Can someone explain the pricing to me

What does this mean? I am paying for pro plan 20$, does this mean I will pay additional 36$ or additional 56$ to my 20$ monthly fee? I read the docs but I still don’t understand how these bonuses work.

The 34$ are bonus so you will NOT pay for for them
you only paid 20$ and you wont pay anything else
Cursur give you limit at 20$ with extra bonus

The pricing has been confusing in many ways thus far. It is improving, but still confusing as of yet.

Cursor doesn’t impose a strict limit. They guarantee “at least” $20 of usage, but they may potentially offer more than that. Hence why you are seeing a “bonus” of $36.14. Exactly how that is determined I cannot say, and we may never know.

I’ve become an extreme user of Cursor’s agent, and I’ve recently moved to the Ultra plan. I started on Pro for the first few months, was on Pro+ for about a month, where I was given usage to around $100 or so, then also paid over $150 of pay-as-you-go usage. So I was given some extra, but in the long run, I ended up spending more than I would have if I had just gone strait to the Ultra plan for $200/mo and the usage limits on that are WAY beyond Pro+.

Usage isn’t determined….well, deterministically, I guess is the best way to put it. I’ve run out of claude-4-sonnet usage on some days, then on later days I was able to use it again without having to pay-as-you-go. Some of it is based on the overall usage of any given model at the current moment. If you select a specific model, say claude-4-sonnet or gpt-5-fast, it is a lot easier to burn through your allotment of requests for your given plan.

If you use the Auto mode of Cursor, it distributes your requests over all the models it is capable of using, and according to their docs you can get more usage out of any given plan by using Auto. When I use Auto, it usually uses claude-4-sonnet (there are just certain output characteristics, no thinking steps, etc.), but Auto can choose to use any model that Cursor deems fit, and sometimes you will notice that the output changes, you might see thinking steps appear (or disappear), etc. Sometimes the nature of the code will change as Auto switches between models for different requests.

Auto will usually allot you a lot more usage each month, than sticking with a single model. Claude usually allows for a lot fewer requests than other models (not sure how GPT-5 will pan out there in the long run), Gemini seems to allow for about 3x or so what is allowed with Claude. For mundane stuff, I’ll often explicitly use GPT-4(something), as it allows for significantly more requests, and I’d rather not burn Sonnet requests on simple asks, research, etc.

You can manage your usage each month. Cursor’s recommended approach is Auto, but sometimes that isn’t as effective as it could be (especially now, there seems to be a severe bug with Auto usage right now clamping conversation lengths to nearly zero). When you are using a specific model, try to use the one best suited for the task. You can enable Custom Modes, and configure various modes to use specific models and allow or disallow certain behaviors (i.e. I have a Research custom mode that uses GPT and disallows code file editing, and a Planning custom mode that uses Gemini and disallows code file editing, etc.) Each mode can be assigned a hotkey, so you can quickly switch modes.

Also, I think the latest version of Cursor finally properly supports using a different model in each tab (previously, and I didn’t realize this at first, when you switched the model, that was GLOBAL, and affected ALL TABS! Oh, did that lead to a few mishaps!)

Anyway. There are a number of ways to optimize your Cursor plan usage. I’d delve into the docs and explore the UI and learn how to optimize cursor for your own use cases.

5 Likes

Thank you so much for such a detailed explanation!

1 Like

Right now the “bonus” for me correlates directly with my Auto and free GPT-5 requests.

Well its 9 cents off, but seems highly correlated.

I have yet to experience Auto getting throttled or nerfed when I go beyond $20 usage.

1 Like

I’m on the $20 plan, but my usage has exceeded the limit. I just want to confirm that I’ll still be charged only $20, as it shows the cost to me as $0.

Yea, you’re all good. You won’t be charged. Only the claude and gpt (if it was outside the promotion week) count towards your $20/mo usage limit. And you can’t really be charged extra on the Pro plan unless you manually enable MAX I believe. You will get an in application warning when you are near or over your limit. You can check your usage in the application. So did you actually get notified that you exceeded your limit, because it looks like you haven’t, since you’ve mostly been using Auto.


I’m on the $20 plan, and I had around $40 in bonus usage after using the GPT-5 model during the free week. After not using Cursor for around 24 hours, all my bonuses were gone. Has anyone else experienced this?

Yea I experienced this too. I think it was their quick fix to some people having GPT-5 being applied to their usage limits. I had like $60 in bonus usage and now none. I think it’s just a visual thing in the application, because the bonuses are just all the non Auto charges over $20 added up.

Thanks to this post I learned that I have more than more than my $20 usage on a Pro subscription.

I continued along and I’m at a bonus of $25.92

image

after which they had enough :slight_smile:

I understand the Pro+ and Ultra options but what does the last option mean “Switch model to Auto”? Is this related to me setting the agent to Claude (didnt like the agent’s behavior in GPT-5)? Also what happens if I switch the model to ‘Auto’? I’m out of credits already anyway…

Auto is a free model; however, it’s going to start costing tokens starting when your subscription renews after 9/15. It is a decent model and great for boilerplate. If you want to be grandfathered into unlimited Auto for a year, you have to get an annual subscription before 9/15. That way your renewal date is a year from now and that will lock in unlimited Auto. More Info: Update to Teams and Auto Pricing

Gpt-5-mini also appears to be free and not count towards monthly usage limits. I wonder if that model would work for you even though you have hit your limit.