top | item 47034131

(no title)

0-_-0 | 13 days ago

The cache gets read at every token generated, not at every turn on the conversation.

discuss

order

mzl|13 days ago

Depends on which cache you mean. The KV Cache gets read on every token generated, but the prompt cache (which is what incurs the cache read cost) is read on conversation starts.

0-_-0|13 days ago

What's in the prompt cache?