Unpredictable / high token and subscription costs

I got tired of burning tokens building the ~same UI over and over, so I thought "why not define a format for the review and build a decent UI just once?".

pscanf · Oct 27, 2026 · comment in “Show HN: A little tool to review and understand PRs more easily”

No lab is profitable, it is a moonshot to expect they'll ever recover the billions frontier labs have put in behind these DCs. I never understand this argument everyone tries to make, AI is too expensive -> It will get cheaper as they scale -> AI is too cheap and not sustainable -> No it's very profitable on API -> go back to 1.

written-beyond · Oct 26, 2026 · comment in “OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?”

Bought the $100/month subscription and hit my 5-hour limit with one prompt on default settings (max effort) in their CLI harness. It might be smart but it's unusable compared to other subscriptions right now.

willmorrison · Oct 23, 2026 · comment in “Kimi K3.1 Pro and K3.1 Pro Highspeed”

If a productive application doesn't work and this burns money of your employer you're going to burn, not the AI.

gauntr · Oct 14, 2026 · comment in “Do Frameworks Matter Anymore?”

I understand the ToS, I wish it was more open, but the reality is that API pricing is way too high and a subscription is all that makes sense currently.

joshstrange · Sep 22, 2026 · comment in “JetBrains Air: A System of Products for Agentic Software Development”

That was a few months ago, and the models have improved (quite a bit) since then, but now I'm happy to send my $20/month to get Claude code. It's still frustrating as hell to come down in the morning, having given it a list of tasks to do overnight, with tests to pass before they're "done" and find that it worked for about 20 minutes after I went to bed, and decided that it would stop at "3am" (it wasn't) and "not d…

spacedcowboy · Aug 31, 2026 · comment in “Apple caught off guard by AI demand for Mac Mini and Mac Studio”

I'm regularly hitting 90-100% on my $200/mo sub and will switch to Codex in a heartbeat if they drop these limits. This constant uncertainty is really annoying.

joshstrange · Aug 18, 2026 · comment in “Claude Code May–August 2026 weekly limits promotion”

Years of hand-wringing about programmers being put out of a job and instead programmers are the ones paying $200/mo for LLMs And on the flipside a lot of AI vendor ideas like helping doctors turn voice transcripts into notes has just been annoying for the prospective user--they feel they may as well type it up themselves if they then have to review and correct the AI notes

firasd · Aug 10, 2026 · comment in “The Philippines' big offshoring industry is growing despite AI”

If it doesn't work or I just abandon it halfway it doesn't matter because it cost me $1 and if it's important I'll just pay one more $1 later.

weitendorf · Jul 30, 2026 · comment in “GitHub is the wrong shape for this new world”

I love using Claude but Fable's unusable wrt useful work like cryptography, biology, &c. Kneecapping my productivity when I pay $100/month is annoying af.

NetOpWibby · Jul 22, 2026 · comment in ““We have information that Moonshot distilled Fable for the development of K3””

In such cases, the user will have to rerun the task and it will very quickly double or triple the cost and makes the old average number misleading! I would argue the retry and flaky cost will be many times bigger than the average token cost and that is the true cost the users have to bear.

sinuhe69 · Jul 21, 2026 · comment in “Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling”

My theory is that sycophancy is just intended to prevent the AI from spiraling into a loop of ineffectually "arguing" or fixating on unimportant details, because it's both kind of annoying when it happens AND it's obvious that the model is spiraling and burning tokens uselessly when it decides to be uselessly critical.

midnightbobarun · Jul 17, 2026 · comment in “Ask HN: Is AI sycophancy a way to reduce compute rather than make users happier?”

