Connect Cursor to an OpenAI-compatible endpoint
Use a separate router.cheap key for development, keep it out of source control, and point Cursor at the documented OpenAI-compatible base URL. Settings names can change across Cursor releases, so verify them in the current client UI.
Connection checklist
- Create a router.cheap account and an API key with only the access your project needs.
- In Cursor's model or provider settings, choose a custom OpenAI-compatible provider.
- Set the base URL to
https://router.cheap/v1, paste the key, and select a model returned by/v1/models. - Send a short test prompt, then verify usage and latency in the dashboard.
Keep editor traffic safe
Use environment-level or app-level secrets, rotate keys when a machine is shared, and avoid sending private repositories to a model until your data-handling requirements are satisfied. See security overview.
Frequently asked questions
Can Cursor use Claude models too?
It depends on the provider mode and model exposed to your account. Use the appropriate compatible endpoint and verify the model in the live catalog.
Why does a model not appear?
The model may not be enabled for your account, the identifier may have changed, or Cursor may cache provider settings. Recheck /v1/models and the current docs.
Should I use my OpenAI key?
No. Use a router.cheap key for the router.cheap base URL and keep provider credentials separate.