Seems like it might be more advantageous to just adjust reasoning effort to retain cache. Maybe in some exceptional cases where there will be a ton more inference to solve the problem, but going significantly dumber in that case seems counterintuitive.

I can really only see the utility of things like spawning subagents to a lower tier model from another provider, and that's something harnesses can already handle (ie. give model specs for certain delegation roles).

I agree that adjusting the reasoning effort to retain cache is a huge thing! But even doing that automatically is currently a challenge for people to figure out and do well, and costs mental energy when perhaps it doesn't need to. For example, there is GPT-5.6-Sol low, med, high, xhigh, max, and lots of "rules of thumb" that people develop on which one to use when.

caching is per model, it does not transfer between them