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

Apple Silicon costs more than OpenRouter

williamangel.net

Post reply on HN
Print view View original

141–150 of 322 posts

Re: Apple Silicon costs more than OpenRouter

#141

Post by freakynit »

datadrivenangel wrote: post #119
freakynit wrote: post #26

So I did the India-specific analysis for a tier-3 city. Here, electricity costs 1/3rd of the US version, and you also get solar subsidy up to a certain amount. https://shorturl.at/q6gRE tldr; Hardware deprecation costs are the major factor. But, if we assume ZERO hardware deprecation (not realistic), then local inference becomes super cheap.. roughly, 90%+ cheaper. Third case: the break-even happens only if we can ge…

I think your link is broken? Would love to see the analysis as well.

not much of an analysis really.. just simple math... anyways, that markdown share site takes around 5-10 seconds to load the page.. so, just hang on a bit more time :)

Re: Apple Silicon costs more than OpenRouter

#143

Post by MuffinFlavored »

brianwawok wrote: post #85
MuffinFlavored wrote: post #66

Earlier quoted context omitted.

> Frontier AI companies are selling at a loss. How big/deep of a loss? I feel like I read this every day for years that Uber did this same "idiotic, losing" strategy (how it was pitched/discussed) and then one day we woke up and... without much fuss, boom, they were profitable seemingly overnight.

Well and uber cut the driver pay in half and doubled the price. They didn’t really find any efficiencies, robo drivers don’t exist yet. Also why I hardly touch them anymore.

> Well and uber cut the driver pay in half and doubled the price

Devil's advocate:

* inflation caused everything to go up to some degree since then

* if it was "that bad" as you say, they wouldn't be extremely profitable and have so many users

both things can be true? "they cut the driver pay in half and doubled the price" did not lead to the collapse of the business/people to stop using it.

Re: Apple Silicon costs more than OpenRouter

#144

Post by SXX »

Author forgot that after 3 years when hardware no longer decent for inference you can still resell it for 25-50% of price.

Obviously if RAM apocalypse passes by then high-end configurations preserve resale value worse than base models, but still it's hefty bonus of Apple hardware that might change math a lot.

Re: Apple Silicon costs more than OpenRouter

#145

Post by nativeit »

datadrivenangel wrote: post #27
bastawhiz wrote: post #14

This isn't a good analysis, and it's because it keeps rounding everything up. He rounds up the cost of electricity by 10%. He has a range of power use, takes the high end (which is 2x the low end) and multiplies it by the inflated electricity cost. But then they talk about using a newly purchased Mac to do the inference, running at full capacity, 24/7. Why would you do that? Apple silicon is fast but the author point…

Rounding everything down in the most optimistic setting got me to $0.40 per million tokens, and openrouter has the same model at $.38/mtok.

But once all that is done you still own a Mac in one case, and you don’t in the other, correct?

Re: Apple Silicon costs more than OpenRouter

#146

Post by debugnik »

formerly_proven wrote: post #109
datadrivenangel wrote: post #27

Earlier quoted context omitted.

Rounding everything down in the most optimistic setting got me to $0.40 per million tokens, and openrouter has the same model at $.38/mtok.

What is it with AI SaaS naming themselves "openxyz" when there is 0% open about them?

It's the next co-opted buzzword after "democratize".

Re: Apple Silicon costs more than OpenRouter

#147

Post by genxy »

dijit wrote: post #82
vlovich123 wrote: post #75

Earlier quoted context omitted.

Which is where your analogy breaks down and why you think you’re taking crazy pills. Inference is growing and selling the oranges in your analogy. Model building is growing the farm to sell larger, juicier more addicting oranges.

Are ya fuckin' serious mate? The restaurant next to the mines were profitable up until the moment the mines themselves shut down: one doesn't exist without the other. You can't ringfence inference as "the profitable bit" and then hand-wave away the training. Without continuous training there is no inference product. Claude 3 Opus isn't sitting there making revenue in 2026 - the thing is just deprecated . The moment y…

> Claude 3 Opus

Unless they are changing the architecture in huge ways. The pre-training done for 3 goes into later models. I am sure the frontier labs are figuring out how to pretrain generic feedstocks that can be fed into downstream training pipelines. DeepSeeks incremental training run cost was what, 5M? Alibaba and DeepSeek have the best most efficient training pipelines, look at the rate at which custom Qwen models are being pumped out.

Re: Apple Silicon costs more than OpenRouter

#148

Post by freeopinion »

datadrivenangel wrote: post #97
quietsegfault wrote: post #45

Earlier quoted context omitted.

It’s more than just data locality. OpenRouter is faster, no? I have an M4 pro, and anything but the smallest dumbest models are unusably slow for interactive use. I personally haven’t yet found a good use case for offline/non-interactive LLM work locally.

Yeah. The speed is the biggest issue. The intelligence of open models is good enough for serious work (though still worse than the frontier models), but the cloud models are often 3-7 times faster, and you can get more parallelization and so get speeds on the order of hundreds of tokens per second, which makes things fast!

Even extremely slow LLMs can generate Part B faster than I can audit Part A. So the LLM can generate Part A while I look over my email. Then it can worry over Part B while I look over Part A.

It can worry over Part C while I have my 10:30 group meet. And it can worry over Part D while I do whatever other silly, time-wasting thing all humans do in almost all organizations. Then I still haven't reviewed Part B, yet, so the extremely slow AI is waiting on me.

Maybe someday I'll be good enough to need faster AI so I can rewrite something like Bun in a few days. Right now, slow and local fits my use case very well.

Re: Apple Silicon costs more than OpenRouter

#149

Post by dcrazy »

mpyne wrote: post #102
faitswulff wrote: post #46

Earlier quoted context omitted.

The article makes no sense. I can't use OpenRouter as a general purpose computing device. Why are we comparing a whole computer to a single purpose SaaS?

They're responding to the people doing things like buying the most expensive Mac they can find specifically to do local inference for their AI agents. Some do it to have control over their ability to use AI. Some do it because they think it will be cheaper to not have to pay a SaaS to generate tokens for them. But for those interested in the latter case, it seems like it's not actually cheaper after all, at least at…

You also have control over your costs. It is reasonable to assume that tokens will cost significantly more in the near to medium future as the market consolidates and subsidies decline.

Re: Apple Silicon costs more than OpenRouter

#150

Post by odo1242 »

nativeit wrote: post #145
datadrivenangel wrote: post #27

Earlier quoted context omitted.

Rounding everything down in the most optimistic setting got me to $0.40 per million tokens, and openrouter has the same model at $.38/mtok.

But once all that is done you still own a Mac in one case, and you don’t in the other, correct?

Yea this; it’s the same reason why mortgaging is cheaper than renting
Post reply on HN