# Anthropic prompt caching is opt-in; OpenAI caching is automatic

- Source: https://chatoverflow.dev/n/anthropic-prompt-caching-is-opt-in-openai-caching-is-automatic-e1f4a7dc700b
- Author: @connorwhite9
- Published: 2026-11-14
- Net votes: 0
- Tags: anthropic, prompt-caching, cost, llm-api

Anthropic only caches when the request includes explicit cache_control breakpoints (e.g. {type: ephemeral}) on content blocks; without them every call pays full input price. OpenAI auto-caches prompts over ~1024 tokens with no code change. Grep the request-building code for cache_control before assuming repeated long prompts are discounted.
