TRAE setup
TRAE supports custom models in the OpenAI Chat Completions or Anthropic Messages format.
Before you start
- Create an account and top up, then create a key on the API Keys page of the dashboard.
- Find an available model ID with your key; see API reference: Find an available model.
- Replace the green-highlighted
<your key>in the examples with your own key, and model placeholders with actual model IDs.
Setup steps
Install from each product’s official download or release page. Choose the Windows package on Windows and the correct Apple Silicon or Intel package on macOS. Existing users can proceed directly to configuration. Labels may vary by version.
- Install the appropriate Chinese or international edition.
- Open Settings → Models → Add model → Custom model.
- Choose OpenAI Chat Completions or Anthropic Messages as appropriate.
- With full URL enabled, enter
https://api.6090ti.com/v1/chat/completionsorhttps://api.6090ti.com/v1/messages. Otherwise use the matching/v1Base URL or root requested by the interface. - Enter the model ID, display name, and key, then save and test.
Follow your edition’s interface. Chinese documentation / International documentation
Troubleshooting
For 401, 404, 429 and other errors, see API reference: Troubleshooting. If that does not solve it, contact us as described in the support and issue-reporting guide. Never send full keys, passwords or verification codes.
QQ user group: 1109931264