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

# Chatbox (Desktop)

> Configure Chatbox to route through LLM Router for unified model access, aggressive context compression, and centralized cost tracking.

***

> ## Documentation Index
>
> Fetch the complete documentation index at: [https://docs.llmrouter.app/llms.txt](https://docs.llmrouter.app/llms.txt)
> Use this file to discover all available pages before exploring further.

# Chatbox & LLM Router

[Chatbox](https://chatboxai.app/) is a popular, cross-platform desktop AI assistant (available for macOS, Windows, and Linux). It allows you to chat with multiple AI models from a single interface.

Because desktop chat applications tend to accumulate extremely long conversation histories, they quickly become expensive to operate. By connecting Chatbox to **LLM Router**, you automatically apply **Chat History Optimization** to your long threads, dropping irrelevant old messages and saving you massive amounts of input tokens.

***

## Step 1: Create an LLM Router API Key

Before configuring Chatbox, you need an API key from LLM Router:

1. Log into the [LLM Router Dashboard](https://llmrouter.app/dashboard).
2. Navigate to the **API Keys** section.
3. Generate a new key and copy it (e.g., `sk-router-...`).

## Step 2: Install Chatbox

If you haven't already, download and install [Chatbox](https://chatboxai.app/) for your operating system.

## Step 3: Configure LLM Router in Chatbox

Chatbox natively supports custom OpenAI-compatible providers. We will configure it to point all traffic to LLM Router.

**1. Open Settings**

Launch Chatbox and open the **Settings** menu (usually a gear icon in the bottom left).

**2. Add a Custom Provider**

Navigate to the **Model Provider** tab. Click **Add** and select the **OpenAI
API Compatible** option.

**3. Enter API Details**

Fill in the connection details for LLM Router: \* **API Host:** Enter
`https://api.llmrouter.app/v1` (Make sure to include `/v1`). \* **API Path:**
Leave this field empty. \* **API Key:** Paste your `sk-router-...` key here.

**4. Validate and Fetch Models**

1. Click the **Check** button next to the API Key field to validate your connection.
2. Click **Fetch** to retrieve the list of available models from LLM Router.

> [!NOTE]
>
> **Model Selection:** Because LLM Router acts as a universal gateway, the
> fetched models will be prefixed with their provider slug (e.g.,
> `anthropic/claude-3-5-sonnet` or `openai/gpt-4o`).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.