You pay per token, even on subscription models the limit is tokens. If I was valued at 1 trillion dollars, and I was in the hole enough to sink a couple small countries' GDP, maybe I would slowly start to optimize to maximize token usage. I want to sell tokens, how do I sell more tokens? Not by doing the same work in less tokens, that's for sure. This is like if you pay me by the hour and then excitedly tell me that…
The ability to assess the user's goal and tune the inference accordingly is there. So, what methods are there to tell if a provider has their thumb on the scale?
Plodding along a longer path to the same goal would burn more tokens without necessarily a decrease in solution quality. Maybe a few more docs.