Claude's tokenizers have actually been getting less efficient over the years (I think we're at the third iteration at the least since Sonnet 3.5). And if you prompt the LLM in a language other than English, or if your users prompt it or generate content in other languages, the costs go higher even more. And I mean hundreds of percent more for languages with complex scripts like Tamil or Japanese. If you're interested in the research we did comparing tokenizers of several SOTA models in multiple languages, just hit me up.
Measuring Claude 4.7's tokenizer costs
51–60 of 540 posts
Re: Measuring Claude 4.7's tokenizer costs
#52LLMs 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…
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.
I agree, and I'm also quite skeptical that Anthropic will be able to remain true to its initial, noble mission statement of acting for the global good once they IPO.
At that point you are beholden to your shareholders and no longer can eschew profit in favor of ethics.
Unfortunately, I think this is the beginning of the end of Anthropic and Modei being a company and CEO you could actually get behind and believe that they were trying to do "the right thing".
It will become an increasingly more cutthroat competition between Anthropic and OpenAI (and perhaps Google eventually if they can close the gap between their frontier models and Claude/GPT) to win market share and revenue.
Perhaps Amodei will eventually leave Anthropic too and start yet another AI startup because of Anthropic's seemingly inevitable prioritization of profit over safety.
Re: Measuring Claude 4.7's tokenizer costs
#53Yeah. 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.
yeah i am still not clear why there are 5 effort modes now on top of more expensive tokenization
Once you've seen a few results of an LLM given too much sway over product decisions, 5 effort modes expressed as various english adjectives is pretty much par for the course
Re: Measuring Claude 4.7's tokenizer costs
#54Don't forget that the model doesn't have an incentive to give right solution the first time. At least with Opus 4.6 after it got nerfed, it would go round in circles until you tell it to stop defrauding you and get to correct solution. That not always worked though. I found starting session again and again until less nerfed model was put on the request. Still all points to artificially make customer pay more.
Re: Measuring Claude 4.7's tokenizer costs
#55The fundamental problem with these frontier model companies is that they're incentivized to create models that burn through more tokens, full stop. It's a tale as old as capitalism: you wake up every day and choose to deliver more value to your customers or your shareholders, you cannot do both simultaneously forever. People love to throw around "this is the dumbest AI will ever be", but the corollary to that is "thi…
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.
Re: Measuring Claude 4.7's tokenizer costs
#56The title is a misdirection. The token counts may be higher, but the cost-per-task may not be for a given intelligence level. Need to wait to see Artificial Analysis' Intelligence Index run for this, or some other independent per-task cost analysis.
The final calculation assumes that Opus 4.7 uses the exact same trajectory + reasoning output as Opus 4.6. I have not verified, but I assume it not to be the case, given that Opus 4.7 on Low thinking is strictly better than Opus 4.6 on Medium, etc., etc.
Re: Measuring Claude 4.7's tokenizer costs
#57Re: Measuring Claude 4.7's tokenizer costs
#58Earlier quoted context omitted.
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.
I agree, and I'm also quite skeptical that Anthropic will be able to remain true to its initial, noble mission statement of acting for the global good once they IPO. At that point you are beholden to your shareholders and no longer can eschew profit in favor of ethics. Unfortunately, I think this is the beginning of the end of Anthropic and Modei being a company and CEO you could actually get behind and believe that…
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.
Re: Measuring Claude 4.7's tokenizer costs
#59On actual code, I see what you see a 30% increase in tokens which is in-line with what they claim as well. I personally don't tend to feed technical documentation or random pros into llms. Given that Opus 4.6 and even Sonnet 4.6 are still valid options, for me the question is not "Does 4.7 cost more than claimed?" but "What capabilities does 4.7 give me that 4.6 did not?" Yesterday 4.6 was a great option and it is to…
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.
I'm still using 4.5 because it gets the niche work I'm using it for where 4.6 would just fight me.
Re: Measuring Claude 4.7's tokenizer costs
#604.7 one-shot rate is at least 20-30% higher for me
How are you able to track this as you use it? A bit stumped atm