Chatbox and Cherry Studio in China: one key, no VPN, Alipay

Chatbox and Cherry Studio are popular desktop AI clients. With Router One added as a custom provider, both reach GPT, Claude, Gemini and more from Mainland China without a VPN, on one key that you fund with a card or Alipay in one hosted checkout, or with USDT/USDC. Each client has its own setup guide with the exact fields; this page covers access, payment and which guide to follow.

Get your API key

One key, 30+ models

One custom provider reaches the GPT, Claude, Gemini, Grok and DeepSeek chat models in the catalog. Pay as you go, up to 90% off official prices on select models.

Direct access, no VPN

Both clients call Router One at api.router.one, which is reachable from Mainland China without a VPN. Review the published benchmark below before relying on any point-in-time network result.

Pay in RMB

Fund the wallet with a card or Alipay in one hosted checkout, or with USDT/USDC on six chains. No foreign credit card required.

Review the China latency benchmark

This page does not make a separate latency promise. The published snapshot, last updated 2026-05-15, covers Beijing, Shanghai, and Shenzhen on China Telecom, China Unicom, and China Mobile in a rolling 7-day window. It is not an SLA, and individual networks may vary; review the full method and caveats before judging fit for your workload.

Read the published benchmark

Pick the setup guide for your client

The two clients take Router One in different places. Each guide lists the exact labels, values and model settings, checked against Cherry Studio 2.1.3 and Chatbox 1.23.5 on 2026-09-29 and re-checked on 2026-10-03 (Cherry Studio 2.1.4; Chatbox 1.23.5 is still the latest).

Client	Where to add Router One	What to enter	APIs and model IDs
Cherry Studio	Settings → Model Provider → Add Provider → Add Custom Provider	The host root https://api.router.one for the OpenAI, Anthropic and OpenAI Responses endpoints; Cherry appends /v1 and the path	OpenAI for every chat model; Anthropic for Claude and DeepSeek V4 IDs; OpenAI Responses for GPT, DeepSeek V4 and Grok IDs
Chatbox	Settings → Model Provider → Add → Add Custom Provider	API Host https://api.router.one/v1, which Claude API Compatible mode needs as well	OpenAI API Compatible for every chat model; Claude API Compatible for Claude and DeepSeek V4 IDs; OpenAI Responses API Compatible for GPT, DeepSeek V4 and Grok IDs

Cherry Studio setup guide Chatbox setup guide

Get started in three steps

1Create a Router One key and top upSign up at router.one, create a key in Dashboard → API Keys with Create Key and give it a maxSpend cap. Fund the wallet with a card or Alipay on the hosted checkout, or with USDT/USDC — no foreign credit card required.
2Add Router One as a custom providerIn Cherry Studio, add a custom provider and enter https://api.router.one for its OpenAI and Anthropic endpoints. In Chatbox, add a custom provider in OpenAI API Compatible mode with API Host https://api.router.one/v1. Paste the key in either client.
3Pick a model and check LogsAdd exact model IDs from /models, such as anthropic/claude-sonnet-5, send a message, and match the request in Dashboard → Logs by time, model and cost.

provider settings

# Cherry Studio → Add Custom Provider → Endpoint settings
OpenAI / Anthropic:  https://api.router.one
# Chatbox → Add Custom Provider → OpenAI API Compatible
API Host:            https://api.router.one/v1
API Key:             sk-your-router-one-key

No low fixed cap for normal paid usage. Each key and each account runs under default request-per-minute and token-per-minute limits, and upstream constraints may still apply; if a request returns 429, back off and retry (honor Retry-After when it is sent), and if your traffic needs higher limits, email support@router.one to have the key or account limits raised.

FAQ

Do I need a VPN?

No proxy or VPN is required for the Router One endpoint. The China latency benchmark on this page documents the dated network snapshot and its caveats.

Which client should I use, and where are the setup steps?

