Every team wants AI. Then three questions arrive: What does it cost? Where are the keys? Can we stop it? A platform engineer built SanVi, an OpenAI-compatible AI gateway on Kubernetes powered by the LiteLLM engine, to give teams a single endpoint that answers three operational questions: what AI usage costs, where API keys are held, and whether requests can be stopped. The project centralizes model access and control for applications consuming AI services. sandhil kypa https://dev.to/sandhil kypa b7cd7c3d5f39 Posted on Every team wants AI. Then three questions arrive: What does it cost? Where are the keys? Can we stop it? I'm a platform engineer, and I built SanVi to answer all three on Kubernetes. The gateway Apps call one OpenAI-compatible endpoint LiteLLM engine