Measuring Claude 4.7's tokenizer costs

I meant reference Toby Ord's work here. I think his framing of the performance/cost frontier hasn't gotten enough attention https://www.tobyord.com/writing/hourly-costs-for-ai-agents

> It's not really clear whether Opus 4.5+ represent a level shift on this frontier or just inhabits place on that curve which delivers higher performance, but at rapidly diminishing returns to inference cost.

I think we're reaching the point where more developers need to start right-sizing the model and effort level to the task. It was easy to get comfortable with using the best model at the highest setting for everything for a while, but as the models continue to scale and reasoning token budgets grow, that's no longer a safe default unless you have unlimited budgets.

I welcome the idea of having multiple points on this curve that I can choose from. depending on the task. I'd welcome an option to have an even larger model that I could pull out for complex and important tasks, even if I had to let it run for 60 minutes in the background and made my entire 5-hour token quota disappear in one question.

I know not everyone wants this mental overhead, though. I predict we'll see more attempts at smart routing to different models depending on the task, along with the predictable complaints from everyone when the results are less than predictable.

They're also getting closer to IPO and have a growing user base. They can't justify losing a very large number of billions of other people's money in their IPO prospectus.

So there's a push for them to increase revenue per user, which brings us closer to the real cost of running these models.

FWIW, Artificial Analysis has a "Intelligence vs Cost" plot on their front page that shows models' score vs cost to run the benchmark, which should be more fair in this sense. According to that one, Opus 4.7 (max) is slightly cheaper than 4.6 (though still very expensive).

I mean, the signs have been there that the costs to run and operate these models wasn't as simple as inference costs. And the signs were there (and, arguably, are still there) that it costs way, way more than many people like to claim on the part of Anthropic. So to me this price hike is not at all surprising. It was going to come eventually, and I suspect it's nowhere near over. It wouldn't surprise me if in 2-3 years the "max" plan is $800 or $2000 even.

That sounds very plausible. But it implies they could offer even higher performance models at much higher costs if they chose to; and presumably they would if there were customers willing to pay. Is that the case? Surely there are a decent number of customers who’d be willing to pay more, much more, to get the very best LLMs possible.

Like, Apple computers are already quite pricey -- $1000 or $2000 or so for a decent one. But you can spec up one that’s a bit better (not really that much better) and they’ll charge you $10K, $20K, $30K. Some customers want that and many are willing to pay for it.

Is there an equivalent ultra-high-end LLM you can have if you’re willing to pay? Or does it not exist because it would cost too much to train?

Yeah. Combine this with much of Corpos right now using a “burn as many tokens as you need” policy on AI, the incentive is there for them to raise price and find an equilibrium point or at least reduce the bleed.

Once they implement their models directly in silicon, the cost will come down and the speed will go up. See Taalas.

What a well thought and written comment. I totally agree.

This is a bad take. It's not really wrong in the sense that yes higher performance does cost more.

But it ignores completely the fact that the same intelligence is dropping by an order of magnitude (at least) every 12 months.

GPT o1 launched at $600/M output tokens and GPT4.5 launched at $150/M.

Opus 4.7 is $25/M for more intelligence

heh adaptive thinking is letting the meter run itself. they make more when it runs longer.

For me it was pretty clear from the start that costs will have to increase. It is the classical drug dealer model: first you hook them with cheap supply, maybe even free, then you slowly jack the prize up to a level that can (just) be sustained. Then you decrease the quality of the product by diluting it so you get more bucks for each gram you bought. You could also call it enshittification if you like.

The goal of every company that needs to make ever more money for investors is to earn more money while spending less. There are many ways of doing this without reducing the quality of the product, e.g. using less staff to do more, getting more compute out of same the energy, using cheaper or free energy, optimizing algorithms in ways that do not degrade quality or you grow because you gain more customers and break into new markets etc. And once you made all these optimizations and the market is saturated, then the only optimizations left are the ones where the quality goes down or the risk is increased. Quality in that sense, is what you can get away with without customers jumping ship. So you will also work on locking customers in and make jumping ship look very hard and complicated.

[dead]

> The fact that Anthropic is rapidly trying to increase price may betray the fact that their recent lead is at the cost of dramatically higher operating costs.

