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.
@manton I go back and forth and even though the quality of GPT5.5 is great, I feel like Fable is better, because it must be right? I think I’m going to go over to your way of thinking very soon.
@robertritz It’s fascinating how much weight is carried by “too powerful to release, so it must be fine for normal people”. 🙂 I do think Fable is better, but not including it in a monthly subscription (after this week) is just too much.
@manton I think its the right decision. I assume its going to tear thru tokens and if they kept allowing it via subscription people would burn through their allowances very quickly. Given that that happens even with normal usage they’d just have a bunch of pissed off customers and frankly most people don’t need Fable.
