> ## 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.

# Blackbox AI (CLI)

> Configure the Blackbox AI CLI to route through LLM Router for intelligent model fallback, aggressive context optimization, and Zero Data Retention (ZDR).

***

> ## 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.

# Blackbox AI & LLM Router

[Blackbox AI](https://www.blackbox.ai/) is a fast and powerful terminal-based AI coding assistant. It excels at generating code, explaining complex logic, and scaffolding projects directly from your command line.

Because terminal assistants frequently ingest large amounts of local code and command outputs, they consume massive amounts of input tokens. By connecting Blackbox AI to **LLM Router**, you automatically apply **Middle-Out Context Compression** to bloated terminal histories and ensure your local `.env` secrets are **Redacted** before they reach third-party AI providers like OpenAI or Anthropic.

***

## Step 1: Installing Blackbox AI CLI

If you haven't installed Blackbox AI yet, run the appropriate command for your operating system:

<CodeGroup>
  ```bash macOS / Linux theme={null}
  curl -fsSL https://blackbox.ai/install.sh | bash
  ```

  ```powershell Windows theme={null}
  iex (irm https://blackbox.ai/install.ps1)
  ```
</CodeGroup>

*Note: You may need to restart your terminal after installation.*

***

## Step 2: Configuring LLM Router

Blackbox AI natively supports custom OpenAI-compatible providers, making integration with LLM Router straightforward.

<Steps>
  <Step title="Get Your API Key">
    Log into the [LLM Router Dashboard](https://llmrouter.app/dashboard) and generate a new API key (e.g., `sk-router-...`).
  </Step>

  <Step title="Run the Configuration Tool">
    Open your terminal and run the built-in configuration wizard: `bash blackbox
          configure `
  </Step>

  <Step title="Set LLM Router as the Provider">
    When prompted by the wizard, enter the following settings:

    * **Provider:** Select `OpenAI Compatible` (Do *not* select OpenAI directly, as we need to override the Base URL).
    * **Base URL:** Enter `https://api.llmrouter.app/v1`
    * **API Key:** Paste your LLM Router API key (`sk-router-...`)
    * **Model:** Enter the specific model you want to use, prefixed with the provider slug (e.g., `anthropic/claude-3-5-sonnet` or `openai/gpt-4o`).
  </Step>
</Steps>

<Note>
  **Model Selection:** Because LLM Router acts as a universal gateway, you must
  prefix your chosen model with the provider slug. If you have configured
  Tag-Based routing in your LLM Router dashboard, you can simply set the model
  to `"router-auto"`.
</Note>

***

## Alternative: Environment Variables

If you prefer not to use the interactive configuration wizard (or if you are automating the setup), you can configure Blackbox AI using standard environment variables in your `~/.zshrc` or `~/.bashrc`:

```bash theme={null} theme={null}
export OPENAI_BASE_URL="https://api.llmrouter.app/v1"
export OPENAI_API_KEY="sk-router-your-api-key-here"
export OPENAI_MODEL="anthropic/claude-3-5-sonnet"
```

*Don't forget to run `source ~/.zshrc` after making changes.*

***

## Step 3: Start Using Blackbox AI

Once configured, you can launch Blackbox AI in interactive mode:

```bash theme={null}
blackbox
```

Or run it with a specific, one-off task:

```bash theme={null}
blackbox "Implement a user authentication system with JWT in Next.js"
```