Or they are just not willing to burn obscene levels of capital like OpenAI.

That.

We already shipped 3 things this year built using Claude. The biggest one was porting two native apps into one react native app - which was originally estimated to be a 6-7 month project for a 9 FTE team, and ended up being a 2 months project with 2 people. To me, the economic value of a claude subscription used right is in the range of 10-40k eur, depending on the type of work and the developer driving it. If Anthropic jacked the prices 100x today, I'd still buy the licenses for my guys.

Edit: ok, if they charged 20k per month per seat I'd also start benchmarking the alternatives and local models, but for my business case, running a 700M budget, Claude brings disproportionate benefis, not just in time saved in developer costs, but also faster shipping times, reduced friction between various product and business teams, and so on. For the first time we generally say 'yes' to whichever frivolities our product teams come up with, and thats a nice feeling.

$200 a month is not what the BigTechs are talking about.

They are talking about every IC becomes an EM, managing teams of agents.

Did you see the leak of Meta’s token consumption? That’s waaay more than you can get for a small $200 a month plan.

Only small businesses and startups pay $200/month, most medium+ sized companies will have an enterprise plan and pay by token usage to access the security, privacy, and compliance guarantees that their legal and security teams require.

Also, I think the $200/mo plan is subsidized by VC money and is likely hemorrhaging money for Anthropic, so it's not really meaningful to reason around that.

Yes 200 as a business expense is really not that bad. But a hobby is hard to justify.

Yeah completely agree. Even out of my own pocket I'd be willing to spend ~1k a month for the current AI, as compared to not having any AI at all. And I bet I could convince an employer to drop 5k a month on it for me. The consumer surplus atm is insane.

Since Anthropic has capacity problems I'm pretty sure they're limiting the $20/month guys to serve the $200/month business plans. I'm afraid coding will increasingly become pay-to-play. Luckily there is good competition.

I mean, my openclaw instance was billing $200 a day for Opus after they banned using the max subscription. I think a fair amount of that was not useful use of Opus; so routing is the bigger problem. but, that sort of adds up, you know! At $1/hr, I loved Openclaw. At $15/hour, it's less competitive.

[dead]

I believe that's why 90% of the focus in these firms is on coding. There is a natural difficulty ramp-up that doesn't end anytime soon: you could imagine LLMs creating a line of code, a function, a file, a library, a codebase. The problem gets harder and harder and is still economically relevant very high into the difficulty ladder. Unlike basic natural language queries which saturate difficulty early.

This is also why I don't see the models getting commoditized anytime soon - the dimensionality of LLM output that is economically relevant keeps growing linearly for coding (therefore the possibility space of LLM outputs grows exponentially) which keeps the frontier nontrivial and thus not commoditized.

In contrast, there is not much demand for 100 page articles written by LLMs in response to basic conversational questions, therefore the models are basically commoditized at answering conversational questions because they have already saturated the difficulty/usefulness curve.

Whenever we get the locally runnable 4k models things are going to get really awkward for the big 3 labs. Well at least Google will still have their ad revenue I guess.

Depends a lot on the task demands. "Got 95% of the way to designing a successful drug" and "Got 100% of the way" is a huge difference in terms of value, and that small bump in intelligence would justify a few orders of magnitude more in cost.

It probably depends what you're using the models for. If you use them for web search, summarizing web pages, I can imagine there's a plateau and we're probably already hitting it.

For coding though, there is kind of no limit to the complexity of software. The more invariants and potential interactions the model can be aware of, the better presumably. It can handle larger codebases. Probably past the point where humans could work on said codebases unassisted (which brings other potential problems).

I'm seeing a lot of sentiment, and agree with a lot of it, that opus 4.6 un-nerfed is there already and for many if not most software use cases there's more value to be had in tooling, speed, and cost than raw model intelligence.

At this point, I still don't see a reason to use Opus. I'm happy with Sonnet's performance for a third of the price. Tried several times with not a big gain.

yeah thats is my biggest issue - im okay with paying 20-30% more but what is the ROI? i dont see an equivalent improvement in performance. Anthropic hasnt published any data around what these improvements are - just some vague “better instruction following"

At normal viewing distance(let's say cinema FOV) most people won't see a difference between 4k and 8k never mind 16k.

