> For the complete documentation index, see [llms.txt](https://docs.raga.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raga.ai/ragaai-catalyst/concepts/enable-custom-gateway.md).

# Enable Custom Gateway

Run metric evaluations on your own LLM models, even if you use a custom gateway.

### Via UI:

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2FkZLlNKXKJra0oJQCUrqS%2F4.workdaycustomgatewayconfig-ezgif.com-video-to-gif-converter%20(1).gif?alt=media&amp;token=cf5ed901-856f-44c4-bcca-54f0a64ae5b4" alt=""><figcaption></figcaption></figure>

To enable your custom LLM gateway for metric evaluations on RagaAI Catalyst, you need to follow these steps:

1. Navigate to Settings -> API Keys and scroll down to the **Custom Parameters** section.
2. Enter the relevant deployment values for the following two custom key parameters:
   1. api\_base - Your relevant server link
   2. model - Name of the model to be used for metric evaluation
3. Click "Add" to save the variables within your Catalyst instance

You are now ready to run evaluations using this gateway. Simply choose "custom\_gateway" in the dropdown for "Model" when triggering your metric evaluations (learn how to run an evaluation here).

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2FSx8qaBAO3eBQv7M5Vo9u%2Fimage.png?alt=media&amp;token=0ded2540-63d4-4f6c-b851-07ab4ba588b6" alt=""><figcaption></figcaption></figure>

### Via SDK:

This action is currently supported on the UI only.