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

# NVIDIA

> Integrate with NVIDIA NIM as an AI Provider

Add your NVIDIA NIM endpoints to begin accessing your models in Arize AX's prompt playground.

<Note>
  By adding this integration, your data may be sent to your NVIDIA deployment for certain actions within Arize AX (e.g., prompt playground) and your account may be billed for usage.
</Note>

## Add the Integration Using the Arize Skills

Add an NVIDIA NIM integration from your coding agent using the [Arize Skills](/ax/agents/arize-skills):

<Prompt description="Create an NVIDIA integration named 'my-nvidia-nim' with my base URL https://integrate.api.nvidia.com/v1/ and API key nvapi-...">
  Create an NVIDIA integration named 'my-nvidia-nim' with my base URL [https://integrate.api.nvidia.com/v1/](https://integrate.api.nvidia.com/v1/) and API key nvapi-...
</Prompt>

## Add the Integration from Arize AX

### Select NVIDIA from the Providers List

<Frame caption="The AI Provider integrations tab">
  ![The AI Provider integrations tab](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-nvidia.png)
</Frame>

### Fill Out Your Integration Details

<Frame caption="The NVIDIA integration configuration pane">
  ![The AI integration details tab](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-nvidia-details.png)
</Frame>

Give your integration a name. Then set your base URL and API key from your NVIDIA NIM account. If you are using the default API at `https://integrate.api.nvidia.com/v1/` then you don't need to set the base URL.

> Enter the base URL including the version path (e.g., `https://integrate.api.nvidia.com/v1/`). **Do not** include endpoint paths like `/chat/completions` as these are appended automatically.

If you need to send any extra headers to every request, set these.

You then need to define the available model deployments. If you have the default NVIDIA models available then you can enable NVIDIA default models. Otherwise add your deployment name as a custom model name.

### Advanced Settings

<Frame caption="The Advanced Settings configuration pane">
  ![The AI integration details tab](https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/ai-integration-providers-advanced-settings.png)
</Frame>

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.