# What is context caching?

Context caching is the explicit form of prompt caching: you register a large block of context, a policy book, a codebase, a document set, once, and reference it across many requests. The provider holds the computed state, so each request pays the discounted cached rate instead of reprocessing the corpus.

It suits workloads where many questions hit one large, stable corpus: policy answering over the same handbook, review agents reading the same codebase, support flows grounded in the same documentation.

Implicit prompt caching does the same job automatically when prefixes repeat; explicit context caching adds control over lifetime and reuse. Either way the economics are the published cached-input rate on the model’s pricing page.

## Related terms

- [Context window](https://allocate.network/glossary/context-window.md)
- [Retrieval-augmented generation](https://allocate.network/glossary/rag.md)
- [Prompt caching](https://allocate.network/glossary/prompt-caching.md)

---

[HTML page](https://allocate.network/glossary/context-caching) · [Machine-readable catalog](https://allocate.network/catalog.json)