---
title: "What did AI cost you this quarter?"
description: "AI infrastructure costs are often billed to a platform team as one lump sum, leaving Finance without a departmental breakdown and teams without feedback on their usage. The post presents a working demo on Red Hat OpenShift AI that attributes requests and token consumption through department-specific MaaS API keys, shared model servers, Prometheus metrics, Perses dashboards, and MLflow traces. In its example, three departments generate 79,420 inference requests and consume 634 million tokens against a $14,200 quarterly bill, while Marketing’s 32% GPU utilization reveals roughly $34,000 in annual waste. The system combines aggregate usage filters with request-level details such as prompts, token counts, latency, and calculated cost, and the post argues that showback helps identify inefficient allocations and model mismatches rather than police teams."
---

# What did AI cost you this quarter?

[Red Hat](https://yomu.fyi/company/red-hat) · Markell Rawls, Suhas Kashyap · Sep 18, 2026

**Type:** Tutorial

## Summary

AI infrastructure costs are often billed to a platform team as one lump sum, leaving Finance without a departmental breakdown and teams without feedback on their usage. The post presents a working demo on Red Hat OpenShift AI that attributes requests and token consumption through department-specific MaaS API keys, shared model servers, Prometheus metrics, Perses dashboards, and MLflow traces. In its example, three departments generate 79,420 inference requests and consume 634 million tokens against a $14,200 quarterly bill, while Marketing’s 32% GPU utilization reveals roughly $34,000 in annual waste. The system combines aggregate usage filters with request-level details such as prompts, token counts, latency, and calculated cost, and the post argues that showback helps identify inefficient allocations and model mismatches rather than police teams.

## Context

The subject is departmental AI cost attribution: turning shared-cluster inference activity into usage and dollar breakdowns that platform teams can present to Finance. The post frames showback as a way to identify idle capacity, inefficient model choices, and teams struggling with poor model fit.

## Approach / What changed

The demo uses MaaS API keys and subscriptions to establish department identity and quotas, vLLM or llm-d to serve models, Prometheus and the cluster observability operator to collect token metrics, Perses to display subscription and model usage, and MLflow to trace individual inference requests. Per-model input and output token rates are then used to calculate costs.

## Takeaways

- Department-specific MaaS API keys provide the identity boundary needed to associate model requests and token consumption with teams.
- Perses exposes aggregate usage by subscription or model, while MLflow traces provide request-level prompts, token counts, latency, and calculated cost.
- Marketing’s 32% GPU utilization indicates that 68% of its allocated capacity was idle, corresponding to roughly $34,000 in annual waste at the stated node price.

## FAQ

### Does cost attribution require a separate billing tool or application-code changes?

No separate billing system is required to get started. If applications already call the MaaS Gateway with department-specific API keys, Prometheus, the built-in Perses dashboard, and MLflow can provide the usage and trace data without application-code changes.

### How does showback help teams beyond assigning them a bill?

It can reveal inefficient allocations and model mismatches. In the example, HR’s repeated prompting indicated that its assigned model was a poor fit; access to higher-quality models reduced token consumption while improving the team’s experience.

### What can the demo show, and how quickly can it run?

On OpenShift AI 3.4 or later, the demo can display per-department cost attribution through Perses and MLflow after configuring the environment and generating traffic. The post says the demo runs in about five minutes and includes prompt sets, a Kubernetes Job deployment, and a presenter walkthrough.

**Tags:** [Kubernetes](https://yomu.fyi/topic/kubernetes), [MLflow](https://yomu.fyi/topic/mlflow), [OpenShift AI](https://yomu.fyi/topic/openshift-ai), [Prometheus](https://yomu.fyi/topic/prometheus)

- Source: [Red Hat](https://developers.redhat.com/articles/2026/09/18/what-did-ai-cost-you-this-quarter)
- Source URL: https://developers.redhat.com/articles/2026/09/18/what-did-ai-cost-you-this-quarter
- Ingested by Yomu: 2026-09-18T15:00:13.589Z

[Read original post](https://developers.redhat.com/articles/2026/09/18/what-did-ai-cost-you-this-quarter)