{
  "id": "prompt-caching",
  "code": "PTL-0081",
  "term": "Prompt Caching",
  "aliases": [
    "context caching",
    "prefix caching"
  ],
  "category": "optimization",
  "definition": "Prompt caching stores the model's processed state for a reused prompt prefix, such as a long system prompt or document, so later requests sharing that prefix are cheaper and faster.",
  "description": "Because caches match on an exact prefix, prompts are structured with stable content first and variable content last.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "system-prompt",
    "prompt-compression",
    "context-engineering"
  ],
  "introduced": 2024,
  "sources": [
    {
      "title": "Prompt caching",
      "authors": "Anthropic",
      "year": 2024,
      "url": "https://platform.claude.com/docs/en/build-with-claude/prompt-caching"
    }
  ],
  "url": "https://protologue.com/t/prompt-caching/",
  "citation": "Protologue. (2026). Prompt Caching. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0081). https://protologue.com/t/prompt-caching/"
}