> may have actually been cheaper to use Fable on low even though the cost per token is drastically higher

Well that's the problem with these black boxes. You really have no idea beforehand how many tokens a given task is going to take. There's simply too many variables involved. It's therefore only natural for people to assume "the cheaper and older model is probably going to cost less overall to use than the newer, more expensive one."

I'm definitely using more credit per task, using Fable, but I'm also giving it much more difficult tasks. You're right, it's very hard to tell. I think that using Opus would be more expensive because of the number of iterations I would need to go through.