Override Cursor's OpenAI base URL and add the model name manually.
This guide connects Cursor to the platform so you can reach Claude, GPT, Gemini and others with a single token. Three values are all you need: endpoint, token, model name.
Create a token (starting with sk-) in the console first and make sure the account has credit. New here? Start with your first request in 5 minutes.
Go to Settings → Models in Cursor. First add the model name manually (it must match the platform's model name exactly), then enter the API key and enable the base-URL override.
| Field | Value |
|---|---|
| OpenAI API Key | your sk- token |
| Override Base URL | https://api.router.ai/v1 |
| Custom model name | claude-sonnet-5 |
Before running anything complex, just say hello and check you get a reply. To test the token on its own, call the API directly:
curl https://api.router.ai/v1/chat/completions \
-H "Authorization: Bearer sk-your-token" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","messages":[{"role":"user","content":"hello"}]}'
A JSON response containing choices means you are connected. The call shows up in your billing records shortly after.
Click Verify after filling things in — Cursor only activates the config once verification passes. Note that the override applies to models you added yourself; some built-in features (codebase indexing, tab completion) still use Cursor's own service by design.
Wrong token, a stray space, or a copy that dropped the leading sk-. Copy it again in full.
Almost always the URL suffix. The OpenAI-compatible format needs a trailing /v1; the native Anthropic and Gemini formats must not have it. Check the table above.
The account is out of credit. See top-up methods.
Model names must match the catalog exactly, including case and hyphens. Copy the exact name from the models page.