If you understand your problem well and know 80-90% what you want it to look like (or it just isn't very hard), it's just more cost effective to use a smaller model. Even Opus is overkill for a lot of the work I do. Most code I produce is from Luna Max implementing against fairly prescriptive plans made by bigger models.

Yeah, I just threw it into a refactoring problem, and it started to produce a mess because of a bad API I decision I made 5 years ago (when I had no idea what I was writing). So stopped it, went back a step, fixed that very old piece of tech debt, then asked for the refactoring again and got exactly what I wanted.