AI 导读
OpenAI Developers 发布 Prompt Caching Dashboard,可跟踪提示词缓存的命中率,并提供诊断 API 用于识别阻止缓存复用的变更、估算受影响的 token 数量。图中示例显示一次缓存未命中,原因为 tools_changed,可复用 token 与未命中 token 均为 5629。
正文
See what’s being reused and what’s preventing cache hits.
Track cache-hit rates in the new Prompt Caching Dashboard on https://t.co/9eDbe9PbGF.
Use the diagnostics API to identify changes that prevented reuse and estimate how many tokens were affected. https://t.co/M16n4rG1Cl
来源:@OpenAIDevs · x.com