I Forgot About My AI Inference Bill for a Month

Tue, 18 Aug 2026 00:00:00 +0000

I run a service that routes AI inference to the cheapest available GPU. So I spend an unreasonable amount of time staring at provider pricing dashboards. And the thing I keep learning is that the sticker price on an AI model tells you almost nothing about what inference actually costs you.

Take a 70B parameter model. Provider A charges $0.60 per million input tokens. Provider B charges $0.90. Provider A is cheaper, right?

How a Spreadsheet Turned Into an AI Inference Router

Fri, 14 Aug 2026 00:00:00 +0000

I accidentally stumbled on spot market pricing for AI compute. So naturally, I built a service around it.

The short version: GPU prices vary wildly between providers. Same model, same output, different costs depending on when and where you run it. An H100 on one provider costs $2.10/hr right now. Same GPU on another, $3.80/hr. Tomorrow those numbers will be different again.

I found out the hard way. I was running AIVory Guard on a single provider, picked because it was cheapest when I checked. A month later the bill was 40% higher than I expected. The prices had moved and I had not noticed.

Smart-Inference on Ilscipio - Enterprise Commerce Experts

I Forgot About My AI Inference Bill for a Month

How a Spreadsheet Turned Into an AI Inference Router