> ## 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.

# OpenCode

> Configure OpenCode, the powerful terminal AI coding assistant, to work with LLM Router for intelligent routing, Skills, Zero Data Retention, and cost optimization.

***

## 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.

# OpenCode Integration

[OpenCode](https://opencode.ai) is a fast and intuitive terminal-based AI coding assistant. It helps developers generate code, debug, refactor, explain code, and build features directly from the command line.

By connecting OpenCode to **LLM Router**, you can access top models from Anthropic, OpenAI, Google, xAI, and others through a single unified endpoint while gaining intelligent routing, Skills, context optimization, and privacy features.

## Configuring OpenCode with LLM Router

### 1. Start OpenCode

Open your terminal and run:

```bash theme={null}
opencode
```

### 2. Connect to LLM Router

In the OpenCode interface, run the connect command:

```bash theme={null}
/connect
```

* Select **OpenAI Compatible** (or Custom Provider)
* **Base URL**: `https://api.llmrouter.app/v1`
* **API Key**: Paste your LLM Router API key (`sk_llmr_...`)

### 3. Select a Model

Run the following command to choose a model:

```bash theme={null}
/models
```

You can select any model available through LLM Router, such as:

* `anthropic/claude-opus-4.6`
* `anthropic/claude-sonnet-4.6`
* `openai/gpt-5.4`
* `google/gemini-3.1-pro`
* `xai/grok-4.20`

### 4. Configure Routing via LLM Router Dashboard (Recommended)

For the best experience, set up your routing preferences in the **LLM Router Dashboard**:

* Assign tags like `coding`, `testing`, `ui design`, `refactoring`, etc.
* Enable relevant **Skills**
* Turn on **Zero Data Retention (ZDR)** for sensitive projects
* Configure default model preferences and optimization settings

These settings will automatically apply to all requests made from OpenCode.

### 5. (Optional) Advanced Configuration

You can create a configuration file named `opencode.json` for more control:

```json theme={null}
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "custom": {
      "baseUrl": "https://api.llmrouter.app/v1",
      "apiKey": "sk_llmr_your_key_here",
      "model": "anthropic/claude-opus-4.6"
    }
  }
}
```

## Start Using OpenCode

Once connected, you can start coding with natural language prompts:

```bash theme={null}
opencode "Create a full-stack todo app with Next.js 15 and Supabase"
```

or

```bash theme={null}
opencode "Refactor this authentication logic to use JWT with refresh tokens"
```

All your requests will be intelligently routed and optimized by LLM Router.

## Benefits

* Access to the best models with automatic routing
* Automatic relevant Skill injection
* Zero Data Retention for private codebases
* Reduced costs through context optimization