Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The real prices of frontier models

playcode.io

Post reply on HN
Print view View original

41–50 of 91 posts

Re: The real prices of frontier models

#41

Post by add-sub-mul-div »

robbie-c wrote: post #39

Is it on topic to complain about the various claude-isms in this article? I don't know any actual humans that write titles like "Two floors the rate card hides". I find my brain disengages once I suspect something of being written by an LLM. If the author didn't put much effort into writing it, should I expect them to have put much effort into fact-checking it? Edit: this specific title has been deleted from the arti…

Yes it's worth commenting about. Not everyone, but many want to know that signal just like you do. It not only provides a useful heuristic about the article, but about whatever product or service they're advertising/selling.

Re: The real prices of frontier models

#43

Post by petercooper »

jnwatson wrote: post #11

The real elephant in the room is pricing for KV cache writes and reads. That makes all the difference for tasks with large context.

Cache writes/reads are the majority of the picture for agentic development. When you see these people saying a coding run "used 200 million tokens" or whatever, most of that is cache reads, so it should be the headline price IMO (and is one reason why DeepSeek API is so striking with its minuscule cache pricing).

Re: The real prices of frontier models

#44

Post by j45 »

dinkleberg wrote: post #33
j45 wrote: post #17

An individual token, and the level of energy it represents (electricity, or relative effectiveness per model) increasingly seems the space of obsfucation. This space can be increasingly avoided by becoming, and remaining, efficient and effective with prompts.

That is one of the interesting things about Neuralwatt cloud. Their pricing is based on energy rather than tokens (actually they have a token-based alternative, but claim the energy pricing results in 95% cheaper results). I've tried out their subscription offer and it does seem like you get a lot more usage even on the cheap plan. However since the energy metering is pretty much unique to them (at least that I've se…

I think I saw something like that, and it made me realize the watt isn't the only measurement. The watt can be spent effectively, or ineffectively, thus obsfucating mileage per watt.

How we drive AI will cause mileage variances, but over time the improved practices can measurably change.

Re: The real prices of frontier models

#45

Post by dgellow »

sscaryterry wrote: post #42
dgellow wrote: post #36

Earlier quoted context omitted.

Could you elaborate?

If I need to put 2 and 2 together for you: https://en.wikipedia.org/wiki/Shrinkflation

Would you mind sharing your actual thoughts instead of this vague posting? What does AMD have to do with Anthropic?

Re: The real prices of frontier models

#46

Post by mft_ »

robbie-c wrote: post #39

Is it on topic to complain about the various claude-isms in this article? I don't know any actual humans that write titles like "Two floors the rate card hides". I find my brain disengages once I suspect something of being written by an LLM. If the author didn't put much effort into writing it, should I expect them to have put much effort into fact-checking it? Edit: this specific title has been deleted from the arti…

"No generation, no estimates - just token counts:"

"Authoritative: it is the same count Anthropic bills against."

"This reframes a headline that looked like good news."

Re: The real prices of frontier models

#47

Post by zaptheimpaler »

Wow this is great, it explains what I've seen. My Codex sub seems to last way longer than Claude in real codebases, and Claude eats up a ton of context in the initial read. I thought the harness might be the cause but it seems like tokenization is probably the bulk of it.

Re: The real prices of frontier models

#48

Post by dinobones »

Just start pricing in bytes input/output. This whole "token" and "tokenizer" thing is an implementation detail that shouldn't even be leaking out into the API.

Providers change tokenizers all the time with model updates, and it's often not even possible to query/figure out how text is tokenized without actually just sending the LLM a request.

Just switch to charging for bytes of intelligence. Please. Claude Shannon figured this out decades ago.

Re: The real prices of frontier models

#49

Post by sscaryterry »

dgellow wrote: post #45
sscaryterry wrote: post #42

Earlier quoted context omitted.

If I need to put 2 and 2 together for you: https://en.wikipedia.org/wiki/Shrinkflation

Would you mind sharing your actual thoughts instead of this vague posting? What does AMD have to do with Anthropic?

The answer is 4: https://www.theregister.com/software/2026/04/06/claude-code-...

Re: The real prices of frontier models

#50

Post by iLoveOncall »

Very unpalatable completely LLM-written article, but on top of that a lot of the fundations and conclusions are completely wrong, the main one being this one:

> You will see people claim Claude uses 2x to 4x the tokens of GPT. Our measurements do not support that, and overstating it would undercut the real point.

It's not because a single prompt represents only 1.7x the number of tokens that a model doesn't use 4x as many tokens as another, when running as an agent. This doesn't take at all the number of tokens of the output into account, and the number of tokens of the potential tool calls from this output, which directly feeds back to input tokens.

The article also has a very small test set (16 documents), all of very small length (15K tokens at most, when models go up to 1M in context and agents routinely exceed this and have to summarize).

Complete garbage article.

Post reply on HN