Philip Z on Mythryl: “> Cache reads now cost $0.25 per million tokens, 75% less than Fable…”

> Cache reads now cost $0.25 per million tokens, 75% less than Fable 5 This is a *huge* price drop, given that cache reads inevitably end up most of your costs, because of the quadratic nature of LLM conversations. blog.exe.dev/expensively-...

blog.exe.devExpensively Quadratic: the LLM Agent Cost Curve - exe.dev blogCache reads are quadratic and dominate your long agentic conversations.

1/9/26, 8:39 pm1 repost8 likes

Post