The cheapest LLM request is the one you don't send. If the same question shows up twice, there's no reason to pay twice — the model's answer hasn't changed, and the user doesn't care where it came from.
This post covers both: what caching is, the two kinds you'll run into, where each works, and how to enable it on LLM Gateway without touching your code.
What Caching Actually Does
A cache sits between your app and the LLM provider. When a request comes in:
The gateway hashes the request parameters (model, messages, temperature, tools, system prompt) into a cache key
