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

# Gateway Setup

> Configure your application to use the Muxx Gateway.

This guide shows you how to route your LLM requests through the Muxx Gateway.

## Prerequisites

* A Muxx account with a project created
* Your Muxx API key (`muxx_sk_live_...`)
* Provider API keys configured in your project settings

## Configuration

### OpenAI

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    from openai import OpenAI

    client = OpenAI(
        base_url="https://gateway.muxx.dev/v1",
        default_headers={
            "X-Muxx-Api-Key": "muxx_sk_live_xxxxxxxxxxxx"
        }
    )

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "user", "content": "Explain quantum computing in simple terms"}
        ]
    )
    print(response.choices[0].message.content)
    ```
  </Tab>

  <Tab title="TypeScript">
    ```typescript theme={null}
    import OpenAI from 'openai';

    const client = new OpenAI({
      baseURL: 'https://gateway.muxx.dev/v1',
      defaultHeaders: {
        'X-Muxx-Api-Key': 'muxx_sk_live_xxxxxxxxxxxx',
      },
    });

    const response = await client.chat.completions.create({
      model: 'gpt-4o',
      messages: [
        { role: 'user', content: 'Explain quantum computing in simple terms' },
      ],
    });
    console.log(response.choices[0].message.content);
    ```
  </Tab>

  <Tab title="cURL">
    ```bash theme={null}
    curl https://gateway.muxx.dev/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "X-Muxx-Api-Key: muxx_sk_live_xxxxxxxxxxxx" \
      -d '{
        "model": "gpt-4o",
        "messages": [
          {"role": "user", "content": "Explain quantum computing in simple terms"}
        ]
      }'
    ```
  </Tab>
</Tabs>

### Anthropic

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    from anthropic import Anthropic

    client = Anthropic(
        base_url="https://gateway.muxx.dev/v1",
        default_headers={
            "X-Muxx-Api-Key": "muxx_sk_live_xxxxxxxxxxxx"
        }
    )

    response = client.messages.create(
        model="claude-3-5-sonnet-20241022",
        max_tokens=1024,
        messages=[
            {"role": "user", "content": "Explain quantum computing in simple terms"}
        ]
    )
    print(response.content[0].text)
    ```
  </Tab>

  <Tab title="TypeScript">
    ```typescript theme={null}
    import Anthropic from '@anthropic-ai/sdk';

    const client = new Anthropic({
      baseURL: 'https://gateway.muxx.dev/v1',
      defaultHeaders: {
        'X-Muxx-Api-Key': 'muxx_sk_live_xxxxxxxxxxxx',
      },
    });

    const response = await client.messages.create({
      model: 'claude-3-5-sonnet-20241022',
      max_tokens: 1024,
      messages: [
        { role: 'user', content: 'Explain quantum computing in simple terms' },
      ],
    });
    console.log(response.content[0].text);
    ```
  </Tab>
</Tabs>

## Environment Variables

We recommend storing your Muxx API key in environment variables:

```bash theme={null}
export MUXX_API_KEY="muxx_sk_live_xxxxxxxxxxxx"
```

Then reference it in your code:

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

client = OpenAI(
    base_url="https://gateway.muxx.dev/v1",
    default_headers={
        "X-Muxx-Api-Key": os.environ["MUXX_API_KEY"]
    }
)
```

## Adding Metadata

You can attach custom metadata to requests for filtering in the dashboard:

```python theme={null}
client = OpenAI(
    base_url="https://gateway.muxx.dev/v1",
    default_headers={
        "X-Muxx-Api-Key": "muxx_sk_live_xxxxxxxxxxxx",
        "X-Muxx-Metadata": '{"user_id": "user_123", "feature": "chat"}'
    }
)
```

This metadata appears in the dashboard and can be used for filtering and analytics.

## Streaming

The gateway fully supports streaming responses:

```python theme={null}
stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Caching" icon="database" href="/gateway/caching">
    Enable response caching to reduce costs
  </Card>

  <Card title="Rate Limiting" icon="gauge" href="/gateway/rate-limiting">
    Configure request limits
  </Card>
</CardGroup>