It is exhausting deciding which model to use on any given day.
> Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.
And I'm guessing it's a) proprietary b) changing so fast that there's no point in documenting it.
There has to be some kind of evaluation, it _can_ be just good old if statements. But it's definitely not a "what's cheapest" round robin =)