AI Dynamics

Global AI News Aggregator

About

Why API Model Conversations Depend on Prompt Caching

Your 5-minute cache is already dead when you sit down. API models don't keep the thread. Every turn resends the whole history. A one-token tool result still pays that whole history. On Opus 5, 1 million uncached tokens are $5. A hit is $0.50. Cache-hit discounts are

→ View original post on X — @alphasignalai