Claude Fable 5.2: the price cut is the story
Fable 5.2 and Mythos 5.2 shipped cheaper and faster: $8/$40 per million tokens, output up to 30% faster. Prices, benchmarks, and what a run actually costs.
Notes
Short findings from running local AI models and agents on a Mac Studio, made to share.
Why I'm publishing my local AI numbers
This site is my lab notebook for local models and agents, measured on my own hardware, with the raw data attached to every post.
New posts go to the RSS feed first.