model routing — Sending each request to a model chosen by the difficulty of the task, rather than using one model for everything.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Cache-read pricing, not sticker tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → price, decided which model was cheaper on a real AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → workload ($79 vs $155 over 417 tasks) — a router built from pricing sheets is optimizing the wrong number.
