This documentation is provided for informational purposes only and demonstrates how to configure and use our API with third-party AI chat interfaces. Any third-party software, websites, or services mentioned are not operated, controlled, or endorsed by us.

​

Introduction to Codex

• Terminal-based AI coding assistant
• Natural language → code generation
• Local execution with privacy
• Multiple automation modes
• Multi-language support
• Debugging, refactoring & testing automation
• Interactive workflow in CLI

​

Step

1

Install Codex

Install the newest LTS version of Node.jsAfter installation is complete, open the terminal (Windows users use PowerShell) and check the version number.

• macOS, Linux, Windows:

npm i -g @openai/codex

Verify the installation.

codex --version

If the version number is displayed correctly, the installation is successful.

2

Configure Codex

Codex uses the config.toml file to parse provider parameters. Please locate and create/edit this file according to your operating system.Edit or create config.toml fileOn macOS & Linux: ~/.codex/config.tomlOn Windows: C:\Users\<USERNAME>\.codex\config.tomlDelete the previous content and replace it with the following.Configuration file:

model_provider = "routerlink"
model = "world3-router-north-america/openai/gpt-5.3-codex"

[model_providers.routerlink]
name = "RouterLink"
base_url = "https://router-link.world3.ai/api/v1"
env_key = "ROUTERLINK_API_KEY"

You can replace the “model” field with any model that is compatible with the OpenAI format.

3

Codex Loading and Validation

Open the terminal (Windows users use PowerShell). Make sure to replace with the <ROUTERLINK_API_KEY> obtained from RouterLink Key.

• macOS, Linux,

export ROUTERLINK_API_KEY="<ROUTERLINK_API_KEY>"

• Windows PowerShell:

$env:ROUTERLINK_API_KEY = "<ROUTERLINK_API_KEY>"

Launch codex

codex

Select “Yes” to trust this folder.

Now you can use Codex.