> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gately.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Rate Limits
> Understanding API rate limits and best practices for Gately AI LLM services
## Understanding Rate Limits
Each account has a default rate limit of **300 Requests Per Minute (RPM) Per Model**.
Rate limits control how frequently users can make requests to our LLM API within specific time periods. These limits help ensure fair resource distribution and maintain service stability.
Protect against API misuse and abuse
Ensure fair resource distribution
Maintain consistent API performance
## Rate Limit Details
| Limit Type | Value | Period |
| ------------------- | ----- | -------- |
| Per Model | 300 | 1 minute |
| Concurrent Requests | 5 | At once |
When you exceed the rate limit, you'll receive:
```json theme={null}
{
"error": {
"status": 429,
"message": "Too Many Requests",
"detail": "Rate limit exceeded. Please try again in {X} seconds"
}
}
```
## Best Practices
Add rate limiting in your application code to stay within limits:
```typescript theme={null}
const rateLimiter = new RateLimiter({
requests: 300,
period: '1m'
});
```
Implement retry logic with increasing delays:
```typescript theme={null}
const backoff = (attempt) => Math.min(1000 * Math.pow(2, attempt), 10000);
```
Track your API usage through our dashboard:
[View Usage Stats](https://app.gately.ai/dashboard/home)
## Handling Rate Limits
When you receive a 429 error, implement these handling strategies:
1. **Retry Later**: Wait for the specified cooldown period
2. **Optimize Requests**: Batch operations when possible
3. **Monitor Usage**: Track your consumption patterns
## Increasing Rate Limits
Join our Discord community for immediate assistance
Book a call with our sales team for custom limits
Repeatedly exceeding rate limits may result in temporary account restrictions. Please monitor your usage and request limit increases if needed.