Comment by Espressosaurus
7 hours ago
Anything with long context quickly gets dominated by cache reads. Especially for interactive sessions I’ve got cache read % between 95% and 98%.
7 hours ago
Anything with long context quickly gets dominated by cache reads. Especially for interactive sessions I’ve got cache read % between 95% and 98%.
In my mix it's usually 98% or 99% at which point Fable 5.1 was pretty close to the same cost as Opus 5 due to the cheaper cached read. I've seen similar numbers for other people with long-running tasks running experiment loops and than sort of thing.