Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cursor removed cost information from the usage page and CSV export

forum.cursor.com

Post reply on HN
Print view View original

151–160 of 172 posts

Re: Cursor removed cost information from the usage page and CSV export

#151

Post by cyanydeez »

yojo wrote: post #43
visarga wrote: post #36

Earlier quoted context omitted.

The system prompt part is surely cached across all users.

You still pay cache token costs on API calls. Cache cost/token are 90% lower, but you pay it every single turn. I’m not sure if they let you skip the cache write cost on the first turn. That would imply cross-user caching infrastructure or special casing the default system prompt to give you a discount. Maybe? Away from the computer but you could try a “hello” in a fresh session and see what was billed.

Its inexpensive to reserve KV cache for the first turn and would benefit users, given the first turn already requires costly locating and allocating a model slot for a user.

So yeah, when they banned tgird party harnesses there was a technical and $ case to have.

Re: Cursor removed cost information from the usage page and CSV export

#152

Post by cyanydeez »

Groxx wrote: post #55
tosh wrote: post #22

I can only recommend to regularly measure how many tokens a harness+model combination uses for a certain task There are huge token efficiency/bloat differences between agents while working on the same tasks, using the same model, in the same environment Yesterday I ran 10 agentic tasks using GPT 5.6 Sol in an ubuntu 26.04 vm a couple of times with different harnesses and got vastly different token usage. +-----------…

Running some local models and wondering what insanity was consuming 100k+ tokens to respond to "hello world" was rather eye-opening, yeah. Full of pointless fluff.

I think prompt engineering went way to far into verbosity when at the same time agent and tool calling are much more important. Now a small system prompt can grab the contect it needs based on user context before bloating. On local models, i use dynamic context pruning.

Re: Cursor removed cost information from the usage page and CSV export

#153

Post by nijave »

bonestamp2 wrote: post #83
tosh wrote: post #22

I can only recommend to regularly measure how many tokens a harness+model combination uses for a certain task There are huge token efficiency/bloat differences between agents while working on the same tasks, using the same model, in the same environment Yesterday I ran 10 agentic tasks using GPT 5.6 Sol in an ubuntu 26.04 vm a couple of times with different harnesses and got vastly different token usage. +-----------…

> Do not underestimate how much popular harnesses are spamming the context window. The context window is very important. Do we have any insight into whether it is actually spam and not useful info such as project or programming language specific context?

On Claude Code you can run /context and it'll explain everything

Re: Cursor removed cost information from the usage page and CSV export

#154

Post by nijave »

adoltech wrote: post #113
tosh wrote: post #22

I can only recommend to regularly measure how many tokens a harness+model combination uses for a certain task There are huge token efficiency/bloat differences between agents while working on the same tasks, using the same model, in the same environment Yesterday I ran 10 agentic tasks using GPT 5.6 Sol in an ubuntu 26.04 vm a couple of times with different harnesses and got vastly different token usage. +-----------…

> The context window is very important. It is everything. My experience with Claude Code is that you have to decide when to compact to make it efficient. It defaults everything to 1M context and it will never keep it in check. It is strange how little cache reads you hit in smol, that may be a configuration issue.

There's an env var you can set to tell it when to compact. It's especially helpful for models with big context that lose coherence much earlier.

Re: Cursor removed cost information from the usage page and CSV export

#155

Post by oefrha »

redox99 wrote: post #10
aroman wrote: post #5

I was an early and passionate adopter and paying customer of Cursor (since 2023!), but it’s probably been 6 months since I opened it. These days I “write” code with claude code and codex, and read/review it on GitHub. If I need to read it locally, I use a plain text editor. Can someone help me understand what value cursor offers in 2026?

Cursor has two benefits 1) It's still an IDE. Because of pricing I mostly use Codex, but I always have a VSCode/Cursor IDE open, thus have to juggle between the two. Working directly in the IDE is more comfortable. For full on vibecoding that might be worse, but when you want to do a deep review of the changes, an IDE is way better than reading a diff on github. 2) It supports every model. It's often very helpful to…

Cursor as an editor/IDE when you take away LLM features is just a worse VSCode (1) lacking some useful first party features, e.g. highlight of staged changes; (2) where a significant number of extensions can’t be found — yes, I know you can manually install vsix but that’s a pain. I moved back to VSCode once I no longer need Cursor’s (top notch at the time) auto complete.

Also, Cursor really pushes you to use their agent stuff, I had to close/switch just to get to the goddamn code whenever I opened something in Cursor. VSCode is still happy to be an editor where code is centered for my review.

Re: Cursor removed cost information from the usage page and CSV export

#156

Post by blehn »

aroman wrote: post #5

I was an early and passionate adopter and paying customer of Cursor (since 2023!), but it’s probably been 6 months since I opened it. These days I “write” code with claude code and codex, and read/review it on GitHub. If I need to read it locally, I use a plain text editor. Can someone help me understand what value cursor offers in 2026?

