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

# Rate limits

> Request and token quotas per model

# Rate limits

<Note>
  Radium does not currently enforce public RPM, TPM, or concurrency limits. Rate-limit rules may be introduced in the future. This page describes the headers and retry patterns you should build into your integration so you're ready when limits take effect.
</Note>

## Current behavior

* **No fixed quotas** — Requests are evaluated on a best-effort basis.
* **Transient 429s may occur** — During traffic spikes or infrastructure maintenance, you may receive a `429 Too Many Requests` response. Treat these as retryable.
* **No rate-limit headers yet** — The `X-RateLimit-*` headers are reserved for future use and are not returned today.

## Recommended retry strategy

Use exponential backoff with jitter whenever you receive `429` or `503`:

```python theme={null}
import random
import time

def with_retry(fn, max_retries=5):
    for attempt in range(max_retries):
        try:
            return fn()
        except Exception as e:
            status = getattr(e, "status_code", None)
            if status in (429, 503) and attempt < max_retries - 1:
                delay = (2 ** attempt) + random.random()
                time.sleep(delay)
            else:
                raise
```

## Future headers

When rate limits are enabled, these headers will appear in every response:

| Header | Description |
| - | - |
| `X-RateLimit-Limit-Requests` | RPM limit for this key |
| `X-RateLimit-Remaining-Requests` | Requests remaining this minute |
| `X-RateLimit-Remaining-Tokens` | Tokens remaining this minute |
| `X-RateLimit-Reset` | Unix timestamp when limits reset |

## Contact

If you expect sustained high-volume traffic, [contact sales](https://radium.cloud/contact) so we can plan capacity together.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.