Set up Qwen Code

Merge these fields into settings.json and restart Qwen Code. Keep unrelated settings. To return to your previous provider, restore the backup or use Qwen’s authentication and model settings.

Option 1: Use Configure

Sign in and select your local configuration file. Apply LaRouter fills your key and model and writes the file immediately; Reset defaults also writes immediately. If your browser cannot write local files, follow the manual instructions.

See manual instructions

Configuration file location

macOS: ~/.qwen/settings.json
Linux: ~/.qwen/settings.json
Windows: %USERPROFILE%\.qwen\settings.json

These are default locations. For a tool running in WSL, use its Linux path inside WSL. If you changed the configuration directory, select the tool’s actual file. Your browser can only read or write files you select.

Option 2: Configure manually

Back up your files and replace only the placeholders shown below. Codex already uses gpt-5.6-sol. Use model names without router prefixes such as cx/. Keep tool-required local provider bindings such as larouter/ where shown, and preserve unrelated settings.

Setup steps

Merge these fields into settings.json and restart Qwen Code. Keep unrelated settings. To return to your previous provider, restore the backup or use Qwen’s authentication and model settings.

settings.json

{
  "security": {
    "auth": {
      "selectedType": "openai",
      "apiKey": "YOUR_API_KEY",
      "baseUrl": "https://i-larouter.lapage.vn/v1"
    }
  },
  "model": {
    "name": "YOUR_MODEL_ID"
  }
}