Inquiry Regarding Usage Limits on the New Cursor Pro Plan

[user438]

I’m currently on the Cursor Pro plan. I renewed my subscription after the new Pro plan was released. I understood that the previous plan allowed up to 500 “fast” requests and unlimited “slow” requests, but it looks like the new Pro plan imposes a hard limit on total requests. Once I hit that limit, is my only option to either pay for additional usage or upgrade to Pro+ (or a higher) plan? I subscribed because I love how Cursor can edit directories directly—are there any alternative options you’d recommend?

[condor]

hi @user438 and welcome to Cursor Forum.

Thank you for your post.

Cursor is tracking actual consumption of tokens and model instead of counting requests.

There is no hard limit on actual requests but rather based on how much you use up.

You can see your usage in Dashboard > Usage, there is a Included Usage Summary which shows how much you used as included in your plan.

Once you reach your plan usage limit you can either switch to Auto model which is not charged, Usage Based Pricing if you prefer to continue working with premium models or upgrade to a higher plan if that suits your usage better.

You can see more how the token usage works and how to optimize your usage.

Understanding LLM Token Usage

Here is a detailed explanation of LLM (AI) token usage in Cursor: Tokens are used every time you interact with AI models in Cursor. For transparency, token counts are shown as processed and reported by the AI provider. You can check your usage in ‎Dashboard > Usage and, if you have Usage Based Pricing, also in ‎Dashboard > Billing. The dashboard is being improved to show all AI usage of a single request in one line, even when multiple tool calls are combined. Tokens are divided into four group…

[user438]

I’d like to know whether setting “auto” mode allows continuous use of Cursor via prompts regardless of token usage, and if it automatically switches from a high-performance model (while tokens remain) to a lower-performance model once tokens are exhausted.

[condor]

Auto does allow continued use of Cursor even you reach your plan limit. There is no difference in performance based on if you reached your plan limits or not.

[user438]

If I exhaust all my tokens using the Sonnet-4 model and then switch to “auto” mode, can I continue using it without any limits? And the reverse scenario doesn’t apply, right? In other words, even in “auto” mode tokens are still consumed, correct? I’m not very good at English, so this is hard to explain.

[condor]

Yes you can continue using Auto after any model, and while we show the consumption of Auto in Dashboard > Usage, it is not limiting your usage of other models.