# Cursor Integration Guide

Cursor is an AI-powered programming IDE. This guide explains how to use it to call models through the UModelverse platform.

## **System Requirements**

| Platform | Requirements |
| --- | --- |
| Windows | Windows 10 or Windows 11 |
| macOS | macOS 10.15 (Catalina) or later |
| Linux | Major distributions (Ubuntu, Debian, etc.) |

All platforms require a network connection, and a **Cursor Pro plan or higher** (the free tier only supports Auto mode and cannot call custom models).

## **1. Install Cursor**

Go to the [Cursor official website](https://cursor.com/) to download and install the client for your platform.

## **2. Configure the UModelverse API**

### 2.1 Obtain an API Key

Visit the [UModelverse console](https://console.ucloud.cn/modelverse/api) to get your API key. For available models, see the [supported models](https://api-us-ca.umodelverse.ai/v1/models) on the UModelverse platform.

### 2.2 Enter the Configuration in Cursor

1.  Click the settings icon in the top-right corner, then go to **Cursor Settings** → **Models**.
    
2.  Enable both the **OpenAI API Key** and **Override OpenAI Base URL** toggles, and fill in the fields as shown in the table below:
    

| Field | Value |
| --- | --- |
| OpenAI API Key | Your UModelverse [API Key](https://console.ucloud.cn/modelverse/api) |
| Override OpenAI Base URL | `https://api-us-ca.umodelverse.ai/v1` |
| Model | Add models supported by the UModelverse platform, e.g. `gpt-5.2`, `claude-sonnet-4-6` |

3.  Add the desired model names to the model list, then save to start using them.
    

## **3. Using Models**

In the chat panel, first click to disable **Auto** mode, then select the model you added from the model dropdown to begin a conversation.

## **FAQ**

### Getting "The model xxx does not work with your current plan or api key." or can only use Auto?

The free tier of Cursor only supports Auto mode and cannot call custom models. Please upgrade to a **Cursor Pro plan or higher** before using this feature.

### After completing the configuration, the added model cannot be found in the chat?

Disable **Auto** mode in the chat panel, then manually select the desired model from the model dropdown.

### Getting the error "We're having trouble connecting to the model provider." or "Unauthorized User API key"?

Please troubleshoot each of the following:

-   Confirm the API Key is from the UModelverse platform, copied in full, and contains no extra spaces.
    
-   Confirm the Override OpenAI Base URL is set to `https://api-us-ca.umodelverse.ai/v1`.
    
-   Confirm the model name you entered is one of the [supported models](https://api-us-ca.umodelverse.ai/v1/models) on the UModelverse platform. If a model name conflicts with a Cursor built-in model of the same name, try using a version without dots (e.g. write `kimi-k2-6` instead of `kimi-k2.6`).