abuse prevention

LLM endpoints are unusually exposed: every call can spend real money and consume scarce GPU capacity, so abuse is a security and a financial problem at once. What lands is layered controls on tokens and cost, not just request count. Here is the defense.

Rate limits stop a user who costs you too much. They do nothing about a user doing something you forbid. The enforcement system is a different design, and interviewers can tell within a minute whether you have built one.