Chatbox & Cherry Studio in China — one key, 40+ models

Chatbox and Cherry Studio are popular desktop LLM clients. Add Router One as a custom OpenAI-compatible provider and chat with GPT, Claude, Gemini and more — no VPN, paid in RMB, with one key.

Measured latency: VPN vs Router One

Based on the China latency benchmark last updated 2026-05-15, Router One measured 110-130ms p50 across Beijing, Shanghai, and Shenzhen; individual networks may vary.

3-step setup

Add Router One as a custom OpenAI-compatible provider, paste your key, and pick a model. The steps below cover both Chatbox and Cherry Studio.

1. 1Create a Router One API keySign up at router.one and create an API key in the dashboard. Top up with WeChat Pay, Alipay, Stripe, or USDT/USDC — no foreign credit card required.
2. 2Add an OpenAI-compatible providerIn Chatbox: Settings → Model Provider → OpenAI API, set API Host to https://api.router.one/v1 and paste your key. In Cherry Studio: Settings → Model Providers → add an OpenAI provider, set the API host to the same URL and paste your key.
3. 3Pick a model and chatSelect a model (GPT, Claude, Gemini and more) and start chatting — requests route through Router One's China-reachable, OpenAI-compatible endpoint with no VPN.

# Chatbox / Cherry Studio → OpenAI-compatible provider
API Host: https://api.router.one/v1
API Key:  sk-your-router-one-key

No low fixed cap for normal paid usage. Abuse prevention, per-account protection limits, and upstream constraints may still apply; if a request returns 429, check Dashboard -> Logs or contact support to raise limits.

FAQ