Switching models frequently invalidates prompt cache, causing double billing
daniel_mac8 · x · 2026-08-25
@Teknium advises against constantly switching models within a single session. Doing so invalidates the prompt cache on the new model, forcing you to repay the full input token price for the entire context. This is a fundamental aspect of inference, not specific to any one model. Avoid this unless the models are free.
Related event: Teknium: Switching Models Mid-Session Kills Prompt Caches and Doubles Costs(4 posts)→
More from Infra
- Analyst: 80% of neoclouds may not survive, but the demand for their GPU capacity is real — BenBajarin · 2026-10-16
- Apple and Meta partner to run Muse Spark model on linked Mac Studios — pdamodaran · 2026-10-16
- Nvidia's developer base hits 11 million, up ~3.7x from 3 million in 2021 — Beth_Kindig · 2026-10-16
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Meta launches Muse Spark Open, says it runs on two M5 Ultra Mac Studios with Apple's help — The Verge AI · 2026-10-16