Skip to content
Fast Inference
DOCS / Cursor
Integration

Cursor

Use Cursor's OpenAI API key and base URL controls to route supported chat models through Fast Inference.

Cursor supports custom API keys for standard chat models and exposes an OpenAI base URL override in its Models settings. The fast cursor adapter is still in preview, so use Cursor's verified settings UI and reverse the change there.

Configure Cursor manually

  1. Create a project key

    Create a key in API keys and keep it available while you configure Cursor. Do not paste the key into project files or Cursor rules.

  2. Open model settings

    Open Cursor Settings → Models → API Keys. Enter the Fast Inference project key in the OpenAI API key field and set the OpenAI base URL override to:

    text
    https://api.inference.net/v1

    Choose a standard chat model ID from the model catalog, then use Cursor's Verify action.

  3. Send a test prompt

    Start a new standard chat with the custom model. After the response completes, confirm its spend and tokens in Usage.

CLI availability

The released fast CLI does not currently register fast cursor on. Manual setup is not tracked by the CLI, and fast cursor off cannot restore your prior Cursor settings.

Revert the manual setup

Return to Cursor Settings → Models → API Keys. Disable or remove the custom OpenAI key, clear the base URL override, and reselect the Cursor-managed model you used previously.

Troubleshooting

  • Include /v1 in the base URL override.
  • Use a model supported by Cursor's standard chat custom-key flow.
  • Start a new chat after changing the endpoint or model.
  • If verification fails, test the same key and model with the getting-started request to separate gateway and Cursor configuration issues.