These kind of things need real humans to test software - but that is too expensive, slow and doesn't scale, especially with the pace of software development today.

deepankvora · Jul 1, 2026 · story in “Show HN: Bytesalt – AI that finds bugs Playwright tests miss”

Making decisions this way is low-risk, and lower-cost than the token cost of vibe-coding something custom. The analogy to dating apps doesn't work - dating apps reward searching far and wide for something perfect, whereas the business world rewards going with what you know and making decisions quickly.

wavemode · Jun 27, 2026 · comment in “Software Is Becoming Marketing”

A while back I gave the same task to both, and Codex used 20x less of my 5-hour limit (both on the $20/month plan). (This annoyed me since I tend to prefer Claude, but the limits at the time made it unusable for anything serious.)

andai · Jun 26, 2026 · comment in “Previewing GPT‑5.6 Sol: a next-generation model”

You can also start to generate a lot of token spend if you do something like "hey make me a stylized slide deck using internal skill / agent XYZ based on commits A through C", which as an engineer, makes presentations building much less painful.

blobbers · Jun 3, 2026 · comment in “Uber's $1,500/month AI limit is a useful signal for AI tool pricing”

The AI boy do neither well. I have had several frustrating sessions trying to explain a simple concept to it and burning through tokens to do something an intern would be able to do in an hour.

Courty · Jun 3, 2026 · comment in “Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai”

Opus 4.7 to 4.8 has become outrageously priced too, up 50%, and 4.6 was already brutally expensive to begin with. API pricing is a real pain.

ianberdin · May 30, 2026 · comment in “Anthropic surpasses OpenAI to become most valuable AI startup”

Which makes total sense! Subscriptions are sticky, that's why the entire software industry moved towards subscription models (as much as we hate it); the person paying $200/month is more likely to stick around than the person who paid $2000 using the API.

mjr00 · May 27, 2026 · comment in “I think Anthropic and OpenAI have found product-market fit”

I completely agree! Its so frustrating that providers (google, openai, anthropic) silo their $20/month consumer subscriptions away from their API access.

ab613 · May 11, 2026 · comment in “Show HN: OpenGravity – A zero-install, BYOK vanilla JS clone of Antigravity”

i've never done vulnerability disclosure, yet, with opus at max effort, i have found some security issues in popular frameworks/libraries i depend on. a proper report can't be one pass, it has to validate it's a real problem, but ask opus to do that and you run the risk of the api refusing the request, endangering your account status. you ask to do it anyway, and write a report and now, you're burning tokens on a re…

0123456789ABCDE · Apr 28, 2026 · comment in “AI uncovers 38 vulnerabilities in largest open source medical record software”

It's why Claude quality is plummeting and people are leaving in droves because the usage limits are pathetic and the API pricing structure is outrageous. All because they can't scale.

petcat · Apr 25, 2026 · comment in “Google plans to invest up to $40B in Anthropic”

To the enterprise. Everything else is burning money and wasting time.

asim · Apr 16, 2026 · comment in “The local LLM ecosystem doesn’t need Ollama”

>>Anecdotally, Claude on the $20/month plan can only run 1-3 queries per 4 hours before rate limiting, often stopping in the middle of a query. The free version is pretty much unusable.

kamaal · Apr 15, 2026 · comment in “OpenAI's $852B valuation faces investor scrutiny amid strategy shift, FT reports”

Once I get competent enough with that I want to play with the MCP for Ghidra. I have grown tired of people committing AI generated code, so I've been working on a library (written by my own fingers) that allows you to "assume" certain functions exist and have AI generate it for you, and use aggressive memoization to avoid it being too expensive.

tombert · Apr 13, 2026 · comment in “Ask HN: What Are You Working On? (April 2026)”

I used GCP GKE -Autopilot which is dedicated node for every customer which is costly on average $30-45/customer + AI API COST. I have launched couple managed openclaw on AlitaGPT and tried OpenAI GPT 5.1, worst and annoying models, it keeps asking for confirmation 10 times before doing a simple task.

Robelkidin · Apr 13, 2026 · comment in “OpenAI GPT worst AI GPT/model vs. Claude/MiniAAX”

I also never hit limits in codex but... codex is $20/mo not $100/mo so it's making me consider relocating the $100 I spend to Anthropic as play money for z.ai and other tools. I think claude-code has great training wheels (codex does not) but once the training wheels come off, and claude-code becomes as unreliable as it has been then it makes you consider alternatives.

fluidcruft · Apr 12, 2026 · comment in “Pro Max 5x quota exhausted in 1.5 hours despite moderate usage”

