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

# xAI

> Use xAI Grok models through the ngrok AI Gateway.

[xAI](https://x.ai) builds the Grok family of models.

xAI supports Chat Completions and Responses requests.
Responses requests to xAI aren't stored, so `previous_response_id` isn't available. Send the full conversation in each request.

<Note>
  xAI is a **built-in provider** you can pay for with credits, so a provider key is optional.
  Add your own xAI key to bill usage to your xAI account instead of your ngrok.ai credits.
</Note>

## Setup

<Steps>
  <Step title="Create an access key and add credits">
    Follow the [quickstart](/docs/ai-gateway/quickstart) to create an access key and purchase [credits](/docs/ai-gateway/concepts/credits) in [app.ngrok.ai](https://app.ngrok.ai).
  </Step>

  <Step title="Store your xAI API key (optional)">
    Skip this step to pay with credits.
    To bring your own key, create an API key in your [xAI](https://x.ai) account. Then [add a provider key](/docs/ai-gateway/guides/attaching-provider-keys#add-a-provider-key) and [create an access key configuration](/docs/ai-gateway/guides/access-key-configurations#create-a-configuration) with an `xai` routing rule that uses it.
  </Step>

  <Step title="Send requests">
    Send requests with your access key:

    ```python theme={null}
    from openai import OpenAI

    client = OpenAI(
        base_url="https://gateway.ngrok.ai/v1",
        api_key="ng-xxxxx-g1-xxxxx",
    )

    response = client.chat.completions.create(
        model="grok-4.7",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    ```
  </Step>
</Steps>

## Available models

See the [model catalog](/docs/ai-gateway/reference/model-catalog#xai).

## Next steps

* [Provider keys](/docs/ai-gateway/guides/attaching-provider-keys)
* [Access key configurations](/docs/ai-gateway/guides/access-key-configurations)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.