# Prompt Caching

> Reusing unchanged prompt or context segments so repeated model calls can be cheaper or faster.

- Category: Context & Memory
- Stage: Established
- Also called: Context caching, Cache hit
- Canonical: https://www.joelcsaji.com/ai-dictionary/prompt-caching

## Plain English

If the giant system prompt and docs are the same, the provider may not need to process them from scratch.

## Example

An agent repeatedly includes the same tool definitions and project instructions across many turns.

## Why it matters

Caching makes long-context and tool-heavy applications more practical in production.

## Related

- [Context Window](https://www.joelcsaji.com/ai-dictionary/context-window)
- [Function Calling](https://www.joelcsaji.com/ai-dictionary/function-calling)
- [Latency](https://www.joelcsaji.com/ai-dictionary/latency)

## Sources

- [Google Cloud Generative AI Glossary](https://docs.cloud.google.com/docs/generative-ai/glossary)
- [OpenAI: Prompt Caching](https://platform.openai.com/docs/guides/prompt-caching)