 Too Many Requests
Retry-After: 47
```

## Recommended pacing

| Path                                                | Suggested RPM | Notes                                                             |
| --------------------------------------------------- | ------------- | ----------------------------------------------------------------- |
| `POST /v1/chat/completions`                         | ≤ 60          | Streaming calls count too; wait for one to finish before the next |
| `POST /v1/files`                                    | ≤ 30          | Batch where possible; OCR is compute-heavy                        |
| `POST /v1/data`                                     | ≤ 120         | Batch records into one request (up to 1000/batch)                 |
| `GET` reads (`/v1/data`, `/v1/files`, `/v1/models`) | ≤ 120         | —                                                                 |

<Note>
  Exact thresholds are injected per deployment. **Email [Mirobody Support](mailto:developer@thetahealth.ai) to confirm the limits for your account before going live.**
</Note>

## Client backoff

* On `429`, **respect `Retry-After`** — never retry immediately.
* Double the backoff after two consecutive `429`s, up to 5 minutes.
* Don't fire chat calls in parallel; let each stream complete first.