[bigyabai]

> I should just use these models more carefully as they could consume a lot of tokens when they are thinking.

Support is right. You cannot ever use a pay-as-you-go service unconsciously. This isn't an all-you-can-eat buffet, they're Tracfone minutes and you'll spend them accordingly.

If you can't square that mentally, maybe the big expensive models aren't a good match for your workflow.

[throwawayround]

If you read my post carefully you can see that the problem is not the cost of the models or the way I use them but something that is not just hidden from the Cursor UI but misleading. It keeps displaying a 200k context limit and also uses summaries to manage the context. You can only see that it pulled 21M tokens worth of data from Anthropic cache for a 4000 token prompt if you export your usage as a csv and analyse.

[bigyabai]

> It keeps displaying a 200k context limit

Some radiometers cap-out at 3.6 roentgen because they assumed that nobody would need a larger figure. That doesn't mean that 3.6 roentgen is the hard-limit on radiation, though.

Again - any PAYG product requires very explicit discipline to avoid getting smacked with a shady bill. AWS, Vercel or Claude.

[throwawayround]

I think we’re talking past each other a bit.

This isn’t really about PAYG discipline or being surprised by a big bill. I had a spend cap. The problem is that, because of how Cursor implements caching, that prepaid usage got consumed in a way that was impossible to see or reason about ahead of time. I didn’t “overspend,” I just got far less actual work out of the same budget than I reasonably should have.

Also, the 200k context cap is a real cap. Claude does not attend to more than that. Cursor even summarizes aggressively to stay within it. The confusing part is that billing is driven by something else entirely: replaying cached prompt state that the UI implies is no longer relevant.

So from a user’s perspective, you’re operating inside a 200k window, MAX is off, prompts are small, and things look normal. Yet each call can still replay tens of millions of cached tokens that you never see and can’t inspect without exporting CSVs after the fact.

That’s very different from “you used more than you thought.” It’s more like the primary cost driver is invisible and contradicts the mental model the product presents. If the UI showed cache size or warned that a call would replay ~20M cached tokens, I’d agree this is just normal PAYG behavior. But it doesn’t.

That’s the issue I’m pointing out.