Clarifying June 16 Pro Changes

I have the exact same question regarding Cursor’s ‘Max Mode.’ While it’s clear that Max Mode impacts models like GPT-4o and Gemini, I’m wondering if Cursor treats Max Mode and non-Max Mode differently for other models as well.

Specifically, I’d like to understand:

  • Context Management: Does Cursor employ any context compression or optimization techniques specifically for non-Max mode to manage token usage?
  • File Reading Limits: How many lines does Cursor read for each tool call in non-Max mode, especially now that the UI no longer explicitly shows the line range (e.g., ‘read xxx file line 1-200’ or ‘line 1-750’)? It’s hard to discern the difference between Max and non-Max without this information.
  • Tool Call Limits: Are there different tool call limits between Max Mode and non-Max Mode for models other than GPT-4o and Gemini? (We know Max Mode generally allows more, like 200 calls, compared to 25 in non-Max).
1 Like

(this was posted in a removed topic, so I’m reposting here)

Please consider adding a bit of feedback for the user with regards to limits. You mention two types of users, and the second (those that are familiar with usage-based pricing) probably has a good grasp on what affects cost, but your average user (the former group) has absolutely no idea what is more expensive.

The current implementation provides zero feedback to the user. Imagine going grocery shopping, but you have no idea how much any of the items cost, or how much money is in your bank account. You know you’re getting paid, and you have some money in there, but the only feedback you get is when you get to the counter whether there is enough money in your bank account. That’s it. It’s very hard to be a smart consumer when you don’t know the amount you have and you don’t understand how much something costs.

I’m NOT asking for highly technical information. Perhaps just a colored progress bar. Green, you’re in within your local limit, yellow you’re in your burst and you can see it actively dropping, red you’re on auto-only mode. Then I’d know, oh, I only get roughly X % back a day, and I know I have a big day coming up, I’d better back off. In short, it allows me to be a better consumer. I can budget, I can make educated decisions about when I need a more powerful model and how much that’s going to “cost” my available budget. It even shows me when I’ve recovered my local limit. You could add tooltips to this explaining it, and explaining how to reduce and save budget.

It’s just an idea. I know you have costs, and I respect the incredible value you bring. But I can’t responsibly use it without more information.

On a separate note, it would be useful to know what model was chosen when in auto mode. That way if it’s doing a good job, I can begin to make rational decisions when I do force a model rather than just blindly going, “well, this is a tricky problem… and X model is the best right now, I better use the most expensive”.

Just things that I think would qualm a lot of the noise. Right now we just don’t know, until we get up to the counter and find out NOPE, no money in the account.

4 Likes

We introduced Pro+ on June 24! We’re still figuring out how to include it in the Pricing | Cursor - The AI Code Editor page without introducing too much complexity.

2 Likes

We count up the number of tokens the agent model has used, and we turn that into dollars using API list prices. We never show a rate limit on Pro if you’ve used under $20 of compute by this measure.

1 Like

We need to add an indicator on the client side that shows the size of the remaining context of the session and the amount that has been consumed.
Rate limits need to be exposed, and we have the right to know exactly how much context we’re using and what rate limits we’re going to be subjected to.

pro plan says “Access to Background Agents”. There should be the additional information that you have to activate usage based pricing for that!

I hit the rate limit today on claude sonnet. Would be nice to have a warning sooner. To hit the wall out of the dark hurts badly! Especially when reset is at end of paying month. I switch to claude code for now.

There is no indication how a model selection or max mode influences usage. I need a motivation not to use max mode. Without indication everyone will use max mode.

5 Likes

The plan moved from request limits to compute limits

If it has been changed, why is there still a 1x request statement?

TY! You can actually just enable MAX mode (UI is misleading) :slight_smile:

Auto mode: Edit your mode (e.g. Agent) → Model selection, switch on Auto.

Don’t recommend at the moment, tho :slight_smile:

Agreed, this is poorly/ambiguously worded.

Initially, it reads like - “whoo, I get Background Agents!”

Not - “oh, I now have access to the option to pay for Background Agent usage”

Idea: There should be “Auto context size”. Cursor knows the current context usage, and could most probably auto-adapt request size. Win-win for everybody.

sorry, but I will not thank you for your explanation because what you have been doing is acting like an amateur company, changing the rules without notifying anyone and not explaining correctly how you charge for the services you provide.

The last straw was to release the Max mode for a while and now remove it without warning, a childish strategy so that we, the users, buy the Max plan because it is evidently a thousand times superior to the normal mode.

I will start evaluating other options immediately. The Cursor is not a reliable company, despite the excellent tool.

You can use MAX in normal Pro plan now :slight_smile: (tested with 1.2.1)

You can’t change the terms of an agreement without the users explicitly agreeing to it – that’s illegal.

On top of that, everything is slower, even when you pay for it and we still don’t have any clarity of HOW charges are actually calculated. This is a very bad look for Cursor. You need to deal with this in a real way and do it right. The docs don’t provide any kind of clarity.

Max always worked in Pro plan :slight_smile: or did you mean something else?

Not true, it lead to usage based pricing page (at the time I tried).

@leoing Could it be that you had reached a limit? Im using Max daily with Usage Based Pricing off on my personal Pro plan.

No, that was in the 500 credits days, which I totally underused.

1 Like