Models

With Composer, ⌘ K, and Terminal Ctrl/⌘ K, you can easily switch between different models of your choice.

​

Model usage

Cursor has two types of models:

• Premium models: These models are usually more intelligent and count against your monthly request quota based on your subscription plan.
• Free models: These models are usually less faster and have unlimited usage on a paid plan.

If you exceed your monthly premium model quota, you can enable usage based pricing to continue using these models.

For more information on model usage and quotas, see Account Usage.

​

Available models

Cursor has a wide range of models from a variety of providers. See the table below for a complete list of available models.

¹ Counts as 2x fast requests
² Counts as 1/3 fast request
³ 10 requests/day included on paid plan
⁴ Free plan gets 500 requests/day ⁵ Set to the ‘high’ reasoning effort

​

Model hosting

All models are hosted on US-based infrastructure, either by the model’s provider, by Cursor, or by a trusted partner.

As detailed in our Privacy Policy and Security pages, with Privacy Mode enabled, neither Cursor nor any any of the model providers will store or use your data outside of the specific request you make. All data is deleted shortly after each request is fully processed.

You can read more about this on our Privacy page.

​

Model dropdown

Underneath the AI input box in both the Chat and CMD+K modes, you will see a dropdown that allows you to select the model you want to use.

For any models not visible in the dropdown, you can enable and disable them in your Cursor Settings.

​

Auto-select model

You now have the option to allow Cursor to intelligently select the best model for your needs.

This is done based on what model is best suited for the task at hand, and the model’s performance in the past. While this often works best for keeping you in the flow, you can always manually select a different model by disabling this option.

​

Context windows

The ‘context window’ is the amount of tokens that we provide the model with, for it to use in the conversation.

To optimize the AI performance, Cursor curates the context provided to the model to ensure the best experience.

In the Agent, the context windows is 60,000 tokens by default. For Claude 3.7 specifically, the window is up to 120,000 tokens, due to it’s better performance with longer context windows.

For Cmd-K, we limit to around 10,000 tokens to balance speed and quality.

For longer conversations, we automatically summarize the context to preserve token space. Note that these threshold are changed from time to time to optimize the experience.