Prompt caching can inflate your LLM bill: check write premiums, TTL and actual reuse
gethackteam · x · 2026-09-13
A practical reminder that prompt caching can cost extra if you keep paying to write a cache nobody reads:
- Check your provider's cache-write premium, expiry (TTL) and actual reuse rates
- A discounted cache-read price won't help if every request creates a fresh cache
- Anthropic, for example, defaults to a 5-minute TTL — meaning you may be losing money on their cache
More from Infra
- xAI's Memphis datacenter now has its own power sources en route to $100b ARR — PaulYacoubian · 2026-09-13
- DeepSeek's V4.1-Flash KV cache compression could undercut OpenAI and Anthropic's compute moat — justlikemedics · 2026-09-13
- Google to spend $15.1B on Finnish AI infrastructure, including three data centers and 22-year nuclear deal — Beth_Kindig · 2026-09-13
- Dev picks LFM2.5-2.6B and MiniCPM5-2B as favorite edge-device models — reach_vb · 2026-09-13
- Speculative decoding: the trick behind Google's 2-3x faster LLM inference in production — hongyangzh · 2026-09-13
- TRL v1.13 ships long-context training: 1M+ token sequences on a single 8-GPU H100 node — SergioPaniego · 2026-09-13