Open main menu
Article
Quizzes
Tools
EN
Article
Quizzes
Tools
All quizzes
/
LLM Fundamentals
/
What does ...
What does prompt caching do in LLM APIs?
It saves the processed representation of a prompt prefix so repeated requests don't re-process it
It stores the model's output so identical prompts return cached text without calling the model
It compresses the prompt to reduce token count before sending to the API
It batches multiple prompts together to improve throughput
Submit answers