Skip to main content
Use models from your LiteLLM proxy in the prompt playground and evals.
By adding this integration, your data may be sent through your LiteLLM deployment to the underlying model provider for certain actions within Arize AX (e.g., prompt playground) and your account may be billed for usage.

​
Add the Integration Using the Arize Skills

Add a LiteLLM integration from your coding agent using the Arize Skills:

Create a LiteLLM integration named 'my-litellm' with my proxy URL and key sk-...

​
Add the Integration from Arize AX

​
Select LiteLLM from the Providers List

Navigate to Settings -> AI Providers and select LiteLLM.
The AI Provider integrations tab with the LiteLLM tile in the Get Started grid

The AI Provider integrations tab

​
Fill Out Your Integration Details

The LiteLLM integration details pane with name, API key, API base URL, extra headers, custom models, and test integration fields

The LiteLLM integration configuration pane

Enter a name, your API Key (a LiteLLM virtual key), and the API Base URL of your LiteLLM deployment, without /chat/completions.

​
Advanced Settings

The AI integration details tab

The Advanced Settings configuration pane

Expand the Advanced Settings section to configure the following:
  • Supports Function Calling - Turn this on to allow the integration to use function calling features. This is on by default.
  • Authorized Orgs - Configure which organizations have access to this integration.
  • Authorized Spaces - Configure which spaces have access to this integration.

​
Add the Integration

Finally check the box to agree to the terms and conditions, then select the Add Integration button to create the integration.