@openrouter/cli

Claude Code for Open Router

A simple and easy to use utility to login to open router and use any model with claude code!

✨ Features

• Model Routing: Route requests to different models based on your needs (e.g., background tasks, thinking, long context).
• Dynamic Model Switching: Switch models on-the-fly within Claude Code using the /model command.

🚀 Getting Started

1. Installation

First, ensure you have Claude Code installed:

npm install -g @anthropic-ai/claude-code

Then, install Claude Code Router:

npm install -g @openrouter/claude-code

2. Configuration

Create and configure your ~/.openrouter/claude-code-proxy.json file. For more details, you can refer to config.example.json.

The claude-code-proxy.json file has several key sections:

• LOG (optional): You can enable logging by setting it to true. When set to false, no log files will be created. Default is true.
• LOG_LEVEL (optional): Set the logging level. Available options are: "fatal", "error", "warn", "info", "debug", "trace". Default is "debug".
• Logging Systems: The Claude Code Router uses two separate logging systems:
  • Server-level logs: HTTP requests, API calls, and server events are logged using pino in the ~/.copenrouter/logs/ directory with filenames like openrouter-*.log
  • Application-level logs: Routing decisions and business logic events are logged in ~/.openrouter/router.log
• OPENROUTER_API_KEY: To set your OPENROUTER_API_KEY to use in the proxy server
• models: Used to set up routing rules. default specifies the default model, which will be used for all requests if no other route is configured.
• API_TIMEOUT_MS: Specifies the timeout for API calls in milliseconds.

Environment Variable Interpolation

Claude Code Router supports environment variable interpolation for secure API key management. You can reference environment variables in your config.json using either $VAR_NAME or ${VAR_NAME} syntax:

{
  "OPENROUTER_API_KEY": "$OPENROUTER_API_KEY"
}

This allows you to keep sensitive API keys in environment variables instead of hardcoding them in configuration files. The interpolation works recursively through nested objects and arrays.

Here is a comprehensive example:

{
  "OPENROUTER_API_KEY": "$OPENROUTER_API_KEY",
  "LOG": true,
  "models": {
    "default": "deepseek/deepseek-chat",
    "background": "qwen/qwen3-30b-a3b",
    "think": "deepseek/deepseek-reasoner",
    "longContext": "google/gemini-2.5-pro-preview",
    "longContextThreshold": 60000,
    "webSearch": "google/gemini-2.5-flash:online"
  }
}

3. Running Claude Code with the Router

Start Claude Code using the router:

openrouter code

Note: After modifying the configuration file, you need to restart the service for the changes to take effect:

openrouter restart

Models

The models object defines which model to use for different scenarios:

• default: The default model for general tasks.
• background: A model for background tasks. This can be a smaller, local model to save costs.
• think: A model for reasoning-heavy tasks, like Plan Mode.
• longContext: A model for handling long contexts (e.g., > 60K tokens).
• longContextThreshold (optional): The token count threshold for triggering the long context model. Defaults to 60000 if not specified.
• webSearch: Used for handling web search tasks and this requires the model itself to support the feature. You will also need to add the :online suffix after the model name.

You can also switch models dynamically in Claude Code with the /model command: /model model_name Example: /model anthropic/claude-sonnet-4