> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://doc.enterpriserouter.com/getting-started/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://doc.enterpriserouter.com/_mcp/server.

# Getting Started

## Docs

- [Enterprise Router](https://doc.enterpriserouter.com/welcome.md): One endpoint for every frontier model
- [Authentication](https://doc.enterpriserouter.com/authentication.md): How proxy keys work


> **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://doc.enterpriserouter.com/getting-started/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://doc.enterpriserouter.com/_mcp/server.

# Quick Start

## 1. Create an account

Sign up at your Enterprise Router dashboard. You'll need an organization name and an email address.

After signing up, you'll land on your dashboard where you can manage keys, view usage, and monitor your audit trail.

## 2. Create a proxy key

Go to **API Keys** in the sidebar and click **Create Key**.

Give your key a name (e.g., `my-first-key`) and click **Create**. You can leave all other options as defaults for now.

Your key will be shown **once** — copy it and store it somewhere safe. It looks like this:

```
sk-proxy-a1b2c3d4e5f6...
```

## 3. Add credits

Go to **Settings > Billing** and purchase a credit package. In development mode, credits are granted instantly. In production, you'll be redirected to Stripe for payment.

## 4. Make your first request

Install the OpenAI Python SDK if you don't have it:

```bash
pip install openai
```

### Option A: Native Mode

Use the OpenAI SDK exactly as you normally would, but pointed at your gateway:

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-proxy-YOUR_KEY_HERE",
    base_url="https://api.enterpriserouter.com/openai/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What is Enterprise Router?"}]
)

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

### Option B: Unified Mode

Use the OpenAI SDK to call any provider. Prefix the model name with the provider:

```python
from openai import OpenAI

client = OpenAI(
    api_key="sk-proxy-YOUR_KEY_HERE",
    base_url="https://api.enterpriserouter.com/v1"
)

# Call Anthropic using the OpenAI SDK
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",
    messages=[{"role": "user", "content": "What is Enterprise Router?"}]
)

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

## 5. Check your dashboard

Go back to your dashboard. You'll see:

* The request in your **Audit Log** with provider, model, tokens, cost, and latency
* Updated **Usage** metrics showing your spend and savings vs. market rate
* The key's **last used** timestamp updated

## What's next?

* **[Native Mode](/native-mode)** — detailed guides for OpenAI, Anthropic, and Gemini with streaming, tool calling, and more
* **[Unified Mode](/unified-mode)** — call any provider with one SDK
* **[Authentication](/authentication)** — how proxy keys work and how to send them
* **[Key Management](/keys)** — configure provider restrictions, IP allowlists, rate limits, and spend limits