What is the core mechanism of prompt caching?	The system processes an initial request, saves the work to a temporary cache, and then loads that saved work for identical follow-up requests instead of re-processing.
How long does the prompt cache persist?	It is only stored for five minutes.
Is prompt caching enabled by default in clod?	No, it must be manually enabled by adding a cache breakpoint to a block within a message.
What content structure is required to use the cache control feature?	The text fields must be written out in "long form" (using a list containing a dictionary with a type and text field), not the shorthand.
What does a cache breakpoint cache?	All content in the request up to and including the breakpoint.
What condition must a follow-up request meet to utilize the cache?	The content must be identical to the initial request all the way up to the breakpoint.
List three types of blocks where a cache breakpoint can be placed.	Message blocks, tool schemas, and system prompts (or image blocks, tool use, tool results).
In what order are tools, system prompts, and messages joined when fed into clod?	Tools, then the system prompt, then the list of messages.
What is the maximum number of cache breakpoints that can be added?	Up to four.
What is the minimum content length required for content to be written to the cache?	At least 1024 tokens.