And it's not that they "don't notice" it's that they physically can't distinguish finer angular separation.

It's more like, if it gets it right 99% of the time, that sounds incredible.

Until it's making 100k decisions a day and many are dependent on previous results.

I agree, but also the model intelligence is quite spikey. There are areas of intelligence that I don't care at all about, except as proxies for general improvement (this includes knowledge based benchmarks like Humanity's Last Exam, as well as proving math theorems etc). There are other areas of intelligence where I would gladly pay more, even 10X more, if it meant meaningful improvements: tool use, instruction following, judgement/"common sense", learning from experience, taste, etc. Some of these are seeing some progress, others seem inherent to the current LLM+chain of thought reasoning paradigm.

Longer version of the comment https://www.linkedin.com/pulse/imperceptible-upgrade-petko-d...

This will probably happen but I wouldn't plan on it happening soon

yeah there needs to be a corresponding increment improvement in model archetecture.

>IMHO there is a point where incremental model quality will hit diminishing returns.

It's not necessary a single discrete point I think. In my experience, it's tied to the quality/power of your harness and tooling. More powerful tooling has made revealed differences between models that were previously not easy to notice. This matches your display analogy, because I'm essentially saying that the point at which display resolution improvements are imperceptible matters on how far you sit.

Does anyone here use 8k display for work? Does it make sense over 4k?

I was always wondering where that breaking point for cost/peformance is for displays. I use 4K 27” and it’s noticeably much better for text than 1440p@27 but no idea if the next/ and final stop is 6k or 8k?

> IMHO there is a point where incremental model quality will hit diminishing returns.

You mean a couple of years ago?

Yep, and I just made a recommendation that was essentially "never enable Opus 4.7" to my org as a direct result. We have Opus 4.6 (3x) and Opus 4.5 (3x) enabled currently. They are worth it for planning.

At 7.5x for 4.7, heck no. It isn't even clear it is an upgrade over Opus 4.6.

oh wow, that is very telling!

This article is only about the tokenizer. It doesn't measure the number of tokens needed for each request, which could be higher or lower overall.

Opus 4.6 also just got dumber. It's dismissive, hand-wavy, jumps to conclusions way too quickly, skips reasoning... Bubble is going to burst, either some big breakthrough comes up or we are going to see a very fast enshittificafion.

I ran an internal (oil and gas focused) benchmark yesterday and found Opus 4.7 was 50% cheaper than Opus 4.6, driven by significantly fewer output tokens for reasoning. It also scored 80% (vs. 60%).

yep, ran a controlled experiment on 28 tasks comparing old opus 4.6 vs new opus 4.6 vs 4.7, and found that 4.7 is comparable in cost to old 4.6, and ~20% more expensive then new 4.6 (because new 4.6 is thinking less)

https://www.stet.sh/blog/opus-4-7-zod

(Submitted title was "Claude Opus 4.7 costs 20–30% more per session". We've since changed it to a (more neutral) version of what the article's title says.)

im running some experiments on this but based on what i have seen on my own personal data - I dont think this is true

"given that Opus 4.7 on Low thinking is strictly better than Opus 4.6 on Medium, etc., etc.”

Opus 4.7 in general is more expensive for similar usage. Now we can argue that is provides better performance all else being equal but I haven’t been able to see that

Following up on "strictly better" via plot in release announcement:

https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-...

Very unlikely that the article is wrong. the 4.7 intelligence bump is not that big, plus most of the token spend is in inputs/tool calls etc, much of which won't change even with this bump.

[dead]

Yes! I'd be totally happy with today's sonnet 4.6 if I could run it locally.

If you can forgive the obviously-AI-generated writing, [CPUs Aren't Dead](https://seqpu.com/CPUsArentDead) makes an interesting point on AI progress: Google's latest, smallest Gemma model (Gemma 4 E2B), which can run on a cell phone, outperforms GPT-3.5-turbo. Granted, this factoid is based on `MT-Bench` performance, a benchmark from 2023 which I assume to be both fully saturated and leaked into the training data for modern LLMs. However, cross-referencing [Artificial Analysis' Intelligence Index](https://artificialanalysis.ai/models?models=gemma-4-e2b-non-...) suggests that indeed the latest 2B open-weights models are capable of matching or beating 175B models from 3-4 years ago. Perhaps more impressive, [Gemma 4 E4B matches or beats GPT-4o](https://artificialanalysis.ai/models?models=gemma-4-e4b%2Cge...) on many benchmarks.