If you feel that you are not getting a $200/month return on your investment then you should cancel your subscription. I also struggle to understand why you are using a $200/month plan to do investigation and testing when there are $25/month options.

uberman · Apr 7, 2026 · comment in “Ask HN: Why isn't Anthropic eating their own dogfood? A Max subscriber's view”

I downgraded from my $200 a month plan to my $20 plan and hit limits constantly. I try to use the API access I purchased separately, and it doesn't work with Claude Code (something about the 1 million context requiring extra usage) so I have to use it Continue.

dimmke · Apr 4, 2026 · comment in “Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw”

The project's own disclaimer says something about how use "may be subject to the terms of service of third party platforms." That one sentence is doing a heroic amount of work. If the real complaint is that Claude's API is too expensive, fair enough.

rox_kd · Mar 29, 2026 · comment in “Show HN: Run Claude Code using ChatGPT subscription”

I was just planning on using a stack like streamlit, text-embedding-3-small,FAISS for the vector store and it to be driven by a python script. Didn't seem too expensive or too hard based on the handful of queries my team would be using it for, and it was a "low hanging fruit" pain point for my team that I thought could be improved by a RAG chatbot.

overtaxed · Mar 26, 2026 · comment in “From zero to a RAG system: successes and failures”

$40/month at work and $10/month at home, and it's more than I can use. I cannot imagine productively spending $250k/year on LLM coding - you'd need some kind of massive tree of agents reviewing each other's work and I think even then you would struggle to keep them on-task and sanity-checked.

daemonologist · Mar 23, 2026 · comment in “Ask HN: How much are you spending on AI coding at work?”

I run a building design consultancy. I got tired of paying Wix $40/month for a brochure that couldn’t answer simple service questions, and me wasting hours on the same FAQs.

axotopia · Mar 19, 2026 · story in “Show HN: Dumped Wix for an AI Edge agent so I never have to hire junior staff”

I run a building design consultancy for homeowners and architects, not a SaaS firm. Honestly, I'm not going to claim we were trying to build some fantastic ‘anti-fragile alternative’ for the future… I just got tired of paying Wix $40 a month for a brochure no one read.

axotopia · Mar 15, 2026 · story in “Show HN: Dumped Wix, my AEC consultancy's storefront is now an AI Edge”

Intent looks interesting but the fact that they have their own credits system turns me off of it. I pay $200/mo for Claude Code and that's enough for me; I wish I could use Intent with that.

LoganDark · Mar 14, 2026 · comment in “Parallels confirms MacBook Neo can run Windows in a virtual machine”

Currently testing with early users at $49/month (also offering some free subscriptions for getting traction and feedback). Looking for feedback from founders who've struggled with the marketing side, does this solve a real problem for you, or am I missing something fundamental about how technical people want to handle growth?

tsjose · Mar 14, 2026 · comment in “Piqe – AI marketing co-founder that handles community engagement while you code”

Dev becomes more economical, and all of the places where dev was previously too expensive open up. Maybe this time won't work out that way, but history isn't on the side of that prediction.

kpgalligan2 · Mar 7, 2026 · comment in “Tell HN: I'm 60 years old. Claude Code has re-ignited a passion”

They burn tokens scanning files they already saw, guess at dependencies, and give you confident answers based on incomplete context. Lost context = wasted tokens + broken code + time spent fixing what AI was supposed to fix.

atefataya · Feb 26, 2026 · story in “Show HN: Depwire – Dependency graph and MCP tools so AI stops refactoring blind”

I built this for myself because I kept losing track of AI credits, rate limits and token costs across providers.

j0nl1 · Feb 25, 2026 · comment in “Aitracker – Track Claude, Codex, Gemini usage and costs from your terminal”

I opted to upgrade my seat to premium for $100/mo, and I've used it to write code that would have taken a human several hours or days to complete, in that time. I wish I would have done this sooner.

