Pricing

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 is cursor-small?

Cursor-small is our custom model that is not as capable as GPT-4 models but faster and useful for quick editing tasks.

What are fast and slow uses?

Fast uses of GPT-4 are given first priority by our backend and are served faster than OpenAI's public API. On pro, once you hit your fast use limit, you can still use GPT-4, but your requests may be queued behind others at times of high load.

What code do you store?

Do all Cursor features work with an API key?

A few of Cursor's features (including Copilot++ 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 GPT-4 for free.

How are Claude 3.5 Sonnet and GPT-4o counted?

Models like Claude 3.5 Sonnet and GPT-4o are counted as GPT-4 uses. You have 500 fast uses in total, and unlimited slow uses each month.

Where can I ask more questions?

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 Copilot++?

Copilot++ is Cursor's native autocomplete feature. It's a more powerful version of Copilot that can suggest mid-line completions and entire diffs.