> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# xAI

> Learn how to use xAI with Agno.

xAI is a platform for providing endpoints for Large Language models.
See their list of models [here](https://docs.x.ai/docs/models).

We recommend experimenting to find the best-suited model for your use-case. The `grok-3` model is good for most use-cases.

## Authentication

Set your `XAI_API_KEY` environment variable. You can get one [from xAI here](https://console.x.ai/).

<CodeGroup>
  ```bash Mac theme={null}
  export XAI_API_KEY=sk-***
  ```

  ```bash Windows theme={null}
  setx XAI_API_KEY sk-***
  ```
</CodeGroup>

## Example

Use `xAI` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}

  from agno.agent import Agent
  from agno.models.xai import xAI

  agent = Agent(
      model=xAI(id="grok-3"),
      markdown=True
  )

  agent.print_response("Share a 2 sentence horror story.")
  ```
</CodeGroup>

## Live Search

xAI models support live search capabilities that can access real-time information:

<CodeGroup>
  ```python live_search.py theme={null}
  from agno.agent import Agent
  from agno.models.xai import xAI

  agent = Agent(
      model=xAI(
          id="grok-3",
          search_parameters={
              "mode": "on",
              "max_search_results": 20,
              "return_citations": True,
          },
      ),
      markdown=True,
  )

  agent.print_response("What's the latest news about AI developments?")
  ```
</CodeGroup>

<Note> View more examples [here](../examples/models/xai). </Note>

## Params

<Snippet file="model-xai-params.mdx" />

`xAI` also supports the params of [OpenAI](/reference/models/openai).