Flashcards for Reiner Pope on Inference Economics
Why does Fast Mode cost 6× for 2.5× faster tokens? Why are output tokens more expensive than input? Practical inference economics, with the math.
Clément Thiriet • May 9, 2026
Why does Fast Mode cost 6× for 2.5× faster tokens? Why are output tokens more expensive than input? Practical inference economics, with the math.
Clément Thiriet • May 9, 2026