LLM API Cache Hit Math: Why Your DeepSeek Bill Says $4 But the Pricing Says $50

TL;DR Real LLM bills run 3 to 50 times lower than the headline per-million-token price because most input tokens come from cache. DeepSeek's deepseek-v4-flash cache read is $0.0028 per million versus $0.14 cache miss — a 50x discount. Claude Opus 4.6...