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

Measuring Claude 4.7's tokenizer costs

claudecodecamp.com

Post reply on HN
Print view View original

421–430 of 540 posts

Re: Measuring Claude 4.7's tokenizer costs

#421

Post by dang »

jofzar wrote: post #388
dang wrote: post #334

Earlier quoted context omitted.

(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.)

I think it's time to have previous titles show as a edit * icon that can show the previous title. This is not the first time where the more neutral (which imo is better) has caused me to be confused why everyone is saying something different in the comments.

That's probably too much ceremony for HN but petercooper made a really nice HN title edit tracker which is probably still running. Let me see if I can dig it up for you...

Edit: hmm - maybe not: https://news.ycombinator.com/item?id=21617016.

Re: Measuring Claude 4.7's tokenizer costs

#423

Post by mlinsey »

manmal wrote: post #212
mlinsey wrote: post #94

Earlier quoted context omitted.

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 follo…

Common sense isn’t a language pattern. I doubt this will ever work w/ LLMs.

The models that we are paying to generate tokens are already not really just LLMs, as anyone studying language models ten years ago (or someone who describes them as "next token predictors") would understand them. Doing a bunch of reinforcement learning so that a model performs better at ssh'ing into my server and debugging my app is already realllly stretching the definition of "language pattern".

I think when we do get AI that can perform as well as a human at functionally all tasks, they will be multi-paradigm systems; some components will not resemble anything in any commercial system today, but one component will be recognizably LLM-like, and act as an essential communication layer.

Re: Measuring Claude 4.7's tokenizer costs

#424

Post by barrkel »

scuff3d wrote: post #352
hyraki wrote: post #315

Earlier quoted context omitted.

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

It's not gonna stay that way. Token cost is being massively subsidized right now. Prices will have to start increasing at some point.

You can run Qwen3 Coder today - on expensive hardware - but fairly cheaply on a token by token basis. It's no Opus, but you can get things done.

Re: Measuring Claude 4.7's tokenizer costs

#425

Post by abustamam »

doh wrote: post #375
wg0 wrote: post #360

Earlier quoted context omitted.

Who's going to review that output for accuracy? We'll leave performance and security as unnecessary luxuries in this age and time. In my experience, even Claude 4.6's output can't be trusted blindly it'll write flawed code and would write tests that would be testing that flawed code giving false sense of confidence and accomplishment only to be revealed upon closer inspection later. Additionally - it's age old known…

I don't want to defend LLM written code, but this is true regardless if code is written by a person or a machine. There are engineers that will put the time to learn and optimize their code for performance and focus on security and there are others that won't. That has nothing to do with AI writing code. There is a reason why most software is so buggy and all software has identified security vulnerabilities, regardle…

> For all apps I build I have linters, static code analyzers, etc running at the end of each session.

I think this is critically underrated. At least in the typescript world, linters are seen as kind of a joke (oh you used tabs instead of spaces) but it can definitely prevent bugs if you spend some time even vibe coding some basic code smell rules (exhaustive deps in React hooks is one such thing).

Re: Measuring Claude 4.7's tokenizer costs

#426

Post by kamma4434 »

lbreakjai wrote: post #281
fragmede wrote: post #200

Earlier quoted context omitted.

That post doesn't address the human factor of cost, and I don't mean that in a good way. Even if AI costs more than a human, it's tireless, doesn't need holidays, is never going to have to go to HR for sexual harassment issues, won't show up hungover or need an advance to pay for a dying relative's surgery. It can be turned on and off with the flip of a switch. Hire 30 today, fire 25 of them next week. Spin another 5…

The cost to hire a human is highly predictable. The cost of AI isn't. I, as a human, need food and shelter, which puts a ceiling to my bargaining power. I can't withdraw my labour indefinitely. The power dynamics are also vastly against me. I represent a fraction of my employer's labour, but my employer represents 100% of my income. That dynamic is totally inverted with AI. You are a rounding error on their revenue s…

> How do you budget an workforce that could turn 20% more expensive overnight?

Like, say, oil or DRAMs?

Re: Measuring Claude 4.7's tokenizer costs

#427

Post by Ifkaluva »

tabbott wrote: post #268

I find it interesting that folks are so focused on cost for AI models. Human time spent redirecting AI coding agents towards better strategies and reviewing work, remains dramatically more expensive than the token cost for AI coding, for anything other than hobby work (where you're not paying for the human labor). $200/month is an expensive hobby, but it's negligible as a business expense; SalesForce licenses cost fa…

$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.

Re: Measuring Claude 4.7's tokenizer costs

#428

Post by otterley »

outofpaper wrote: post #196
bombcar wrote: post #150

Earlier quoted context omitted.

And worse, he (eventually) has to sell tokens above cost - which may have so much "baggage" (read: debt to pay Nvidia) that it'll be nearly impossible; or a new company will come to play with the latest and greatest hardware and undercut them. Just how if Boeing was able to release a supersonic plane that was also twice as efficient tomorrow; it'd destroy any airline that was deep in debt for its current "now worthle…

That's why open models are going to win in the long run.

I think the key question is “when”? In a highly competitive business environment, companies are going to naturally be attracted to the most capable model if it leads to a competitive advantage and the switching costs are low. This suggests that “open” (giving away inference despite ever-higher training costs) may not win for a very long time, if ever.

Re: Measuring Claude 4.7's tokenizer costs

#430

Post by mistercheese »

KronisLV wrote: post #264
Aurornis wrote: post #157

Earlier quoted context omitted.

> 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 every…

> 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. For a while I used Cerebras Code for 50 USD a month with them running a GLM model and giving you millions of tokens per day . It did a lot of heavy lifting in a software mig…

I have this exact same fear as an IC.

I wonder if Engineering Managers have this same fear, or they’re used to having to distribute complex tasks to senior engineers and gamble with seeming less risky tasks to juniors that may leave ticking time bombs in their code. Just the nature of code written by agents or humans?

Post reply on HN