Prompt caching

Prompt caching stores the processed form of a stable chunk of your prompt, such as a long system prompt or a set of files, so later requests reuse it instead of paying full price to read it again. The first request writes to the cache; later ones read from it.

For an agent that re-reads the same project context every turn, that is the difference between an expensive session and a cheap one. A cache read costs about a tenth of the input price on most models, and less on the newest ones. The write costs a little more than a plain input token, so caching pays off once the content is read back. Model it with the cost calculator.