Why My LLM Feature Cost More Than It Should: Field Notes on Prompt Caching, Cache Breakpoints, and the Timestamp That Killed Every Hit

Automated excerpt

Headline: Prompt caching saves money only when the cached prefix is byte-identical across requests, and a single interpolated timestamp in a system prompt is enough to make every call a cache write instead of a cache read. Q: Does prompt caching change the model's output? Q: Should I cache tool definitions or the system prompt first?

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.