I'm still using Sonnet 4.6 with no issues.
How does this solve the issue? 4.6 will be disabled after one or more release like any other legacy model.
Measuring Claude 4.7's tokenizer costs
11–20 of 540 posts
Re: Measuring Claude 4.7's tokenizer costs
#12And what about with Caveman[1]?
Re: Measuring Claude 4.7's tokenizer costs
#13Earlier quoted context omitted.
haven't people been complaining lately about 4.6 getting worse?
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 to a visual break in the series. Either GPT 5.4-xhigh is no more powerful than GPT 5.2, or the benchmarking apparatus is not sensitive enough to detect such changes.
Re: Measuring Claude 4.7's tokenizer costs
#14Just 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.
Re: Measuring Claude 4.7's tokenizer costs
#15Earlier quoted context omitted.
haven't people been complaining lately about 4.6 getting worse?
People complain about a lot of things. Claude has been fine: https://marginlab.ai/trackers/claude-code-historical-perform...
That performance monitor is super easy to game if you cache responses to all the SWE bench questions.
Re: Measuring Claude 4.7's tokenizer costs
#16And what about with Caveman[1]? 1. https://github.com/juliusbrussee/caveman
Caveman doesn't and cannot change the tokenizer, so the relative token count differences by input category will remain unchanged.
Re: Measuring Claude 4.7's tokenizer costs
#17Yeah. 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.
Re: Measuring Claude 4.7's tokenizer costs
#18On 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 was trying to figure out earlier today how to get 4.6 to run in Claude Code, as part of the output it included "- Still fully supported — not scheduled for retirement until Feb 2027." Full caveat of, I don't know where it came up with this information, but as others have said, 4.5 is still available today and it is now 5, almost 6 months old.
Re: Measuring Claude 4.7's tokenizer costs
#19Pretty funny that this article was clearly written by Claude.
Re: Measuring Claude 4.7's tokenizer costs
#204.7 one-shot rate is at least 20-30% higher for me