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

# Rate limits

> Learn about Anyone request rate limits and how to handle them.

To ensure service stability, Anyone enforces rate limits on API requests.

## Rate limit rules

* Each token has a **requests per minute** limit
* Different models may have different rate limits
* Exceeding the limit results in a `429 Too Many Requests` error

## What to do when rate limited

When you receive a 429 error:

```json theme={null}
{
  "error": {
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}
```

**How to handle it:**

1. **Wait and retry** — the `Retry-After` response header tells you how many seconds to wait
2. **Use exponential backoff** — double the delay between each retry (1s → 2s → 4s → 8s)
3. **Control concurrency** — reduce the number of simultaneous requests

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

def call_with_retry(client, max_retries=3, **kwargs):
    for i in range(max_retries):
        try:
            return client.chat.completions.create(**kwargs)
        except openai.RateLimitError:
            wait = 2 ** i  # exponential backoff
            time.sleep(wait)
    raise Exception("Max retries exceeded")
```

## Increasing your limit

If the default limit isn't enough, you can:

* Top up more credits (higher balance generally means more generous limits)
* Contact support to request a higher limit

<Tip>
  The smart approach is to implement retry logic in your client, rather than assuming requests will never be rate limited.
</Tip>