Cursor ai model settings

The power of Cursor ai lies in its deep integration of large models, where users can not only use built-in models, but also freely configure custom models. The setup is also very simple. The following is the detailed setup method:

Open the settings interface

• Click the gear icon in the upper right corner to enter the settings interface.

• In the menu on the left, select Models.

• You will see that the system provides some large models by default, such as GPT-3.5 and GPT-4, which can be directly selected for use.

Add a custom model

If you need to use another AI model, you can add it as follows:

At the bottom of the model list, click the Add Model button.

In the input box that pops up, enter the model name (such as deepseek-v3 or deepseek-r1 ).

Note: The model name must be entered accurately, otherwise it will not be recognized.

After adding, you need to configure the API Key and request address:

DeepSeek API Application address: https://platform.deepseek.com/usage

API Key: Go to the corresponding official platform to obtain the authorization key.

The official interface documents of the request address will be explained. The DeepSeek is: https://api.deepseek.com/chat/completes.

After the settings are completed, we can click the Verify button to see if the settings are successful. If there is no error message, the model we added will also appear in the model list.

Let’s remove the others, check ☑️ and then you can start using the following two.

In this way, you have successfully configured a custom model and can switch to programming assistance, code generation, or smart conversations at any time using different AIs.