Measuring Claude 4.7's tokenizer costs • Hacker News Board

Re: Measuring Claude 4.7's tokenizer costs

#311

Post by radlad » Fri, Apr 17, 2026, 9:17 PM UTC

tremon wrote: post #275

whalesalad wrote: post #271

Earlier quoted context omitted.

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:

> I read the V1 code this time instead of guessing Does the LLM even keep a (self-accessible) record of previous internal actions to make this assertion believable, or is this yet another confabulation?

Yes, the LLM is able to see the entire prior chat history including tool use. This type of interaction occurs when the LLM fails to read the file, but acts as though it had.

Re: Measuring Claude 4.7's tokenizer costs

#312

Post by b65e8bee43c2ed0 » Fri, Apr 17, 2026, 9:20 PM UTC

criemen wrote: post #293

aulin wrote: post #291

Earlier quoted context omitted.

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

> it's them trying to push the models to burn less compute I'm curious, how does using more tokens save compute?

productivity (tokens per second per hardware unit) increases at the cost of output quality, but the price remains the same.

both Anthropic and OpenAI quantize their models a few weeks after release. they'd never admit it out loud, but it's more or less common knowledge now. no one has enough compute.

Re: Measuring Claude 4.7's tokenizer costs

#313

Post by zozbot234 » Fri, Apr 17, 2026, 9:20 PM UTC

solenoid0937 wrote: post #238

zozbot234 wrote: post #197

Earlier quoted context omitted.

Even 4k turns out to be overkill if you're looking at the whole screen and a pixel-perfect display. By human visual acuity, 1440p ought to be enough, and even that's taking a safety margin over 1080p to account for the crispness of typical text.

1440p is enough if you haven't experienced anything else. Even the jump from 4k to 5-6k is quite noticeable on a 27" monitor. I switched to the Studio Display XDR and it is noticeably better than my 4k displays and my 1440p displays feel positively ancient and near unusable for text.

That's great for contrast, color fidelity and compatibility with the Apple Mac. But the resolution is quite overkill.

Re: Measuring Claude 4.7's tokenizer costs

#314

Post by slopinthebag » Fri, Apr 17, 2026, 9:20 PM UTC

Someone1234 wrote: post #280

chewz wrote: post #244

Earlier quoted context omitted.

7.5 is promotional rate, it will go up to 25. And in May you will be switched to per token billing. Opus 4.5 and 4.6 will be removed very soon. So what is your contingency plan?

Can you link to a source for anything you're claiming?

https://github.blog/changelog/2026-04-16-claude-opus-4-7-is-...

> Over the coming weeks, Opus 4.7 will replace Opus 4.5 and Opus 4.6 in the model picker for Copilot Pro+.

> This model is launching with a 7.5× premium request multiplier as part of promotional pricing until April 30th

TBF, it's a rumour that they are switching to per-token price in May, but it's from an insider (apparently), and seeing how good of a deal the current per-request pricing is, everyone expects them to bump prices sometime soon or switch to per-token pricing.

Re: Measuring Claude 4.7's tokenizer costs

#315

Post by hyraki » Fri, Apr 17, 2026, 9:21 PM UTC

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…

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

Re: Measuring Claude 4.7's tokenizer costs

#316

Post by cebert » Fri, Apr 17, 2026, 9:23 PM UTC

b65e8bee43c2ed0 wrote: post #312

criemen wrote: post #293

Earlier quoted context omitted.

> it's them trying to push the models to burn less compute I'm curious, how does using more tokens save compute?

productivity (tokens per second per hardware unit) increases at the cost of output quality, but the price remains the same. both Anthropic and OpenAI quantize their models a few weeks after release. they'd never admit it out loud, but it's more or less common knowledge now. no one has enough compute.

Do you have a source for that claim?

Re: Measuring Claude 4.7's tokenizer costs

#317

Post by ed_elliott_asc » Fri, Apr 17, 2026, 9:23 PM UTC

whalesalad wrote: post #271

ericol wrote: post #266

I did some work yesterday with Opus and found it amazing. Today we are almost on non-speaking terms. I'm asking it to do some simple stuff and he's making incredible stupid mistakes: This is the third time that I have to ask you to remove the issue that was there for more than 20 hours. What is going on here? and at the same time the compacting is firing like crazy. (What adds ~4 minute delays every 1 - 15 minutes) |…

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:

If it isn’t working for you why don’t you choose an older model? 4.6

Re: Measuring Claude 4.7's tokenizer costs

#318

Post by richstokes » Fri, Apr 17, 2026, 9:24 PM UTC

atonse wrote: post #14

Just yesterday I was happy to have gotten my weekly limit reset [1]. And although I've been doing a lot of mockup work (so a lot of HTML getting written), I think the 1M token stuff is absolutely eating up tokens like CRAZY. I'm already at 27% of my weekly limit in ONE DAY. https://news.ycombinator.com/item?id=47799256

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.

Re: Measuring Claude 4.7's tokenizer costs

#319

Post by sthimons » Fri, Apr 17, 2026, 9:26 PM UTC

b65e8bee43c2ed0 wrote: post #312

criemen wrote: post #293

Earlier quoted context omitted.

> it's them trying to push the models to burn less compute I'm curious, how does using more tokens save compute?

productivity (tokens per second per hardware unit) increases at the cost of output quality, but the price remains the same. both Anthropic and OpenAI quantize their models a few weeks after release. they'd never admit it out loud, but it's more or less common knowledge now. no one has enough compute.

Pretty bold claim - you have a source for that?

Re: Measuring Claude 4.7's tokenizer costs

#320

Post by radlad » Fri, Apr 17, 2026, 9:28 PM UTC

dustingetz wrote: post #219

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…

Human dev labor cost is still the high pole in the tent, even multiplying today's subsidized subscription cost by 10x. If the capability improvement trajectory continues, developers should prepare for a new economy where more productivity is achieved by fewer devs by shifting substantial labor budget to AI.

I'm getting a lot more done by handing off the code writing parts of my tasks to many agents running simultaneously. But my attention still has its limits.