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

# Rate Limits

> Understanding and handling rate limits

## Overview

TokenLab implements rate limits to ensure fair usage and platform stability. Limits vary by account tier.

## Rate Limit Tiers

| Tier        | Requests/min | Description                   |
| ----------- | ------------ | ----------------------------- |
| **User**    | 1,000        | Default tier for all accounts |
| **Partner** | 10,000       | For integration partners      |
| **VIP**     | 10,000       | High-volume users             |

<Note>
  Rate limits are subject to change. Contact [support@tokenlab.sh](mailto:support@tokenlab.sh) for custom limits.
</Note>

## Rate Limit Response

When you exceed the rate limit, the API returns a `429` status code with a `Retry-After` header indicating how long to wait before retrying.

## Rate Limit Exceeded

When you exceed the limit, you'll receive a `429` response:

```json theme={null}
{
  "error": {
    "message": "Rate limit exceeded. Please retry later.",
    "type": "rate_limit_exceeded",
    "code": "rate_limit_exceeded"
  }
}
```

The response includes a `Retry-After` header:

```
Retry-After: 60  # Seconds to wait before retrying
```

## Handling Rate Limits

### Exponential Backoff

Implement exponential backoff for automatic retries:

```python theme={null}
import time
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.tokenlab.sh/v1"
)

def make_request_with_backoff(messages, max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="gpt-4o",
                messages=messages
            )
        except RateLimitError as e:
            if attempt == max_retries - 1:
                raise

            wait_time = 2 ** attempt  # 1, 2, 4, 8, 16 seconds
            print(f"Rate limited. Waiting {wait_time}s...")
            time.sleep(wait_time)
```

### Request Queuing

For high-volume applications, implement a request queue:

```python theme={null}
import asyncio
from collections import deque

class RateLimitedClient:
    def __init__(self, requests_per_minute=1000):
        self.rpm = requests_per_minute
        self.interval = 60 / requests_per_minute
        self.last_request = 0

    async def request(self, messages):
        # Wait if needed to respect rate limit
        now = asyncio.get_event_loop().time()
        wait_time = max(0, self.last_request + self.interval - now)
        if wait_time > 0:
            await asyncio.sleep(wait_time)

        self.last_request = asyncio.get_event_loop().time()
        return await self.client.chat.completions.create(
            model="gpt-4o",
            messages=messages
        )
```

### Batch Processing

For bulk operations, process in batches with delays:

```python theme={null}
def process_batch(items, batch_size=50, delay=1):
    results = []
    for i in range(0, len(items), batch_size):
        batch = items[i:i + batch_size]
        for item in batch:
            result = client.chat.completions.create(
                model="gpt-4o",
                messages=[{"role": "user", "content": item}]
            )
            results.append(result)
        time.sleep(delay)  # Pause between batches
    return results
```

## Best Practices

<AccordionGroup>
  <Accordion title="Monitor your usage">
    Track rate limit headers to stay under limits proactively.
  </Accordion>

  <Accordion title="Implement caching">
    Cache responses for identical requests to reduce API calls.
  </Accordion>

  <Accordion title="Use appropriate models">
    Faster models (like gpt-5-mini) allow more throughput.
  </Accordion>

  <Accordion title="Contact us for higher limits">
    If you need higher limits, contact [support@tokenlab.sh](mailto:support@tokenlab.sh).
  </Accordion>
</AccordionGroup>

## Upgrading Your Tier

To request a tier upgrade:

1. Log in to your [Dashboard](https://tokenlab.sh/dashboard)
2. Go to **Settings → Account**
3. Contact support with your use case

Or email [support@tokenlab.sh](mailto:support@tokenlab.sh) with:

* Your account email
* Expected request volume
* Use case description