Larger models need more memory. I'm willing to bet that most of the tier 1 providers rely on multi-GPU models to serve traffic.
None of that is cheap, 8x GPU nodes that serve less than 20 queries a second are exceedingly expensive to run.
You need to compare like-for-like. You can't say that the cost of building a 5-story apartment is increasing by pointing at the burj khalifa.
I seriously don't get this argument and I see it being repeated all over and over again. Although model possibilities are increasing, no doubt in that, HW costs for inference remained the same and they're mostly driven by the amount of (V)RAM you need.