Easily switching between models. Re: the local read/edit case, it's a bit more seamless than opening in a separate editor.

That's about it.

Re: Cursor removed cost information from the usage page and CSV export

#157

Post by eleventen »

shevis wrote: post #148
eleventen wrote: post #146

Earlier quoted context omitted.

I'm surprised that their biggest feature has not been mentioned: The permissions model is much less noisy in Cursor. Every 30 seconds in claude you get a new, elaborate, contrived bash command that claude wants to run. It's some combination of 10 things you've already granted permission for, but this one is new! Cursor's auto-review run mode fixes that https://cursor.com/docs/agent/security/run-modes I know it's a co…

How is that different from claude’s “auto” permission mode?

I was not aware of auto mode in Claude. In fact, it looks like Claude had it before cursor. Cursor has workspace scoping in a way that Claude does not seem to, but my comment above is mostly moot.

Re: Cursor removed cost information from the usage page and CSV export

#158

Post by zuzululu »

tosh wrote: post #125
zuzululu wrote: post #98

Earlier quoted context omitted.

this benchmark is a very misleading because it doesn't necessarily point to these harnesses saving usage and much of the harness that comes with codex for example is designed at cross functional agentic usage which you will be leaving behind by using a different harness. openai spends a lot of time as does claude. also note that cached is what makes up bulk of the total and codex and claude has huge discounts in that…

smol currently is very simple so it definitely does less things, like no subagent orchestration I will look into how token usage looks like for longer sessions and more complex tasks re caching: the cache ratio for this bench looks 'bad' for smol because it often finishes a task before caching kicks in (caching starts at 1024 tokens) thank you for flagging this

sorry i didn't mean to call you out just wanted to point out at the comments thinking this means using sol/pi you can get many fold savings in tokens which isn't true

smol looks interesting i think it could have a potential niche although tokens are only going to get cheaper and cheaper here

Re: Cursor removed cost information from the usage page and CSV export

#159

Post by tosh »

kelnos wrote: post #134
tosh wrote: post #119

Earlier quoted context omitted.

in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds useful can oversteer the model and make it second guess or take a more complicated route than it normally would (you can see this when looking at traces with and without that injected context) often harnesses also mention in their syst…

> in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens How do you tell, though? I guess what I'm asking is: the data you presented shows some crazy differences, but the token burn alone doesn't tell us enough. What was the output of the task like? Did the harnesses that burned fewer tokens give you as good a result as the ones that burned…

I agree, only looking at the token burn is not enough

in this case it was 10 tasks and all harnesses could complete the tasks successfully, of course now the question is: will this hold for more and more complex tasks but I had to start somewhere :)

Checksum: Compute a file’s SHA-256 checksum and save the exact digest to an output file.

Log correlation: Correlate nested service logs to identify and summarize a request’s complete execution path.

CSV report: Parse quoted CSV data and aggregate paid orders and exact decimal totals by region.

JSONL join: Join related JSON Lines datasets and produce a correctly grouped and ordered report.

Archive repair: Find the correct version of a corrupted file in a tar archive and restore it.

SQLite migration: Safely migrate a SQLite database schema and verify the resulting data and constraints.

Python bug fix: Repair an interval-merging implementation so it passes visible and hidden edge-case tests.

Python CLI: Implement a robust command-line program that reads JSONL and reports validated statistics.

Multi-file feature: Add an atomic feature across a small Python package, CLI, and associated tests.

Pipeline repair: Fix a Make, shell, and Python reporting pipeline so it handles general input and passes verification.

Re: Cursor removed cost information from the usage page and CSV export

#160

Post by tosh »

mikodin wrote: post #132
tosh wrote: post #119

Earlier quoted context omitted.

in my book anything that is (I'm sure well intentioned) and injected to help the agent — but doesn't help it — is a waste of tokens but even injected context that when I read it sounds useful can oversteer the model and make it second guess or take a more complicated route than it normally would (you can see this when looking at traces with and without that injected context) often harnesses also mention in their syst…

I am super curious how much in your opinion the extra prompting is useful? >often harnesses also mention in their system prompt locations of markdown files that the model can consult if the model thinks they might help >that hint alone as part of the system prompt can be strong enough to make the model read in more tokens than would have been necessary I purposefully do this as I imagine it is useful. In my project I…

I do think prompting and reference files (e.g. for architecture, tech stack, …) can be extremely helpful. I also do this in my projects (challenge is keeping drift of these documents at bay).

What I wanted to emphasize is that whatever is in the context (whether system prompt or user message does 'steer' the model in a strong way, so everything in the context affects overall performance in a way. Even if it is 'just' net neutral it takes space up in the context window.

The context window is very very precious, everything that goes into it should help (not just hopefully help).

The challenge is coming up with good stuff to put into that context. A good agents.md file will be better context than whatever the popular harnesses have in their system prompt.

Also good to keep in mind that newer models are very good and more agentic than older models so they are better at exploring their environment based on the tasks you give them.

Post reply on HN