Please can I ask about one parameter you didn't mention here? All of your models have both a reasoning effort setting and also a non-pro vs pro setting. I have some intuitive feel (from experimenting) for the difference a larger vs smaller model makes, and why that's different from adjusting reasoning levels, but I have no real feel for how pro vs non-pro is different in behaviour from adjusting effort.

I think you can think of Pro approximately as running multiple instances of a non-pro model, than giving all their outputs to a final judge model which combines them into a better one.

I use OpenAI models all the time (via Codex) and I've never seen this pro toggle. Where are you seeing that?