TRAE Work

Configure TRAE Work for your enterprise and verify the request in your console logs.

Configuration

Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model

  1. In the TRAE Work desktop app, open Settings → Models → Add Model and choose Custom. The local workspace must be able to reach the enterprise gateway.
  2. Choose OpenAI Chat Completions or Anthropic Messages based on model support, enable Full URL and enter the corresponding endpoint.
  3. Enter the enterprise API key and model ID, then save. Configure optional capabilities according to what the provisioned model supports.
API protocolAddress to enter
Chat CompletionsFull URLhttps://tokenpyxis.com/v1/chat/completions
Anthropic MessagesFull URLhttps://tokenpyxis.com/v1/messages

Verification

Start a local session, select the custom model and complete a plain-text request before testing the intended workflow.

Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps

Troubleshooting

If the request fails, confirm the session is running locally, then check the Full URL toggle and selected protocol.

Business inquiries
Scan with WeChat to add the business team on WeCom