If this trend continues, perhaps we'll have the capabilities of today's best models available to reasonably run on our laptops!

The cost of intelligence is non-linear, with slightly dumber models costing much less. For a growing surface of problems you do not need frontier intelligence. You should use frontier intelligence for situations where you would otherwise require human intervention throughout the workflow, which is much more expensive than any model.

Many people were hoping that Sonnet 4.6 was "Opus 4.5 quality but with Sonnet speed/cost" but unfortunately that didn't pan out.

Efficiency doesn't make as much money. It's in big LLM's best interest to keep inference computationally expensive.

I personally think the whole "the newest model is crazy! You've gotta use X (insert most expensive model)" Is just FOMO and marketing-prone people just parroting whatever they've seen in the news or online.

Does everyone need a graphing calculator? Does everyone need a scientific calculator? Does everyone need a normal calculator? Does everyone need GeoGebra or Desmos ?

So you're happy with an untrustworthy lazy moron prone to stupid mistakes and guesswork?

Surely you can see the first lab that solves this gains a massive advantage?

I agree, and yet here i am using it... However, I think the industry IS going multiple directions all at once with smaller models, bigger models etc. I need to try out Google's latest models but alas what can one person do in the face of so many new models...

[dead]

It's not just in Kolkata, worldwide packs of biscuits etc remained the same size but less inside.

I didn't buy Springles chips in years, even the box now is nothing like it was. Thinner. Shorter. I imagine how far from the top the slices stack up.

See also: Shrinkflation (https://en.wikipedia.org/wiki/Shrinkflation)

I don't understand how people measure how much more or less work they need to do. It's not that gpt-4o was incapable of exuding enormous amounts of code quickly, it's that the tokens were relativ garbage.

How do you have an opinion on 4.6/4.7 here? It's less clear but I could totally see that 4.7 or beyond leads to project completion 20% faster, by removing dead ends, foot guns, less backtracking, etc.

How to tell / measure effectively? No clue.

Yeah that was an interesting discovery in a development meeting. Many people were chasing after the next best model and everything, though for me, Sonnet 4.6 solves many topics in 1-2 rounds. I mainly need some focus on context, instructions and keeping tasks well-bounded. Keeping the task narrow also simplifies review and staying in control, since I usually get smaller diffs back I can understand quickly and manage or modify later.

I'll look at the new models, but increasing the token consumptions by a factor of 7 on copilot, and then running into all of these budget management topics people talk about? That seems to introduce even more flow-breakers into my workflow, and I don't think it'll be 7 times better. Maybe in some planning and architectural topics where I used Opus 4.6 before.

haven't people been complaining lately about 4.6 getting worse?

How long will they host 4.6? Maybe longer for enterprise, but if you have a consumer subscription, you won't have a choice for long, if at all anymore.

Inserting an xhigh tier and pushing max way out has very “these go to 11” vibes.

I'm seeing the opposite. With Opus 4.7 and xhigh, I'm seeing less session usage , it's moving faster, and my weekly usage is not moving that much on a Team Pro account.

Four day workweek!

yeah similar for me - it uses a bunch more tokens and I haven’t been able to tell the ROI in terms of better instruction following

it seems to hallucinate a bit more (anecdotal)

My personal Claude sub (Pro), I can burn through my limit in a couple of hours when using Opus. It's borderline unusable unless you're willing to pay for extended usage or artificially slow yourself down.

> I'm already at 27% of my weekly limit in ONE DAY.

Ouch, that's very different than experience. What effort level? Are you careful to avoid pushing session context use beyond 350k or so (assuming 1m context)?

Iam at 22%, just two task. A bug fixing and a Scalar integration.

I'm at 35% :(

They won't. These are not "issues", it's them trying to push the models to burn less compute. It will only get worse.

I am having a shit experience lately. Opus 4.7, max effort.

> You're right, that was a shit explanation. Let me go look at what V1 MTBL actually is before I try again.

> Got it — I read the V1 code this time instead of guessing. Turns out my first take was wrong in an important way. Let me redo this in English.

