TRAE

Use Cases

Configuration Steps

1. Open Model Management: Open TRAE and go to the account or settings page. Find “Models” in the left-hand menu, and then click “Add Model.” In some versions, you may need to access model management from the model drop-down menu in the chat panel.

2. Open Custom Configuration: Select “Custom Configuration” or “Add Custom Model.”

3. Select the API Format: Select OpenAI Chat Completions. Do not select Anthropic Messages.

4. Enable Full URL: If the interface provides a “Full URL” option, enable it. When enabled, TRAE will use the URL exactly as entered and will not append a request path automatically.

5. Enter the Request URL: Enter https://api.maitoken.com/v1/chat/completions . This is the full request URL.

6. Enter the Model ID: Replace <Model ID> with the exact ID shown in the API Key's model restriction list. We recommend setting the display name to MaiToken - Model ID.

7. Enter the API Key: Paste your MaiToken Key. Enter only the Key itself and do not add Bearer manually.

8. Save the Configuration: Click “Submit” or “Save.” Return to the chat panel, disable Auto, and then select the MaiToken model you just created.

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, request 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