Cursor in China — OpenAI-compatible key, no-VPN gateway

Router One puts 30+ models behind the one key that Cursor's OpenAI slot accepts, topped up in RMB: override Cursor's OpenAI base URL with https://api.router.one/v1, use one Router One key for the chat models you pick, and top up with a card or Alipay — no foreign credit card required. The gateway endpoint is reachable from Mainland China without a VPN. Cursor's own connection is a separate matter: per Cursor's help page, requests made with your own key are routed through Cursor's servers, so the editor still depends on reaching Cursor's backend.

3-step setup

Override Cursor's OpenAI base URL in Settings, paste your Router One key, and add the model you want as a custom model. The Router One side needs no VPN or proxy. Per Cursor's help page (checked 2026-10-01), your own key works with chat models only, and on Teams and Enterprise plans Cursor still adds its Cursor Token Rate to those requests. Router One replaces the model bill for the models you pick, not your Cursor plan. Setting up Cursor outside Mainland China? The global bring-your-own-key guide linked below walks through the same override.

1. 1Create a Router One API keySign up at router.one and create an API key in the dashboard. Top up by card or Alipay on the hosted checkout, or with USDT/USDC — no foreign credit card required.
2. 2Override the OpenAI base URL in CursorOpen Cursor Settings → Models, paste your Router One key into the OpenAI API Key field and save it, then turn on "Override OpenAI Base URL" and set it to https://api.router.one/v1.
3. 3Add a model and send one test messageAdd the exact model ID from /models as a custom model, pick it in the chat or Agent model selector, and send a short message — the request then appears in Dashboard → Logs with its model, tokens and cost.

# Cursor → Settings → Models → OpenAI API Key
Base URL: 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.

OpenAI's proposed November 12, 2026 shutoff and your own key

On August 28, 2026, OpenAI announced that it intends to wind down its contract providing OpenAI models to Cursor, with a proposed shutoff date of November 12, 2026, and that it will not provide future models to Cursor. The date is described as proposed, so check OpenAI's and Cursor's own announcements before planning around it. That contract covers the OpenAI models Cursor serves on its plans. The setup on this page is a separate path: Cursor sends the custom models you add to the base URL you set, and Router One bills them: plan quota for plan-covered models, otherwise your wallet. Per Cursor's help page (checked 2026-10-01), your provider bills own-key requests directly, own keys only work with chat models (for OpenAI keys, standard non-reasoning chat models), and on Teams and Enterprise plans the Cursor Token Rate still applies. Two points are not verified: how Cursor treats the override after November 12, and whether it accepts newer reasoning IDs such as openai/gpt-6-sol or openai/gpt-6-astra as custom models with their full behavior, reasoning effort included. Send one request with the model you plan to use and confirm it in Dashboard → Logs before relying on it.

FAQ