Measuring Claude 4.7's tokenizer costs
claudecodecamp.com
Measuring Claude 4.7's tokenizer costs
1–10 of 540 posts
Re: Measuring Claude 4.7's tokenizer costs
#2On 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 too soon for me to tell if 4.7 is a meaningful lift. If it is, then I can evaluate if the increased cost is justified.
Re: Measuring Claude 4.7's tokenizer costs
#3On 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…
haven't people been complaining lately about 4.6 getting worse?
Re: Measuring Claude 4.7's tokenizer costs
#4On 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…
haven't people been complaining lately about 4.6 getting worse?
No we increased our plans
Re: Measuring Claude 4.7's tokenizer costs
#5I'm still using Sonnet 4.6 with no issues.
Re: Measuring Claude 4.7's tokenizer costs
#6On 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.
Re: Measuring Claude 4.7's tokenizer costs
#7On 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…
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...
Re: Measuring Claude 4.7's tokenizer costs
#8Interesting because I already felt like current models spit out too much garbage verbose code that a human would write in a far more terse, beautiful and grokable way
Re: Measuring Claude 4.7's tokenizer costs
#9On 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.
Opus 4.5 is still available
Re: Measuring Claude 4.7's tokenizer costs
#10LLMs 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 at the cost of dramatically higher operating costs. Their gross margins in this past quarter will be an important data point on this.
I think the tendency for graphs of model assessment to display the log of cost/tokens on the x axis (i.e. Artificial Analysis' site) has obscured this dynamic.