AI news
公司内部站点 · 页面资源保存在本地(2026-10-17 04:19 UTC)· 独立 X 采集尚未配置;互动计数仅限本站

OpenAI Developers improves prompt caching for GPT-6 in the API

OpenAI Developers

OpenAI Developers has improved prompt caching in the API for GPT-6. Cache-hit rates are higher by default, so more input tokens can receive cached-input discounts of up to 90%.

OpenAI Developers says the change helps agents run faster and cost less.