# Every team wants AI. Then three questions arrive: What does it cost? Where are the keys? Can we stop it?

> Source: <https://dev.to/sandhil_kypa_b7cd7c3d5f39/every-team-wants-ai-then-three-questions-arrive-what-does-it-cost-where-are-the-keys-can-we-4682>
> Published: 2026-11-21 10:05:43+00:00

**Key takeaway:** SanVi routes app traffic through one OpenAI-compatible LiteLLM endpoint on Kubernetes, centralizing cost tracking, key management and the ability to halt AI requests.

[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