Both work with Router One as a custom provider. Cherry Studio takes a base URL for each endpoint type (OpenAI, Anthropic, OpenAI Responses and image generation), while Chatbox gives each provider one API mode. The Cherry Studio and Chatbox setup guides linked above list every field; any other client with custom OpenAI-compatible provider settings works the same way.

Can I use Claude in these clients from China?

Yes. Claude-family IDs such as anthropic/claude-sonnet-5 work on the OpenAI-compatible endpoint in both clients, and also on Cherry Studio's Anthropic endpoint or in Chatbox's Claude API Compatible mode with the /v1 host. The requests go to Router One, which is reachable from Mainland China without a VPN, and bill like any other request: plan-covered models draw plan quota first (as of the 2026-09-29 plan response, anthropic/claude-sonnet-5 is in the Mid-tier models tier of Pro, Max and Ultra), and everything else bills to your wallet.

How does billing work?

Use prepaid wallet balance or a live subscription plan. Top up with a card or Alipay on one hosted checkout, or with USDT/USDC on six chains — usage outside plan coverage is metered per token.

Is my data stored?

Router One does not retain prompt or model-response bodies from direct API calls. It records request metadata for billing, usage tracking, and troubleshooting. Playground saves conversation history so users can revisit and continue their chats.

Choose the next step for your desktop client

Next steps for Chatbox or Cherry Studio: open your client's setup guide, check the provider settings, choose a model, find a guide for another client, or top up the wallet.

Cherry StudioFill in Cherry Studio's endpoint settingsAdd a custom provider with the host root for the OpenAI, Anthropic and OpenAI Responses endpoints, then add exact chat IDs and set up Agent or images.ChatboxChoose Chatbox's API mode and API hostAdd a custom provider in OpenAI API Compatible mode with the /v1 host; Claude API Compatible mode needs /v1 too, and its Fetch lists no models.WorkBuddyAdd Router One to WorkBuddy as a custom modelUse Settings → Model → Custom with the full /v1/chat/completions URL, your API key and an exact catalog ID; custom-model costs bill to your Router One key.Provider setupConfirm the OpenAI-compatible provider settingsUse this when you need the base URL, authentication shape, or request contract behind the desktop-client fields.Model selectionChoose a live model from the catalogCompare current model IDs, capabilities, context windows, and posted pricing before adding a custom model.Self-hosted web UIServe a team through Open WebUIAdd the gateway as one OpenAI API connection and the model catalog appears for every user on your instance.Self-hosted chat UIRun LibreChat on the gatewayAdd the gateway as a custom OpenAI-compatible endpoint in librechat.yaml and pick catalog models for every user on your instance.Desktop and Docker RAG appSet up AnythingLLM's Generic OpenAI providerEnter the /v1 URL, key, exact model ID and context window in Settings → LLM or the Docker .env; keep the built-in embedder for document chat.Self-hosted knowledge-base appAdd Router One as a FastGPT model channelOne OpenAI-protocol channel in the bundled AI Proxy: /v1 base URL, exact model IDs, channel test, then one trace per node call.Self-hosted RAG engineConfigure RAGFlowAdd Router One as an OpenAI-API-Compatible instance for RAGFlow's LLM slot, and keep embedding and rerank models on another provider.Knowledge-base applicationConfigure MaxKBConnect the chat model through an OpenAI-compatible provider and configure document embeddings separately.Obsidian pluginConfigure Copilot for ObsidianAdd a BYOK custom provider with the /v1 Base URL and full model IDs; leave Enable CORS off so Quick Chat streams.Browser extensionTranslate pages through Immersive TranslateEnter the full /v1/chat/completions URL as the custom API endpoint (it works in every version; 1.30.2 or later also accepts /v1), then pick a chat model from the catalog as the translation engine.Other clientsBrowse SDK and client setup guidesMove to a dedicated guide for an SDK, coding tool, framework, or another client instead of adapting desktop-client steps.BillingFund the shared wallet with AlipayAlipay credits the prepaid Router One wallet that this desktop client uses for model requests.

Start using Chatbox & Cherry Studio in China

Get your API key