Simon Willison blogged about letting Fable decide when to use cheaper models:

Jesse Vincent just gave me a related tip to help avoid burning too many of those valuable Fable tokens in the few days we have left before the prices go up. Tell Fable to use other models for smaller tasks, applying its own judgement about which model to use.

Fable pricing is nutty. I’m happy to just run GPT-5.5 with fast and xhigh for everything and not worry about it.