agentVIDEO
OpenAI 改进 GPT-6 的 API 提示缓存
GPT-6 默认缓存命中率提高，更多输入 token 可享最高 90% 的缓存输入折扣，让 agent 更快更省。
OpenAI Developers
@OpenAIDevs2026.09.23收录原推发布于 2026.09.23
OpenAI Developers @OpenAIDevs原推发布于 2026.09.23
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%. https://t.co/NZse8QKr8G
x.com/openaidevs/status/2102506476401258678采集于 2026.09.23 10:42