We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost less.
Higher cache-hit rates by default mean more input tokens benefit from cached-input discounts of up to 90%.
prompt caching — Reusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Higher default cache-hit rates plus a new diagnostics dashboard let AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → builders cut GPT-6 input-tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → costs by up to 90% without re-architecting prompts.
