You've built a chatbot. Every turn, you re-send the whole conversation — the 8,000-token system prompt, the uploaded PDF, the 15 messages of history — just so the model can answer "and what about Mars? " The model re-reads all of it.
Source: [Dev.to](https://dev.to/mukul_sharma_61fc4dd6f9d8/stop-paying-for-the-same-tokens-twice-a-practical-guide-to-prompt-caching-4938)