MaiToken
Login/Register

WorkBuddy

Use Cases

Suitable for beginners who want to add a custom OpenAI model through a graphical interface.

Recommended Method: Use the Standard Base URL

  1. Open Settings: Open WorkBuddy, click the settings icon in the lower-left corner, and go to Settings → Model.

  2. Add a Model: Click Add, +, or Custom in the custom model section.

  3. Select Custom: Select Custom as the provider, and select OpenAI Compatible or OpenAI Chat Completions as the protocol.

  4. Enter the URL: Enter https://api.maitoken.com/v1 .

  5. Disable Custom Protocol: Keep Custom Protocol disabled. When it is disabled, WorkBuddy will automatically append the standard /chat/completions path.

  6. Enter the Key and Model: Enter your MaiToken Key in the API Key field, and enter <Model ID> in the Model Name or Model ID field.

  7. Configure Model Capabilities: If the interface asks whether the model supports Tool Calling or Streaming, enable these options according to the model's actual capabilities. If you are unsure, enable them first and test whether the Agent works correctly.

  8. Save the Configuration: Click Save, and then select the model from the Custom group in the chat model selector.

Field Recommended Value
URL https://api.maitoken.com/v1
Custom Protocol Disabled
API Key <your MaiToken Key>
Model <Model ID>
Enable Custom Protocol only if WorkBuddy does not allow you to save a Base URL or explicitly requires a full request URL. After enabling it, change the URL to https://api.maitoken.com/v1/chat/completions .

Test the Configuration

  1. Test a Basic Conversation: Enter “Reply with OK only” in the chat box. If you receive a valid response, the API Key, URL, and Model ID are configured correctly.

  2. Test Project Reading: Open a test project and enter “Read the current project directory and list only the files at the first level. Do not modify any files.”

  3. Test Agent Capabilities: Ask the Agent to create a file named test-maitoken.txt and write hello into it. Confirm that the file was created successfully. Do not use a real production project for testing.

Common Issues

Issue Solution
The request URL becomes /v1/v1 /v1 was entered twice in the URL. Keep only https://api.maitoken.com/v1 .
A 404 error occurs after enabling Custom Protocol When Custom Protocol is enabled, enter the full URL: https://api.maitoken.com/v1/chat/completions .
The model does not appear in the list Manually enter the exact Model ID in Custom model management, and then reopen the model selector.