:facepalm:

> he’s making .. mistakes

Claude and other LLMs do not have a gender; they are not a “he”. Your LLM is a pile of weights, prompts, and a harness; anthropomorphising like this is getting in the way.

You’re experiencing what happens when you sample repeatedly from a distribution. Given enough samples the probability of an eventual bad session is 100%.

Just clear the context, roll back, and go again. This is part of the job.

You're assuming errors cannot be retried/recovered. They can.

What do you mean by this? What are you frustrated by?

You're offended by their political beliefs, so you don't like the way the model works?

using dumber models to own the libs

I work at a company that has gone all in on Anthropic, and we're just shoveling money at them. I suspect there are a more enterprises than we realize that are doing this.

When I read these comments on Hacker News, I see a lot of people miffed about their personal subscription limits. I think this is a viewpoint that is very consumer focused, and probably within Anthropic they're seeing buckets of money being dumped on them from enterprises. They probably don't really care as much about the individual subscription user, especially power users.

1. HN is so unrepresentative of real life. You have people on their $20/$200 subscriptions complaining about usage limits. They are a tiny fraction of Anthropic's revenue. API billing and enterprise is where the money is.

2. Anthropic and OpenAI's financials are totally different. The former has nearly the same RRR and a fraction of the cash burn. There is a reason Anthropic is hot on secondary and OAI isn't

OpenAI is dealing with exactly the same energetic and financial constraints as Anthropic. That will become apparent soon.

No, you're forgetting the never ending world shattering models being released every couple of months. Each one with 2X token costs of course, for a vague performance gain and that will deprecate the previous ones.

yeah i am still not clear why there are 5 effort modes now on top of more expensive tokenization

What was your level methodology and results? Can't just post "too expensive" and not explain how you went about it.

yeah opus 4.7 feels a lot more verbose - i think they changed the system prompt and removed instructions to be terse in its responses

I had a case yesterday where Claude wrote me a series of if/elses in python. I asked it if it could use some newer constructs instead, and it told me that I was on a new enough python version that I could use match/case. Great!

And then it proceeded to rewrite the block with a dict lookup plus if-elses, instead of using match/case. I had to nag it to actually rewrite the code the way it said it would!

yeah it seems like sonnet 4.6 burns thru tokens crazy fast. I did one prompt, sonnet misunderstood it as 'generate an image of this' and used all of my free tokens.

Mythos is basically this

The company I work for provides all engineering employees with a Claude subscription. My job isn't writing (much) code, and we have Copilot with MS Office, plus multiple internal AI tools on top of that. So I'm free to do low-stakes experiments on Claude without having to worry about hitting my monthly usage limit.

I am finding that for complex tasks, Claude's quality of output varies _tremendously_ with repeated runs of the same model and prompt. For example, last week I wrote up (with my own brain and keyboard) a somewhat detailed plain english spec of a work-related productivity app that I've always wanted but never had the time to write. It was roughly the length of an average college essay. The first thing I asked Claude to do was not write any code, but come up with a more formal design and implementation plan based on the requirements that I gave. The idea was to then hand _that_ to Claude and say, okay, now build it.

I used Opus 4.6 with High reasoning for all of this and did not change any model settings between runs.

The first run was overall _amazing_. It was detailed, well-written, contained everything that I asked for. The only drawback was that I was ambiguous on a couple of points which meant that the model went off and designed something in a way that I wasn't expecting and didn't intend. So I cleared that up in my prompt, and instead of keeping the context and building on what was already there, I started a new chat and had it start again from scratch.

What it wrote the second time was _far_ less impressive. The writing was terse, there was a lot less detail, the pretty dependency charts and various tables it made the first time were all gone. Lots of stuff was underspecified or outright missing.

New chat, start again. Similar results as the second run, maybe a bit worse. It also started _writing code_ which was something I told it NOT to do. At this point I'm starting to panic a little because I'm sure I didn't add, "oh, and make it crappy" to the prompt and I was a little angry about not saving the first iteration since it was fairly close to what I had wanted anyway.

I decided to try one last time and it finally gave me back something within about 95% of the first run in terms of quality, but with all the problems fixed. So, I was (finally) happy with that, and it used that to generate the application surprisingly well, with only a few issues that should not be too hard to fix after the fact.

