← Back to Model Beat
Models·Sep 22·all news from September 22, 2026

Better prompt caching for GPT-6

OpenAI has introduced new prompt caching features for GPT-6, including explicit breakpoints, enhanced diagnostics, and improved hit rates. These updates are designed to lower latency and operational costs for developers by allowing the model to more efficiently reuse previously processed input data.

Covered by 1 source

Related stories

ModelsGoogle Joins OpenAI, Anthropic, Meta in Disclosing AI HacksSep 18 · 21 sourcesModelsClaude discovers a novel enzyme system with CRISPR-like repeatsSep 22 · 8 sourcesModelsIntroducing GPT-6 Sol and LunaSep 22 · 7 sourcesModelsIntroducing Gemini 3.8 Live with Live AvatarSep 24 · 3 sources