Cursor
Configure Cursor to use Engy models through a custom OpenAI base URL.
This page explains how to add Engy models to Cursor. It is intended for developers who want to use open models from Engy in the Cursor editor.
Prerequisites
Before you begin, make sure you have:
- Cursor with a paid plan. On the free plan, Cursor does not allow custom models and shows the message "Named models unavailable"
- An Engy API key. For details, see API keys
Configure Cursor
Open the API key settings
In Cursor, open Cursor Settings, go to Models, and expand API Keys.
Enter the Engy key and base URL
Under OpenAI API Key, set the following values:
| Field | Value |
|---|---|
| OpenAI API Key | Your Engy API key |
| Override OpenAI Base URL | https://api.engy.ai/v1 |
Turn on the Override OpenAI Base URL toggle, and then click Verify.
Add a model
Under Models, click + Add model, and enter engy/glm-5.2. Turn on the model.
Select the model
In the chat panel, select the model that you added.
Model names
Cursor requires custom model names in vendor/model form. Prefix the Engy model ID with engy/, for example engy/qwen3.8-27b or engy/deepseek-v4-flash-0731.
Engy ignores the prefix, so the model and the price are the same as without it. The part after the prefix must match a model ID exactly. For the list of model IDs, see Models and pricing.
Limitations
- Custom models are available in the chat and plan panel only. Tab completion and Composer continue to use Cursor's own models.
- Cursor sends the requests from its own servers, not from your computer. The configuration therefore works on any machine.