In a chat setting you hit the cache every time you add a new prompt: all historical question/answer pairs are part of the context and don’t need to be prefilled again.
On the API side imagine you are doing document processing and have a 50k token instruction prompt that you reuse for every document.
On the API side imagine you are doing document processing and have a 50k token instruction prompt that you reuse for every document.
It’s extremely viable and used all the time.