Skip to main content

Connecting in Cursor

VPN required

Cursor proxies requests through its own servers, so an active VPN is required for it to work. This comes from Cursor itself, not from Explyt.

Paid Cursor subscription required

Connecting an external LLM gateway requires a Pro subscription or higher. Custom API keys are not available on the free plan.

  1. Open the Cursor settings: Cmd/Ctrl + Shift + J → the Models section

  2. Expand the API Keys block:

    • Turn on the OpenAI API Key toggle
      • The Enable OpenAI API Key window appears
        • Click the Enable OpenAI API Key button
      • Paste the key issued to you by the administrator into the API key field
        • If you see these instructions but do not have an API key, contact your organization's administrator
    • Turn on the Override OpenAI Base URL toggle and paste the OpenAI-compatible URL issued to you (<YOUR_URL>)
      • If you see these instructions but do not have an OpenAI-compatible URL, contact your organization's administrator

  3. In the model list at the top, turn off all built-in Cursor models (switch the toggles off)

  4. Scroll the model list down, then click the + Add Custom Model button

  5. Add the models supported by Explyt by name (shown with auto as an example)

    • To get the full list of models, contact your organization's administrator or open <YOUR_URL>/models
    • Main recommended models:
      • auto – maximum availability (uptime) and high quality
      • Anthropic/opus-5 – Anthropic model with high-quality answers
      • OpenAI/gpt-5.6-sol – general-purpose OpenAI model

    Cursor: adding a model by name

    Cursor: enabling the added model

  6. In the chat window, expand the model list

  7. Turn off the Auto toggle (this is the mode in which Cursor picks a model on its own), then choose the added model (auto or another one)

    Cursor: choosing the added model

For errors, see Error messages.