Event ·Single source

Alibaba Cloud Model Studio 推出 context caching,重复 prompt 只算一次全价

Alibaba Cloud Model Studio 上线 context caching 功能,针对同一 prompt 和同一批文档被反复调用却每次都按全价计费的问题。做法是把重复内容缓存一次,之后的调用直接复用,不改变现有架构。适合 prompt 固定、文档重复度高的应用场景。

Current read

阿里云百炼上线 context caching:同一段 prompt 或文档缓存一次就能重复复用,省掉重复 token 的钱,改造成本很低。

2 sources22° AI heatLast updated 2026/10/26 04:47:43

Evidence

2 sources
Primary source阿里云 Alibaba Cloud
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.