Measuring Claude 4.7's tokenizer costs • Hacker News Board

Re: Measuring Claude 4.7's tokenizer costs

#171

Post by ezst » Fri, Apr 17, 2026, 6:33 PM UTC

ethin wrote: post #118

louiereederson wrote: post #10

LLMs exist on a logaritmhic performance/cost frontier. 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. To me, it is hard to reject this hypothesis today. The fact that Anthropic is rapidly trying to increase price may betray the fact that their recent lead is a…

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 yea…

> It wouldn't surprise me if in 2-3 years the "max" plan is $800 or $2000 even.

I'd rather be surprised if they are still doing business by then.

Re: Measuring Claude 4.7's tokenizer costs

#172

Post by yorwba » Fri, Apr 17, 2026, 6:33 PM UTC

Majromax wrote: post #13

solenoid0937 wrote: post #7

Earlier quoted context omitted.

People complain about a lot of things. Claude has been fine: https://marginlab.ai/trackers/claude-code-historical-perform...

While that's a nice effort, the inter-run variability is too high to diagnose anything short of catastrophic model degradation. The typical 95% confidence interval runs from 35% to 65% pass rates, a full factor of two performance difference. Moreover, on the companion codex graphs ( https://marginlab.ai/trackers/codex-historical-performance/ ), you can see a few different GPT model releases marked yet none correspond…

Yes, MarginLab only tests 50 tasks a day, which is too few to give a narrower confidence interval. On the other hand, this really calls into question claims of performance degradation that are based on less intensive use than that. Variance is just so high that long streaks of bad luck are to be expected and plausibly the main source of such complaints. Similarly, it's unlikely you can measure a significant performance difference between models like GPT 5.4-xhigh and GPT 5.2 unless you have a task where one of them almost always fails or one almost always succeeds (thus guaranteeing low variance), or you make a lot of calls (i.e. probably through the API and not in interactive mode.)

Re: Measuring Claude 4.7's tokenizer costs

#173

Post by colechristensen » Fri, Apr 17, 2026, 6:34 PM UTC

wslh wrote: post #156

colechristensen wrote: post #152

Earlier quoted context omitted.

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

But the unique thing about AI is that the "world" is depending on it like water, oil, gas, etc. Not just a specific use case.

So it should be free? What's your point exactly?

Re: Measuring Claude 4.7's tokenizer costs

#174

Post by cbg0 » Fri, Apr 17, 2026, 6:34 PM UTC

omega3 wrote: post #123

CharlesW wrote: post #115

Earlier quoted context omitted.

> Commercial inference providers serve Chinese models of comparable quality… "Comparable" is doing some heavy lifting there. Comparable to Anthropic models in 1H'25, maybe.

Benchmarks suggests they are comparable: https://artificialanalysis.ai/?models=claude-opus-4-6-adapti... But let's say for the sake of discussion Opus is much better - still doesn't justify the price disparity especially when considering that other models are provided by commercial inference providers and anthropics is inhouse.

Try doing real work with them, it's night and day difference especially for systems programming. The non-frontier models to a lot of benchmaxxing to look good.

Re: Measuring Claude 4.7's tokenizer costs

#175

Post by JimmaDaRustla » Fri, Apr 17, 2026, 6:35 PM UTC

CharlesW wrote: post #121

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

> 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)?

I'm mind blown people are complaining about token consumption and not communicating what thinking level they're using - if cost is a concern and you're paying any attention, you'd be starting with medium and seeing if you can get better results with less tokens. Every person complaining about token usage seem to have no methodology - probably using max and completely oblivious.

Re: Measuring Claude 4.7's tokenizer costs

#176

Post by JimmaDaRustla » Fri, Apr 17, 2026, 6:36 PM UTC

jmward01 wrote: post #17

Yeah. I just did a day with 4.7 and I won't be going back for a while. It is just too expensive. On top of the tokenization the thinking seems like it is eating a lot more too.

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

Re: Measuring Claude 4.7's tokenizer costs

#177

Post by Bridged7756 » Fri, Apr 17, 2026, 6:36 PM UTC

qq66 wrote: post #42

This is the backdoor way of raising prices... just inflate the token pricing. It's like ice cream companies shrinking the box instead of raising the price

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.

Re: Measuring Claude 4.7's tokenizer costs

#178

Post by AndyNemmity » Fri, Apr 17, 2026, 6:37 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

I'm at 35% :(

Re: Measuring Claude 4.7's tokenizer costs

#179

Post by renticulous » Fri, Apr 17, 2026, 6:38 PM UTC

mattkevan wrote: post #83

devmor wrote: post #58

Earlier quoted context omitted.

Skeptical is a light way to put it. It is essentially a forgone conclusion that once a company IPOs, any veil that they might be working for the global good is entirely lifted. A publicly traded company is legally obligated to go against the global good.

It’s not really, companies like GM used to boast about how well they treated their employees and communities. It was Jack Welch and a legion of like-minded arseholes who decided they should be increasingly richer no matter who or what paid for it.

Middle class productive population produces commons goods and resources which gets exploited by Elites. Tragedy of the Commons applied to wealth generation process itself.

Re: Measuring Claude 4.7's tokenizer costs

#180

Post by AndyNemmity » Fri, Apr 17, 2026, 6:38 PM UTC

JimmaDaRustla wrote: post #175

CharlesW wrote: post #121

Earlier quoted context omitted.

> 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)?

I'm mind blown people are complaining about token consumption and not communicating what thinking level they're using - if cost is a concern and you're paying any attention, you'd be starting with medium and seeing if you can get better results with less tokens. Every person complaining about token usage seem to have no methodology - probably using max and completely oblivious.

It's unsurprising when this is the first day that tokens have been crazy like this.

All of us doing crazy agentic stuff were fine on max before this. Now with Opus 4.7, we're no longer fine, and troubleshooting, and working through options.