---
title: xAI (Grok)
slug: guides/server/providers/xai
---
<Tip>To enable xAI (Grok) models with Letta, set `XAI_API_KEY` in your environment variables. </Tip>

## Enabling xAI (Grok) models
To enable the xAI provider, set your key as an environment variable:
```bash
export XAI_API_KEY="..."
```
Now, xAI models will be enabled with you run `letta run` or start the Letta server.

### Using the `docker run` server with xAI
To enable xAI models, simply set your `XAI_API_KEY` as an environment variable:
```bash
# replace `~/.letta/.persist/pgdata` with wherever you want to store your agent data
docker run \
  -v ~/.letta/.persist/pgdata:/var/lib/postgresql/data \
  -p 8283:8283 \
  -e XAI_API_KEY="your_xai_api_key" \
  letta/letta:latest
```

<Accordion icon="square-terminal" title="CLI (pypi only)">
### Using `letta run` and `letta server` with xAI
To chat with an agent, run:
```bash
export XAI_API_KEY="sk-ant-..."
letta run
```
This will prompt you to select an xAI model.
```
? Select LLM model: (Use arrow keys)
 » letta-free [type=openai] [ip=https://inference.letta.com]
   grok-2-1212 [type=xai] [ip=https://api.x.ai/v1]
```
To run the Letta server, run:
```bash
export XAI_API_KEY="..."
letta server
```
To select the model used by the server, use the dropdown in the ADE or specify a `LLMConfig` object in the Python SDK.
</Accordion>

## Configuring xAI (Grok) models

When creating agents, you must specify the LLM and embedding models to use. You can additionally specify a context window limit (which must be less than or equal to the maximum size). Note that xAI does not have embedding models, so you will need to use another provider.

```python
from letta_client import Letta

client = Letta(base_url="http://localhost:8283")

agent = client.agents.create(
    model="xai/grok-2-1212",
    embedding="openai/text-embedding-3-small",
    # optional configuration
    context_window_limit=30000
)
```
xAI (Grok) models have very large context windows, which will be very expensive and high latency. We recommend setting a lower `context_window_limit` when using xAI (Grok) models.