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

# Retries

> When an LLM call fails, our system detects the error and retries the request to prevent failovers.

There are 2 ways to enable Retries and set the number of retries and the time to wait before retrying:

## Add it from the UI

Go to the [Retries page](https://platform.keywordsai.co/platform/api/retries) and enable retries and set the number of retries and the initial retry time.

<Frame>
  <img height="200" width="500" src="https://mintcdn.com/keywordsai/2wmUpdE2X_JopYHH/images/api-features/retries.png?fit=max&auto=format&n=2wmUpdE2X_JopYHH&q=85&s=c77937e1f740f8a6015a22e90422131a" alt="Retries Page" data-path="images/api-features/retries.png" />
</Frame>

## Add it in code

You can also add the retry parameters in the request body to enable retries and set the number of retries and the time to wait before retrying.

```json theme={"system"}
{
// ...some other Keywords AI params...
    "retry_params": {
        "num_retries": 3,
        "retry_after": 0.1,  // seconds, minimum time to wait before retry.
        "retry_enabled": true
    }
}
```

## Supported parameters

<ResponseField name="retry_params" type="object">
  Enable or disable retries and set the number of retries and the time to wait before retrying.

  <Accordion title="Properties">
    <ResponseField name="retry_enabled" type="boolean" required>
      Enable or disable retries.
    </ResponseField>

    <ResponseField name="num_retries" type="number">
      The number of retries to attempt.
    </ResponseField>

    <ResponseField name="retry_after" type="number">
      The time to wait before retrying in seconds.
    </ResponseField>
  </Accordion>
</ResponseField>