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

# xAI (Grok)

> Use xAI's Grok models through Prisma AIRS AI Gateway for chat completions, function calling, and vision capabilities.

## Quick Start

Get started with xAI in under 2 minutes:

<CodeGroup>
  ```sh cURL icon="square-terminal" theme={"system"}
  # 1. Add @x-ai provider in model catalog
  # 2. Use it:

  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -d '{
      "model": "@x-ai/grok-beta",
      "messages": [{"role": "user", "content": "Hello!"}]
    }'
  ```

  ```python OpenAI Py icon="python" theme={"system"}
  from openai import OpenAI

  # 1. Install: pip install openai
  # 2. Add @x-ai provider in model catalog
  # 3. Use it:

  client = OpenAI(
      api_key="PORTKEY_API_KEY",  # AI Gateway API key
      base_url="https://aigw.portkey.ai/v1"
  )

  response = client.chat.completions.create(
      model="@x-ai/grok-beta",
      messages=[{"role": "user", "content": "Hello!"}]
  )

  print(response.choices[0].message.content)
  ```

  ```js OpenAI JS icon="square-js" theme={"system"}
  import OpenAI from "openai"

  // 1. Install: npm install openai
  // 2. Add @x-ai provider in model catalog
  // 3. Use it:

  const client = new OpenAI({
      apiKey: "PORTKEY_API_KEY",  // AI Gateway API key
      baseURL: "https://aigw.portkey.ai/v1"
  })

  const response = await client.chat.completions.create({
      model: "@x-ai/grok-beta",
      messages: [{ role: "user", content: "Hello!" }]
  })

  console.log(response.choices[0].message.content)
  ```
</CodeGroup>

## Add Provider in Model Catalog

Before making requests, add xAI to your Model Catalog:

1. Go to [**Model Catalog → Add Provider**](https://stratacloudmanager.paloaltonetworks.com/)
2. Select **xAI**
3. Enter your [xAI API key](https://accounts.x.ai/)
4. Name your provider (e.g., `x-ai`)

<Card title="Complete Setup Guide" icon="book" href="/docs/aigw/product/model-catalog">
  See all setup options and detailed configuration instructions
</Card>

***

## xAI Capabilities

### Tool Calling (Function Calling)

<CodeGroup>
  ```bash cURL theme={"system"}
  curl https://aigw.portkey.ai/v1/chat/completions \
       -H "Content-Type: application/json" \
      -H "Authorization: Bearer $PORTKEY_API_KEY" \
       -d '{
         "model": "@x-ai/grok-beta",
         "messages": [
           {"role": "system", "content": "You are a helpful assistant."},
              {"role": "user", "content": "What'\''s the weather like in Delhi?"}
         ],
         "tools": [{
           "type": "function",
           "function": {
             "name": "getWeather",
             "description": "Get the current weather",
             "parameters": {
               "type": "object",
               "properties": {
                 "location": {"type": "string", "description": "City and state"},
                 "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
               },
               "required": ["location"]
             }
           }
         }],
         "tool_choice": "auto"
       }'
  ```
</CodeGroup>

### Vision

Process images with Grok's vision capabilities:

<CodeGroup>
  ```bash cURL theme={"system"}
  curl https://aigw.portkey.ai/v1/chat/completions \
       -H "Content-Type: application/json" \
      -H "Authorization: Bearer $PORTKEY_API_KEY" \
       -d '{
         "model": "@x-ai/grok-beta",
          "messages": [{
             "role": "user",
             "content": [
               {"type": "text", "text": "What'\''s in this image?"},
               {
                 "type": "image_url",
                 "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
               }
             ]
          }],
         "max_tokens": 300
       }'
  ```
</CodeGroup>

***

## Supported Models

xAI offers powerful models through Grok:

| Model       | Context Length | Description                                  |
| ----------- | -------------- | -------------------------------------------- |
| grok-beta   | 131,072 tokens | Latest Grok model with enhanced capabilities |
| grok-2-1212 | 32,768 tokens  | Previous generation Grok model               |

Check [xAI's documentation](https://docs.x.ai/docs) for the latest model information.

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Gateway Configs" icon="sliders" href="/docs/aigw/product/ai-gateway">
    Add fallbacks, load balancing, and more
  </Card>

  <Card title="Observability" icon="chart-line" href="/docs/aigw/product/observability">
    Monitor and trace your xAI requests
  </Card>

  <Card title="Guardrails" icon="shield-check" href="/docs/aigw/product/guardrails">
    Enforce input/output checks on requests
  </Card>
</CardGroup>

***

## FAQs

<AccordionGroup>
  <Accordion title="How do I get an xAI API key?">
    Sign up at [xAI](https://accounts.x.ai/) and generate your API key from the console.
  </Accordion>

  <Accordion title="Is the xAI API free to use?">
    xAI typically provides free credits to start. Contact their support team for additional credits.
  </Accordion>

  <Accordion title="How do I handle xAI rate limits?">
    Check your current rate limits in the xAI console. Use the AI Gateway's [load balancing](/docs/aigw/product/ai-gateway/load-balancing) to distribute requests across multiple providers.
  </Accordion>
</AccordionGroup>


## Related topics

- [Enterprise Gateway](/docs/aigw/changelog/enterprise.md)
- [Claude Code](/docs/aigw/integrations/libraries/claude-code.md)
- [Open Responses](/docs/aigw/product/ai-gateway/responses-api.md)
- [Conductor](/docs/aigw/integrations/libraries/conductor.md)
- [Prisma AIRS AI Gateway Models](/docs/aigw/product/model-catalog/gateway-models.md)