Cursor setup
Cursor lets you bring your own OpenAI-compatible key and base URL. Configure it once and use TokenMilo’s Claude and GPT models in Cursor chat and agent.
Updated 2026-11-16
Cursor’s settings UI changes often; menu names may differ slightly, but the steps are the same: key → base URL → models.
1. Add your key and base URL
- Open Cursor Settings (
Ctrl/Cmd + Shift + J) → Models. - Under API Keys, paste your TokenMilo key into OpenAI API Key.
- Enable Override OpenAI Base URL and enter
https://api.tokenmilo.com/v1.
2. Add models
Click + Add model and add the model IDs you want:
claude-sonnet-5-5
claude-opus-5-5
gpt-6.1-solSee the full model list. Untick built-in models that TokenMilo doesn’t serve, then click Verify.
3. Use them
Pick the model from the dropdown in the chat panel (Ctrl/Cmd + L). Costs per request appear on the Usage Logs page of the console.
FAQ
Do I still need a Cursor plan?
Chat and agent requests with your custom models are billed by TokenMilo. Some features such as Tab completion always use Cursor’s own models and follow Cursor’s pricing.
Why does key verification fail?
Usually the base URL is missing /v1, or Cursor verifies with a built-in model name that TokenMilo doesn’t have. Add a TokenMilo model first, enable only that one, then verify.
Related guides
- Cline setup (VS Code) — Configure the Cline coding agent with Claude via TokenMilo.
- Kilo Code setup — Add a TokenMilo custom provider to the Kilo Code agent.
- Roo Code setup (VS Code) — Use Claude 5.x and GPT-6 in Roo Code via the OpenAI Compatible provider.
- Continue setup (VS Code & JetBrains) — Configure Claude and GPT in Continue’s config.yaml.
- Trae custom model setup — Add Claude and GPT to the Trae IDE as custom models.
- Zed setup — Use TokenMilo models in the Zed editor’s agent panel.
Need an API key?
Sign up at TokenMilo, top up, and create a key in the console in under a minute.