Since 20 October, GPT-5.6 and later can hold a cached prefix for at least 12 hours in the Responses API. Writes cost 2.5x input; read prices are unchanged.
Anthropic released Claude Haiku 5.5 on 7 October at $0.10 input and $0.50 output per million tokens for prompts up to 100K, a tenth of Haiku 4.5's price. Sonnet 5.5 cache reads fall from $0.20 to $0.10.
A repeated prompt can cost less when its beginning stays the same. Here is how to arrange stable instructions and changing context so the cache has something useful to reuse.
Token prices are the input to your bill, not the bill. Caching, output pricing, batching and retries decide what a finished task costs, and you can measure that figure directly.