Local isn’t (just) about cost, it’s control and trust.
Apple Silicon costs more than OpenRouter
31–40 of 322 posts
Re: Apple Silicon costs more than OpenRouter
#32OpenRouter doesn't expose all the LLM sampling parameters/research that llamacpp, vllm, sglang, et al expose (so no high temperature/highly diverse outputs). Also OpenRouter doesn't let you use steering vectors or LoRA or other personalization techniques per-request. Also no true guarantees of ZDR/privacy/data sovereignty.
Oh, and the author didn't mention at all anything related to inference optimization, so no idea if they even know about or enabled things like speculative decoding, optimized attention backends, quantization, etc.
At least AI slop would have hit on far more of the things I listed above. This is worse-than-AI.
Re: Apple Silicon costs more than OpenRouter
#33This 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.
I’ll keep my data local over a $.02/mtok difference.
Re: Apple Silicon costs more than OpenRouter
#34"Accelerated depreciation (if any) from shortening the lifespan of the device will be more expensive than the electricity" Shortening the lifespan?
The amount of FUD and notion that hardware depreciates in this manner is widely held. I blame Michael Burry of the Big Short who is perpetuating these lies to the investor community today.
There's a bunch of retro hardware which should make people pause and realize they're stupid to assume hardware slows down on average even 5% 20 years later (it's probably closer to 2% and I'm being generous).
HVAC/power delivery and generation are the major factors, and if you didn't skimp/get defective parts for this and replace failed moving parts (usually fans), your hardware is basically the same 20 years down the line as it was today.
Also using LLMs locally doesn't even induce sustained 100% GPU usage over significant periods of time for most real (agentic coding in OpenCode) use-cases.
Re: Apple Silicon costs more than OpenRouter
#35> Let's round up to $0.20 per kWh.
Next paragraph
> At ~50-100 watts and $0.18/kWh that's $0.009 or $0.018 per hour. $0.02 per hour. $0.48 cents per day for the electricity to be running inference at 100%.
lol
Re: Apple Silicon costs more than OpenRouter
#36I simply can't go back to cloud AI. Privacy and full control are more important to me than speed and SOTA models.
Also predictability, resilience, sovereignty. I'm not worried about other people's outages, that unexpected demand will impact me at an inconvenient time, that someone's watering down my model, that my costs will change unpredictably or that some unforseen error will lead to a huge bill.
It's in the same category as rooftop solar for me. It doesn't have to make strict economic sense if you're the particular type of person who gets peace of mind from control of infrastructure / reduced dependency.
Re: Apple Silicon costs more than OpenRouter
#37OP is comparing against Gemma everywhere but concludes paying Anthropic make more sense. Anthropic is $15 per million output token which is 30-35x more expensive even in openrouter .
This is like comparing e-bike at home with e-bike rental and concluding therefore we need to rent Toyota since it can go at similar speeds. Getting tired of bad posts getting much attention .
Re: Apple Silicon costs more than OpenRouter
#38This 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…
nothing about the current data center craze looks efficient.
Re: Apple Silicon costs more than OpenRouter
#39This 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…
using it 24/7 brings the average cost down, not up. the less you use local LLM, the less sense it makes since you paid a lot for hardware you don't use
The hardware has multiple uses for the same cost. The pay-per-use server does not.
Re: Apple Silicon costs more than OpenRouter
#40Local LLMs aren’t about cost, but control.