Prerequisites
- Cursor Pro: the “Override OpenAI Base URL” setting is gated behind the Pro plan. Free-plan accounts can’t follow this guide.
- A GMI Cloud account at console.gmicloud.ai
- Cursor installed
- About 5 minutes
Step 1. Get your GMI API key
- Sign in to console.gmicloud.ai.
- Open API Keys → Create API Key.
- Copy the key now, it won’t be shown again.
Step 2. Open Cursor’s model settings
In Cursor, open Settings → Models (or⌘ , then search “Models”).
Step 3. Add the GMI base URL
Scroll to API Keys.- Enable OpenAI API Key and paste your GMI API key into the field (Cursor uses the OpenAI key slot for any OpenAI-compatible provider).
- Enable Override OpenAI Base URL.
-
Set the URL to:
Step 4. Add the models you want
In the Models list at the top of the settings page:- Click Add or search model.
- Type the GMI model ID (e.g.
anthropic/claude-opus-4.7,zai-org/GLM-5.1-FP8,moonshotai/Kimi-K2.6,deepseek-ai/DeepSeek-V4-Pro). - Toggle the new model on.
Step 5. Use it
Open any chat or Composer panel and select one of your GMI-routed models from the dropdown. Inline edits and⌘ K work too.
Tips
- Mixing providers. You can keep Cursor’s built-in models on (Composer 2.5, Sonnet 4.6, etc.) and add GMI models alongside them. Cursor only uses the GMI base URL for models you added manually.
- Bad model name. If a request 404s, the model ID is wrong. GMI model IDs always include the provider prefix (e.g.
openai/gpt-5.5, notgpt-5.5). - Pro required. The OpenAI API Key field alone doesn’t change routing, both toggles (key + base URL override) must be on.
Next steps
- Try Claude Code or Codex with the same GMI account.
- Stuck? Email support@gmicloud.ai.