In my book, the single most effective way to spend tokens is having it review code/specs you've written. One advantage to putting the ai in that position is that unreliable competence isn't much of a problem as you can ignore bad suggestions.

I would also recommend explaining the specs and doing a lot of your back and forth with a lower end model and set it to a higher end model only once the conversation history has all the context you feel the higher end model needs.