GPT-6's improved prompt caching cuts agent costs; leads AutomationBench at 88% less
OpenAIDevs · x · 2026-09-23
OpenAI detailed GPT-6's improved prompt caching: agents do less redundant processing, and more context stays reusable as reasoning effort and tool availability change, making responses faster and cheaper.
The same thread cites AutomationBench (measuring whether models can complete real business workflows across apps): GPT-6 Sol (xhigh) leads Fable 5.1 (max with Opus 5 fallback) with 88% lower reported cost per task.
More from Infra
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- Analyst: 41% of all AI inference will run below the 20 MW line by 2031 — antavedissian · 2026-11-12
- Small AI sites under 20 MW mostly skip the permitting fights battering big data centers — antavedissian · 2026-11-12
- AI inference to grow 1,000x in 5 years, but power only 10x — where does it run? — antavedissian · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12