Which prompt-construction pattern is most likely to actually hit the provider's prompt cache?

Attempt it

Quick reference

TL;DR

Prompt caching reuses prefill KV for a byte-identical prefix, so cached input bills at roughly 10 percent of normal; any variable content above stable content breaks the hit.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine reading the same long instruction sheet aloud before every conversation. The first time you read it slowly, but you remember it, so next time you can skip straight to the new question. Prompt caching is that memory for the model. When the start of your prompt is exactly the same as before, the provider reuses the work it already did and charges you a small fraction for those repeated tokens. But the trick only works from the very beginning. If you change even one word near the top, like stamping today's date, the model has to reread everything below it from scratch and you pay full price again. So you keep the unchanging part at the front and put the part that changes at the very end.

Key concepts

Prompt caching KV cache Prefill Time to first token

Detailed answer & concept explanation

~8 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

3 min: why prefill reuse enables the discount + cached read at ~10 percent and the write premium + byte-identical prefix matching + stable-first prompt layout + TTFT win and what silently breaks a hit.

Real-world examples

Real products, models, and research that use this idea.

Anthropic's Claude Opus 4.7 prompt caching bills cache reads at roughly 10 percent of input rate, with a one-time write premium, controlled by explicit cache breakpoints.
OpenAI's GPT-5.5 applies automatic prefix caching for repeated prompt prefixes above a token threshold, discounting the cached input segment.
Google's Gemini 3.1 Pro offers both implicit and explicit context caching so long stable documents are billed at a reduced cached rate.
RAG agents built on LangChain place the system prompt and tool schemas first so cache hits survive across thousands of per-query retrievals.
vLLM and SGLang expose automatic prefix caching that shares cached KV blocks across requests with common system prompts on self-hosted stacks.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QWhy does cached input cost roughly 10 percent rather than zero?

Sign in or go Pro to see the approach for this follow-up.

QWhy is there a write premium on the first cached request?

Sign in or go Pro to see the approach for this follow-up.

QHow does prompt caching interact with retrieval-augmented generation layout?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Putting a per-request value like a timestamp, session ID, or freshly retrieved chunks above the stable system prompt. It poisons the prefix and forces full-price prefill on everything below.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.