> ## 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.

# Quickstart

> Get up and running with Muxx in under 5 minutes.

This guide will help you start logging your LLM requests with Muxx in just a few minutes.

## Prerequisites

* A Muxx account ([sign up here](https://muxx.dev/signup))
* An API key from your LLM provider (OpenAI, Anthropic, or Google)

## Step 1: Create a Project

1. Log in to the [Muxx dashboard](https://muxx.dev)
2. Create or select an organization
3. Click **New Project** and give it a name
4. Add your LLM provider API key in the project settings

## Step 2: Create Your Muxx API Key

1. In your project, go to **Settings** → **API Keys**
2. Click **Create Key**
3. Choose **Live** for production or **Test** for development
4. Click **Create** and copy the key immediately

```
muxx_sk_live_xxxxxxxxxxxxxxxxxxxx
```

<Warning>
  The full key is only shown once. Store it securely—you'll need it to authenticate requests.
</Warning>

<Info>
  See [API Keys](/dashboard/api-keys) for more details on key management and security best practices.
</Info>

## Step 3: Choose Your Integration

<Tabs>
  <Tab title="Gateway Only">
    The simplest option—just change your base URL.

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

    client = OpenAI(
        api_key="your-openai-key",  # Or use OPENAI_API_KEY env var
        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": "Hello!"}]
    )
    ```
  </Tab>

  <Tab title="Python SDK">
    For deeper tracing with spans and decorators.

    ```bash theme={null}
    pip install muxx
    ```

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

    muxx = Muxx(api_key="muxx_sk_live_xxxxxxxxxxxx")
    client = muxx.wrap(OpenAI())

    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    ```
  </Tab>

  <Tab title="TypeScript SDK">
    For Node.js and TypeScript applications.

    ```bash theme={null}
    npm install muxx
    ```

    ```typescript theme={null}
    import { Muxx } from 'muxx';
    import OpenAI from 'openai';

    const muxx = new Muxx({ apiKey: 'muxx_sk_live_xxxxxxxxxxxx' });
    const client = muxx.wrap(new OpenAI());

    const response = await client.chat.completions.create({
      model: 'gpt-4o',
      messages: [{ role: 'user', content: 'Hello!' }],
    });
    ```
  </Tab>
</Tabs>

## Step 4: View Your Logs

After making a request, head to the [Muxx dashboard](https://muxx.dev). You'll see:

* **Request logs** with full payloads
* **Token usage** and cost breakdown
* **Latency** measurements
* **Model** and provider information

## Next Steps

<CardGroup cols={2}>
  <Card title="Gateway Setup" icon="server" href="/gateway/setup">
    Configure caching, rate limiting, and more
  </Card>

  <Card title="Python SDK" icon="python" href="/sdk/python/quickstart">
    Add tracing and observability decorators
  </Card>

  <Card title="TypeScript SDK" icon="js" href="/sdk/typescript/quickstart">
    Integrate with your Node.js application
  </Card>

  <Card title="Dashboard Guide" icon="chart-line" href="/dashboard/overview">
    Explore analytics and team features
  </Card>
</CardGroup>