> ## 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.

# LibreChat

> Configure LibreChat, the open-source AI chat platform, to use LLM Router for intelligent routing, Skills, Zero Data Retention, and unified access to top AI models.

***

## 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 models, tags, and features before exploring further.

# LibreChat Integration

[LibreChat](https://librechat.ai) is a popular open-source AI chat platform that you can self-host. It supports multiple providers and gives you a beautiful ChatGPT-like interface.

By connecting LibreChat to **LLM Router**, you get intelligent tag-based routing, automatic Skill injection, context optimization, Zero Data Retention (ZDR), and access to the best models from Anthropic, OpenAI, Google, xAI, and more through a single endpoint.

## Configuring LibreChat with LLM Router

### 1. Install LibreChat

```bash theme={null}
git clone https://github.com/danny-avila/LibreChat.git
cd LibreChat
cp .env.example .env
```

> **Note:** Windows users can use `copy` instead of `cp`. Docker Desktop is required.

### 2. Create Docker Override File

Create a file named `docker-compose.override.yml` in the root directory:

```yaml filename="docker-compose.override.yml" theme={null}
services:
  api:
    volumes:
      - type: bind
        source: ./librechat.yaml
        target: /app/librechat.yaml
```

### 3. Add API Key to Environment

Add your LLM Router API key to the `.env` file:

```env filename=".env" theme={null}
LLM_ROUTER_API_KEY=sk_llmr_your_key_here
```

### 4. Configure Custom Endpoint

Create a `librechat.yaml` file in the root directory:

```yaml filename="librechat.yaml" theme={null}
version: 1.2.8
cache: true

endpoints:
  custom:
    - name: "LLM Router"
      apiKey: "${LLM_ROUTER_API_KEY}"
      baseURL: "https://api.llmrouter.app/v1"
      titleConvo: true
      models:
        default:
          - "anthropic/claude-opus-4.6"
          - "anthropic/claude-sonnet-4.6"
          - "openai/gpt-5.4"
          - "google/gemini-3.1-pro"
          - "xai/grok-4.20"
        fetch: true
      titleModel: "anthropic/claude-sonnet-4.6"
```

> **Tip:** Setting `fetch: true` automatically pulls all available models from LLM Router.

### 5. Start LibreChat

```bash theme={null}
docker compose up -d
```

Or restart if already running:

```bash theme={null}
docker compose restart
```

Access LibreChat at `http://localhost:3080`

### 6. Select LLM Router Endpoint

In the LibreChat interface:

1. Click the endpoint dropdown at the top
2. Select **LLM Router**
3. Choose your preferred model

## Configuration Options

You can further customize the endpoint in `librechat.yaml`:

* `titleConvo`: Enable automatic conversation titles
* `titleModel`: Model used for generating titles
* `dropParams`: Remove unsupported parameters
* `modelDisplayLabel`: Custom label for the endpoint

See the [LibreChat custom endpoints documentation](https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/custom_endpoint) for more options.