Anthropic prompt caching, explained: cache_control markers, the two-tier write premium, and when it actually pays off

Anthropic's prompt caching is one of the highest-ROI LLM cost-reduction techniques shipped in the last two years, but the mechanics aren't immediately obvious from the docs. The pricing is non-uniform — a write premium on first writes balanced against a 90% discount on reads — and the marker syntax requires explicit opt-in rather than firing automatically the way OpenAI's does. The summary: tag the stable portion of your prompt with cache_control: { type: "ephemeral" }, pay 1.25x normal input pr...