Qwen Code

Qwen Code: configure the API key, model and provider in your terminal.

Published instructions · App version: unverified

Chat, ping, invoke and content-generation examples may send real billable requests. Check the model, balance, rate and minimum before running them. GET /v1/models checks authentication and the catalogue only. Set up environment variables safely

Base URL to paste

OpenAI SDKs generally use a URL ending in /v1; Anthropic SDKs use the root URL. Avoid adding /v1 twice. Protocol compatibility does not guarantee every provider feature.

https://thapi.cloud/v1

Prerequisites

Install qwen CLI
API keys

Recommended model: gpt-5.6-sol

Quick way — command / config

export STALI_API_KEY="sk-thapi-..."

Where to place file / fill Settings

Filemacos

~/.qwen/settings.json

Back up the file; merge modelProviders, security.auth and model as shown. Keep existing providers; set STALI_API_KEY in the environment before opening qwen.

Filelinux

~/.qwen/settings.json

Same as macOS.

Filewindows

%USERPROFILE%\.qwen\settings.json

Create the .qwen directory if missing.

Verify connection

Open qwen; check that /auth is OpenAI and /model selects gpt-5.6-sol. Send a message only if you accept the usage charge.

Troubleshooting

Symptom	Reason	How to handle
404	baseUrl in modelProviders.openai is missing /v1.	https://thapi.cloud/v1

Notes

Checked against official documentation on 2026-10-23; the complete app has not been tested against the live service.

API CLI