Cursor Frequently Asked Questions

Why isn't Cursor completely free?

Large-language models cost quite a bit of money to run. To grow Cursor sustainably without compromising our service quality, we need to cover our costs.

What are the premium models?

GPT-4, GPT-4o, and Claude 3.5 Sonnet are all considered premium models. You have 500 fast uses and unlimited slow uses each month for these models.

What are fast and slow uses?

Fast uses of premium models are given first priority by our backend. On Pro, once you hit your fast usage limit, you can still use premium models, but your requests may be queued behind others at times of high load.

What code do you store?

With "Privacy mode", your code is never stored anywhere other than your machine and will never be trained on. Otherwise, we may save prompts / collect telemetry data to improve Cursor.

Do all Cursor features work with an API key?

A few of Cursor's features (including Tab and Apply from Chat) are powered by custom models and cannot be charged to an API key.

How do the plan limits work?

If you go over your limit, we'll nicely ask you to upgrade. You can use up to 50 uses of the premium models for free.

What is cursor-small?

Cursor-small is our custom model that is not as capable as premium models but is faster and useful for quick editing tasks.

Where can I ask more questions?

Feel free to join and post on our forum. If you'd rather keep your question private, you can email us directly at [email protected].

Who owns the code generated in Cursor?

You! Regardless of whether you use the free, pro or business version of Cursor, all generated code is yours and free to be used however you like, including commercially.

What is Cursor Tab?

This is Cursor's native autocomplete feature. It's a more powerful Copilot that suggests entire diffs with especially good memory.