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

# Rate Limits & Performance

## 1. Do image/video generation models have RPM limits?

Yes, RPM (requests per minute) limits vary by model:

* Veo 3.1: approximately 50 RPM
* Seedance: approximately 200 RPM
* Kling: depends on the specific model

## 2. Can I request an increase in RPM limits?

Yes. RPM upgrades can be flexibly arranged based on your usage needs. Please contact us with your requirements.

## 3. What happens if my actual usage doesn't reach the committed RPM?

If a user's actual RPM is continuously below the committed level for one week, the platform will adjust the rate limit according to the following policy (whichever is lower):

* Reduce the limit to the peak RPM from the past week
* Revert to the model's default rate limit

## 4. What should I do if I get a 429 "server overload" or "RPM limit exceeded" error?

This means you have hit a rate limit. For rate limits by model, please refer to: [https://docs.myrouter.ai/docs/model/llm-rate-limits](https://docs.myrouter.ai/docs/model/llm-rate-limits)

Temporary solutions:

* Reduce request frequency
* Implement exponential backoff retry in your code
* Contact support to increase your RPM quota based on your top-up amount

## 5. Model responses frequently time out?

Especially for image editing models like Gemini, processing time can be long (potentially 1-10 minutes). Suggestions:

* Set the timeout to 10 minutes or more
* Use asynchronous task mode (if applicable)
* Avoid calling resource-intensive tasks during peak hours

***

**Contact Support**

If the above FAQ does not resolve your issue, please contact technical support through the following channels:

* Email: [support@myrouter.ai](mailto:support@myrouter.ai)
* Please provide the following information:
  * Problem description + screenshots
  * Account ID (UUID)
  * Trace ID (if available, usually found in the error message)
  * Request parameters (with sensitive data redacted)