--- title: Cursor removed cost information from the usage page and... description: A Cursor user reports that the Usage page switched from displaying dollar amounts to token counts, making it harder to track daily spending. A Cursor team... canonical: https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Cursor removed cost information from the usage page and CSV export | daily.dev og:description: A Cursor user reports that the Usage page switched from displaying dollar amounts to token counts, making it harder to track daily spending. A Cursor team... og:url: https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z og:image: https://api.daily.dev/og/posts/z3dIrxq1Z.png og:image:alt: Cursor removed cost information from the usage page and CSV export og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Cursor removed cost information from the usage page and CSV export **[Hacker News](https://daily.dev/sources/hn)** · 2 min read · 1 upvotes · 1 comments ## Summary A Cursor user reports that the Usage page switched from displaying dollar amounts to token counts, making it harder to track daily spending. A Cursor team member explains this is intentional: individual plans now show token counts with 'Included' labels, while enterprise plans retain dollar amounts. Dollar figures are still accessible via Dashboard > Spending or by exporting a CSV from Dashboard > Usage, where on-demand charges appear in the Cost column. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community take How the wider developer community reacted, aggregated from 1 discussion and 256 comments across hackernews (as of 2026-08-02). **TL;DR:** The thread is primarily critical of Cursor's recent decision to hide token/cost usage data from users, with a parallel discussion about how different AI coding harnesses vary wildly in token efficiency — with minimalist harnesses like 'smol' using 30x fewer tokens than Claude Code for the same tasks. **Sentiment:** 15% positive · 45% mixed · 40% skeptical **The case for** - Cursor's tab-completion ('Cursor Tab') is praised as best-in-class for hand-editing code. - Cursor's auto-review run mode reduces permission-prompt noise compared to Claude Code. - Cursor now includes Grok 4.5 and Composer 2.5, giving access to multiple capable models under one subscription. - Minimalist harnesses like 'smol' can complete simple agentic tasks at a fraction of the token cost of full-featured harnesses. **The pushback** - Cursor removed dollar-cost visibility from the usage CSV and the in-editor cost indicator, making it hard for users to track spending. - Popular harnesses like Claude Code inject massive system prompts (tools, memory systems, markdown hints) that bloat token usage up to 30x vs. minimal alternatives. - Cursor's IDE experience has reportedly regressed — keyboard shortcuts changed, the CLI now opens a chat interface instead of the project folder. - Token usage data is opaque across most AI coding tools, making it hard to evaluate cost-efficiency or model ROI. - Cursor's pricing is seen as uncompetitive now that Claude Code and Codex subscriptions offer similar or better capability. **By community** - hackernews (skeptical): Commenters are broadly critical of Cursor hiding cost data and bloated harness token usage, with many reporting they've already switched to Claude Code, Codex, or terminal-based agents. **Hottest debate:** Whether Cursor's removal of cost/usage visibility was an accidental bug fix or an intentional dark pattern to obscure spending. **Open questions** - Do the extra tokens injected by full-featured harnesses actually improve task outcomes, or are they genuinely wasteful? - How does smol perform on longer, more complex tasks where context compaction becomes necessary? - Will Cursor reverse its decision to hide per-session cost data for individual users? - Is there a principled way to benchmark harness quality beyond token count (e.g., task success rate, trace quality)? **Highlights** > 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. +-------------+-----------+-----------+-----------+-----------+--------+ | Harness | API total | Input | Cached | Uncached | Output | +-------------+-----------+-----------+-----------+-----------+--------+ | smol | 172,807 | 142,334 | 8,704 | 133,630 | 30,473 | | Pi | 427,211 | 392,767 | 137,216 | 255,551 | 34,444 | | OpenCode | 1,564,429 | 1,523,957 | 1,204,736 | 319,221 | 40,472 | | Codex | 3,005,744 | 2,953,154 | 2,649,344 | 303,810 | 52,590 | | Hermes | 3,856,611 | 3,808,231 | 3,167,232 | 640,999 | 48,380 | | Claude Code | 5,073,137 | 5,029,969 | 4,587,008 | 442,961 | 43,168 | +-------------+-----------+-----------+-----------+-----------+--------+ https://x.com/__tosh/status/2083593799872237680 I'm not surprised that Claude Code is