MPSimmons · Feb 17, 2026 · comment in “Claude Sonnet 4.6”

Wait the two problems are apparently the price, and the reliability? And you're asking a company famously burning money building a tool that is used for vibe-coding (aka unreliable software development) to build a replacement?

philipwhiuk · Feb 14, 2026 · comment in “OpenAI should build Slack”

Most “AI + browser” setups still bolt MCP tools onto Playwright and hope for the best, so every click dumps full DOMs, accessibility trees, and logs into the model. That burns tokens, collapses context, and makes long sessions unreliable.

tanmay001 · Feb 14, 2026 · story in “Show HN: Why Playwright-CLI Beats MCP for AI‑Driven Browser Automation”

Kind of ironic as claude code keeps showing this "get $50 bucks for referral" when coding on $200/mo plan, so fucking annoying.

mirekrusin · Feb 9, 2026 · comment in “Testing Ads in ChatGPT”

*First open-source project. Built after getting tired of Mem0's $50/month bills.*

varunpratap369 · Feb 7, 2026 · story in “Show HN: SuperLocalMemory – AI memory that stays on your machine, forever free”

*Show HN: I built a code compressor that saves 30-70% on AI API costs* I'm tired of paying $100s/month for AI API calls when half the tokens are just whitespace and boilerplate.

affanshaiksurab · Jan 31, 2026 · story in “Show HN: I built COON an code compressor that saves 30-70% on AI API costs”

Putting aside the AI aspect entirely, I'm simply curious if this is a viable Overleaf competitor -- especially since it's free. I do self-host Overleaf which is annoying but ultimately doable if you don't want to pay the $21/mo (!).

crazygringo · Jan 27, 2026 · comment in “Prism”

At this point I just assume Claude Code isn't OSS out of embarrassment for how poor the code actually is. I've got a $200/mo claude subscription I'm about to cancel out of frustration with just how consistently broken, slow, and annoying to use the claude CLI is.

frumplestlatz · Jan 23, 2026 · comment in “Unrolling the Codex agent loop”

Out of pure boredom and tired of all these Chat websites selling my data and with ChatGPT's new update on ads - I decided enough was enough and created my own Chat application for privacy. Like every other architect, I searched for a good database and eventually gave up on specialized ones for chat because they were either too expensive to host or too complex to deal with.

neya · Jan 23, 2026 · comment in “Scaling PostgreSQL to power 800M ChatGPT users”

While I have you on the line, I'm also experiencing tons of API request timeouts using Claude Code's own TUI client (on the $200/mo plan!!) and I don't know how to mitigate that, and it is frustrating

pmarreck · Jan 22, 2026 · comment in “Claude Chill: Fix Claude Code's flickering in terminal”

I've been waiting for something like this for ages. Cursor making me pay $20/month when all I use from it is autocomplete was always a little annoying, especially as they changed the UI to push agents more and it got in the way.

notsylver · Jan 22, 2026 · comment in “Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete”

The $20/month one gives you much better models though. All I’m saying is that the vast majority of people who say that AI dev tools don’t work and are a waste of time/money don’t know how and really haven’t even made a serious attempt at learning how to use them.

brokencode · Jan 21, 2026 · comment in “Vibecoding #2”

I tried to use the official gemini-cli to avoid API costs. It’s unusable for agentic work.

basher · Jan 18, 2026 · comment in “Google's "AI Ultra" Is a Storage Plan Disguised as a Dev Tool”

(Using it from Australia may also contribute to its slow perf) Antigravity was also painful to use at launch where more queries failed then succeeded, however they've basically solved that now to the point where it's become my most used editor/IDE where I've yet to hit a quota limit, despite only being on the $20/mo plan - even when using Gemini 3 Pro as the default model.

mythz · Jan 8, 2026 · comment in “How Google got its groove back and edged ahead of OpenAI”

They charge 5% on top of each model’s api costs, but I think it’s worth it to have one centralized place to insert my money and monitor my usage. I like being able to switch out models without having to change my tools, and I like being able to easily head-to-head compare claude/gemini/gpt when I get stuck on a tricky problem.

jdanbrown · Dec 18, 2025 · comment in “Gemini 3 Flash: Frontier intelligence built for speed”

Out of frustration, I built an AI API proxy that automatically routes each request to the cheapest available provider in real-time. The problem: AI API pricing is a mess.

h2o_wine · Nov 26, 2025 · comment in “API that auto-routes to the cheapest AI provider (OpenAI/Anthropic/Gemini)”