Live data from Hacker News

Apple Silicon costs less than OpenRouter

twitter.com

11–20 of 24 posts

Re: Apple Silicon costs less than OpenRouter

#12

You managed to reverse the title somehow.

That's some HN shenanigans, I swear I copy pasted my original title. https://imgur.com/a/UgJqWEh

For future reference, after posting you have a couple minutes to undo any of those auto-shenanigans. I always check, and undo whatever appears to be a silly regex.

YC is super AI-forward regarding request for startups, so it feels like about time that this became an LLM-based thing. LLMs do have their uses.

note: would be hilarious if this was the result of an LLM fail, using a new system. I am a regex muggle, but could a normal regex implementation have even fumbled like that?

Re: Apple Silicon costs less than OpenRouter

#14

The title is Apple Silicon costs LESS than OpenRouter. Not sure why it got updated to this - maybe because I referenced the original HN post? Here's the full post: TLDR; When you consider batching, cache and input tokens, together with the residual cost of Macbook Pro is actually 14% cheaper than OpenRouter. This becomes a whooping 3x (i.e. 65%) cheaper if you consider MoE models like Gemma 4 26B. There was a well-me…

The tweet does not make clear what the power cost assumptions are? That is wildly variable and important! For some people it may be, perhaps not for others.

Re: Apple Silicon costs less than OpenRouter

#15

The title is Apple Silicon costs LESS than OpenRouter. Not sure why it got updated to this - maybe because I referenced the original HN post? Here's the full post: TLDR; When you consider batching, cache and input tokens, together with the residual cost of Macbook Pro is actually 14% cheaper than OpenRouter. This becomes a whooping 3x (i.e. 65%) cheaper if you consider MoE models like Gemma 4 26B. There was a well-me…

The tweet does not make clear what the power cost assumptions are? That is wildly variable and important! For some people it may be, perhaps not for others.

I used the same assumptions as the original HN post https://news.ycombinator.com/item?id=48168198

Re: Apple Silicon costs less than OpenRouter

#16

Earlier quoted context omitted.

That's some HN shenanigans, I swear I copy pasted my original title. https://imgur.com/a/UgJqWEh

For future reference, after posting you have a couple minutes to undo any of those auto-shenanigans. I always check, and undo whatever appears to be a silly regex. YC is super AI-forward regarding request for startups, so it feels like about time that this became an LLM-based thing. LLMs do have their uses. note: would be hilarious if this was the result of an LLM fail, using a new system. I am a regex muggle, but co…

Thanks for the info. Daniel fixed it - and no it wasn't an LLM error. :P

Re: Apple Silicon costs less than OpenRouter

#17

Earlier quoted context omitted.

That's some HN shenanigans, I swear I copy pasted my original title. https://imgur.com/a/UgJqWEh

For future reference, after posting you have a couple minutes to undo any of those auto-shenanigans. I always check, and undo whatever appears to be a silly regex. YC is super AI-forward regarding request for startups, so it feels like about time that this became an LLM-based thing. LLMs do have their uses. note: would be hilarious if this was the result of an LLM fail, using a new system. I am a regex muggle, but co…

has to be AI, right? i mean.. less is more i guess?

But this is actually pretty fucked up. Just casually inverting the meaning of titles. Unacceptable tbh

Re: Apple Silicon costs less than OpenRouter

#18

Earlier quoted context omitted.

That's some HN shenanigans, I swear I copy pasted my original title. https://imgur.com/a/UgJqWEh

I think the most correct would be "OpenRouter costs 800% less than Apple Silicon" ;)

I don't think I follow?

Re: Apple Silicon costs less than OpenRouter

#19

Similar titled discussion from a day ago: https://news.ycombinator.com/item?id=48168198

From the other discussion: "running at full capacity, 24/7. Why would you do that?".

Also, I'd say if you're using Mac anyway that changes the economics, depends whether you've had to upgrade specs to run the size models you want. Going up to 64, 96 or 128GB adds 1000s to the price.

However when I'm doing non local inference, I rarely use a model as small as 32B.

Post reply on HN