not optimized for an OpenAI model but I was still quite shocked re how much of a difference the harness makes. Disclaimer: I'm working on 'smol' which is a minimalist harness but it's really nothing special, just a minimal system prompt, no skills files, only tool is shell Do not underestimate how much popular harnesses are spamming the context window. The context window is very important. > — [tosh on hackernews · 14 comments](https://news.ycombinator.com/item?id=49136112) > Claude Code injects a ton of tools into the system prompt, including their “memory system” that’s like 10k+ tokens. Depending on your task shape, this can easily double your task cost (e.g. a low context-using job that takes many turns, like a monitoring loop). You should use --disallowed-tools to prune any tools not needed for the task. Note that this is also a perpetual game of whack-a-mole since they’re always adding new tools. > — [yojo on hackernews · 4 comments](https://news.ycombinator.com/item?id=49136204) > (I work at Cursor) You can still see what you’re billed on the Spending page. We did accidentally break dollar costs in the Usage CSV export yesterday while cleaning up an old feature flag. That was not intentional and the CSV export is fixed now. That feature flag also showed a dollar usage graph to some self-serve users. The confusing part was included plan usage shown as $, which is not what you’re billed (on-demand usage is). Some people read it as actual spend, so we decided to remove that graph. > — [jonjohnsen on hackernews · 3 comments](https://news.ycombinator.com/item?id=49136792) > While there's a lot of bloat in the harnesses, almost all of it is cached. Your harness appears to be caching almost nothing. That will almost certainly bode extremely poorly for longer-running tasks than the simple ones you mentioned testing. Benchmaxxing for simplistic tasks could leave you not only suffering in completion rate on complex tasks but also possibly even not end up with the cost gains you're hoping for. And maybe that's fine if the only thing you use agents for is the very simple tasks, which is certainly a defensible decision, but probably bears mentioning when you're comparing it against harnesses with a different design goal. > — [applfanboysbgon on hackernews · 1 comments](https://news.ycombinator.com/item?id=49138242) > If users start questioning the ROI of your AI product just hide the “I” from them. Problem solved. > — [cmiles8 on hackernews · 1 comments](https://news.ycombinator.com/item?id=49136463) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=49135257) · 263 points · 256 comments ## Community discussion Top comments from developers on daily.dev. **@robertoabr** · 0 upvotes > This is terrible. This really hurts my ability to pick models and workflows that are cost efficient in cursor. ## Similar posts on daily.dev - [What Happened to Cursor Pricing? 2026 Guide & 5 Cost Cutting Tips](https://daily.dev/posts/what-happened-to-cursor-pricing-2026-guide-5-cost-cutting-tips-56qhyjlmq) · finout · 0 upvotes · 0 comments - [All roads lead to metered pricing](https://daily.dev/posts/all-roads-lead-to-metered-pricing-yvoujksya) · Kilo Blog · 132 upvotes · 31 comments - [Why token cost is hidden by design in most agent UIs](https://daily.dev/posts/why-token-cost-is-hidden-by-design-in-most-agent-uis-hekzq90vu) · Medium · 1 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Cursor removed cost information from the usage page and CSV export","url":"https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z"},"datePublished":"2026-08-01T16:40:47.897Z","dateModified":"2026-08-02T01:19:20.728Z","description":"A Cursor user reports that the Usage page switched from displaying dollar amounts to token counts, making it harder to track daily spending. A Cursor team...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/866d25c85d464c1658c6c3bf52c863e8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/866d25c85d464c1658c6c3bf52c863e8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"ai-coding","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Cursor removed cost information from the usage page and CSV export"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/cursor-removed-cost-information-from-the-usage-page-and-csv-export-z3dirxq1z","comment":[{"@type":"Comment","text":"This is terrible. This really hurts my ability to pick models and workflows that are cost efficient in cursor.","datePublished":"2026-08-03T16:03:48.348Z","dateModified":"2026-08-03T16:04:27.753Z","url":"https://daily.dev/posts/z3dIrxq1Z#c-0HWoYPaX0","author":{"@type":"Person","name":"Roberto","url":"https://daily.dev/robertoabr","image":"https://lh3.googleusercontent.com/a/ACg8ocIrhn233TOE2pUApapJMZg7nYCFdnK8zisSHxCRVrIFU89R1A=s96-c"}}]} ```