So I guess 4th time was a charm, and the fare was about $7 in tokens to get there.

That’s the joy of purchasing an intangible and non-deterministic product. The profit margin is completely within the vendor’s control and quality is hard for users to measure.

I think the ideal way for these LLMs to work will be using AST-level changes instead of "let me edit this file".

grit.io was working on this years ago, not sure if they are still alive/around, but I liked their approach (just had a very buggy transformer/language).

>and most of the tokens are just echoing back the old code with minimal changes

I thought coding harnesses provided tools to apply diffs so the LLM didn't have to echo back the entire file?

I want to give give you realistic expectations: Unless you spend well over $10K on hardware, you will be disappointed, and will spend a lot of time getting there. For sophisticated coding tasks, at least. (For simple agentic work, you can get workable results with a 3090 or two, or even a couple 3060 12GBs for half the price. But they're pretty dumb, and it's a tease. Hobby territory, lots of dicking around.)

Do yourself a favor: Set up OpenCode and OpenRouter, and try all the models you want to try there.

Other than the top performers (e.g. GLM 5.1, Kimi K2.5, where required hardware is basically unaffordable for a single person), the open models are more trouble than they're worth IMO, at least for now (in terms of actually Getting Shit Done).

gemma4 and qwen3.6 are pretty capable but will be slower and wrong more often than the larger models. But you can connect gemma4 to opencode via ollama and it.. works! it really can write and analyze code. It's just slow. You need serious hardware to run these fast, and even then, they're too small to beat the "frontier" models right now. But it's early days

Not sure why all the other commentors are failing to mention you can spend considerably less money on an apple silicon machine to run decent local models.

Fun fact: AWS offers apple silicon EC2 instances you can spin up to test.

My anecdotal experience with a recent project (Python library implemented and released to pypi).

I took the plan that I used from Codex and handed it to opencode with Qwen 3.5 running locally.

It created a library very similar to Codex but took 2x longer.

I haven't tried Qwen 3.6 but I hear it's another improvement. I'm confident with my AI skills that if/when cheap/subsidized models go away, I'll be fine running locally.

You should be aware that any model you can run on less than $10k worth of hardware isn't going to be anywhere close to the best cloud models on any remotely complex task.

Many providers out there host open weights models for cheap, try them out and see what you think before actually investing in hardware to run your own.

The latest Qwen3.6 model is very impressive for its size. Get an RTX 3090 and go to https://www.reddit.com/r/LocalLLaMA/ to see the latest news on how to run models locally. Totally fine for coding.

i think the new qwen models are supposed to be good based on some the articles that i read

Unless you use H100 or 4x 5090 you won't get a decent output.

The best bang for the buck now is subcribing to token plans from Z.ai (GLM 5.1), MiniMax (MiniMax M2.7) or ALibaba Cloud (Qwen 3.6 Plus)

Running quantized models won't give you results comparable to Opus or GPT.

I would encourage you to post a link here, and also to submit to HN if you haven't already. :)

On the contrary, I threw a multi-threading optimization task on it, that 4.5 and 4.6 have been pretty useless at handling. 4.7 bested my hand-tuned solution by almost 2x on first attempt.

This was what I thought was my best moat as a senior dev. No other model has been able to come close to the throughput I could achieve on my own before. Might be a fluke of course, and they've picked up a few patterns in training that applies to this particular problem and doesn't generalize. We'll see.

> it refused to even touch the code.

???

please i beg post the prompt and the refusal

I literally can not imagine a model refusing to do something

No, see, we have to leave writing code to fully identity-verified individuals working on behalf of only the largest institutions now because what if they decided to write malware?

effort level is separate from tokenization. Tokenization impacts you the same regardless.

I find 5 thinking levels to be super confusing - I dont really get why they went from 3 -> 5

yeah thats the part that is unclear to me as well - if our usage capacity is now going to run out faster.

Boris said on Twitter that they've increased rate limits for everyone.

How are you able to track this as you use it? A bit stumped atm

How does this solve the issue? 4.6 will be disabled after one or more release like any other legacy model.

> Commercial inference providers serve Chinese models of comparable quality…

"Comparable" is doing some heavy lifting there. Comparable to Anthropic models in 1H'25, maybe.

