Open a terminal or command-line tool on your device.

On macOS or Linux, you can use Terminal.

On Windows, you can use Command Prompt, PowerShell, or the terminal in your development environment.

Run the following command in your terminal:

openclaw config

Press Enter to start the configuration process.

Select the following option from the configuration menu:

Local

Press Enter.

This option applies the configuration to your local OpenClaw environment.

Next, select:

Model

Press Enter.

This option configures the model service used by OpenClaw.

Select:

Custom Provider

Press Enter.

Choose this option when you want to connect OpenClaw to a custom OpenAI-compatible API service.

When prompted for the API Base URL, enter:

https://api.wox.lol/v1

Press Enter.

This address tells OpenClaw to send model requests to the WOX API gateway.

When prompted for an API key, enter your actual API key.

Example:

YOUR_API_KEY

In most cases, you do not need to add the Bearer prefix manually unless OpenClaw explicitly asks for the complete Authorization header.

When prompted for a model name, enter the ID of the model you want to use.

Example:

YOUR_MODEL_ID

Make sure you enter the complete model ID provided by the platform.

After completing all required fields, confirm and save the configuration.

Once saved, OpenClaw will use this custom provider for local model calls.