The real costs are dropping because of real efficiency gains and compute cost reductions.
The inference costs are dropping at a similar rate.
The inference costs are dropping at a similar rate.
I would add that inference cost decreases is what we should expect, it stands to reason there will be algorithmic improvements in inference, and compute cost is still going down just because of (a somewhat sloped) Moore's law.
Maybe you could also be a bit friendlier and forthcoming in your responses.