> So intelligence has turned into a utility.

"Utility" is close, but "energy source" may be closer. When it becomes the thing powering the pace of work itself, raising prices is less about charging for access and more about taxing dependency.

Like every startup ever, they were selling it to you at a loss to compete for market share and are slowly increasing pricing. Duh.

Given that they haven’t even gone public yet, doesn’t that seem like putting the cart before the horse a bit? And if they’re already enshittifying it won’t be long until the other placers start doing so as well. Have we passed peak LLM intelligence and are we now watching it degrade as they fail to roll these new advanced models out to their increasing user base? Are the finances not adding up?

Lots of questions.

anthropic’s pricing is all based on token usage

https://platform.claude.com/docs/en/about-claude/pricing

So if you are generating more tokens, you are eating up your usage faster

> The fundamental problem with these frontier model companies is that they're incentivized to create models that burn through more tokens

That's one market segment - the high priced one, but not necessarily the most profitable one. Ferrari's 2025 income was $2B while Toyota's was $30B.

Maybe a more apt comparison is Sun Microsystems vs the PC Clone market. Sun could get away with high prices until the PC Clones became so fast (coupled with the rise of Linux) that they ate Sun's market and Sun went out of business.

There may be a market for niche expensive LLMs specialized for certain markets, but I'll be amazed if the mass coding market doesn't become a commodity one with the winners being the low cost providers, either in terms of API/subscriptions costs, or licensing models for companies to run on their own (on-prem or cloud) servers.

> but the corollary to that is "this is the most aligned the incentives between model providers and customers will ever be" because we're all just burning VC money for now.

Please say this louder for everyone to hear. We are still at the stage where it is best for Anthropic's product to be as consumer aligned (and cost-friendly) as possible. Anthropic is loosing a lot of money. Both of those things will not be true in the near future.

Their bigger incentive is to deliver the best product in the cheapest way, because there is tight competition with at least 2 other companies. I know we all love to hate on capitalism but it's actually functioning fine in this situation, and the token inflation is their attempt to provide a better product, not a worse one.

I'm mostly surprised that people found the output quality of Opus 4.6 good enough... 4.7 so far is a pretty sizable improvement for the stuff I care about. I don't really care how cheap 4.6 was per task when 90% of the tasks weren't actually being done correctly. Or maybe it's that people like the LLM agreeing with them blindly while sneakily doing something else under the hood? Did people enjoy Claude routinely disregarding their instructions? Not really sure I understand, I truly found 4.6 immensely frustrating (from the getgo, not just the "pre-nerf" version, whatever that means). 4.7 is a buggy mess, it's slow, and it costs a lot per token. It's also a huge breath of fresh air because it actually seems to make a good faith effort at doing the thing you asked it to do, and doesn't waste your time with irrelevant nonsense just to make it look busy or because it thinks you want that nonsense (I mean, it still does all of these things to some extent, but so far it seems like it does them much less than 4.6 did).

Disclaimer: I'm always running on max and don't really have token limits so I am in a position not to care about cost per token. But I am not surprised by the improved benchmark results at all, 4.6 was really not nearly as strong of a model as people seem to remember it being.

are you okay with paying more for your services without any perceived improvement in the service itself?

> The compute is expensive, what is with this outrage?

Gamblers (vibe-coders) at Anthropic's casino realising that their new slot machine upgrade (Claude Opus) is now taking 20%-30% more credits for every push of the spin button.

Problem is, it advertises how good it is (unverified benchmarks) and has a better random number generator but it still can be rigged (made dumber) by the vendor (Anthropic).

The house (Anthropic) always wins.

> People just want free tools forever?

Using local models are the answer to this if you want to use AI models free forever.

Can we have one thread about Claude without people trying to shovel Caveman?

Much of the token usage is in reasoning, exploring, and code generation rather than outputs to the user.

Does making Claude sound like a caveman actually move the needle on costs? I am not sure anymore whether people are serious about this.

To me, caveman sounds bad and is not as easy to understand compared to normal English.

Caveman doesn't and cannot change the tokenizer, so the relative token count differences by input category will remain unchanged.

isn’t caveman a joke? why would you use it for real work?