---
title: "Red Hat AI Inference 3.5 MaaS governance on AKS"
description: "Red Hat AI Inference 3.5 extends its Model-as-a-Service (MaaS) governance layer to non-OpenShift Kubernetes distributions, including Azure Kubernetes Service (AKS). MaaS adds multi-tenant API governance on top of the inference platform, controlling authentication, rate limiting, and model access via Authorino and Limitador from Red Hat Connectivity Link (Kuadrant). A model is first deployed with a single LLMInferenceService YAML, creating a vLLM server and router-scheduler, but the endpoint is open. Applying a MaaSSubscription and MaaSAuthPolicy activates governance: Authorino validates API keys or JWTs, and Limitador enforces token rate limits. The post demonstrates three enforcement scenarios on an AKS cluster with a T4 GPU running Qwen3-0.6B: 401 for missing or invalid keys, 200 for authenticated requests, and 429 when rate limits are exceeded, blocking requests before they reach vLLM."
---

# Red Hat AI Inference 3.5 MaaS governance on AKS

[Red Hat](https://yomu.fyi/company/red-hat) · clobner · Oct 13, 2026

**Type:** Tutorial

## Summary

Red Hat AI Inference 3.5 extends its Model-as-a-Service (MaaS) governance layer to non-OpenShift Kubernetes distributions, including Azure Kubernetes Service (AKS). MaaS adds multi-tenant API governance on top of the inference platform, controlling authentication, rate limiting, and model access via Authorino and Limitador from Red Hat Connectivity Link (Kuadrant). A model is first deployed with a single LLMInferenceService YAML, creating a vLLM server and router-scheduler, but the endpoint is open. Applying a MaaSSubscription and MaaSAuthPolicy activates governance: Authorino validates API keys or JWTs, and Limitador enforces token rate limits. The post demonstrates three enforcement scenarios on an AKS cluster with a T4 GPU running Qwen3-0.6B: 401 for missing or invalid keys, 200 for authenticated requests, and 429 when rate limits are exceeded, blocking requests before they reach vLLM.

## Context

The post addresses the governance challenge of securing AI model endpoints, authenticating developers, and preventing runaway GPU costs on public cloud Kubernetes clusters. It builds on a previous article about Red Hat AI Inference’s inference layer on non-OpenShift managed Kubernetes (xKS) and focuses on the MaaS governance layer deployed on Azure Kubernetes Service (AKS) with a cluster of 4 nodes (3 CPU, 1 GPU with NVIDIA T4) running Kubernetes 1.34.8.

## Approach / What changed

Deploy Red Hat AI Inference 3.5 with MaaS enabled on AKS. Install the governance layer components: RHCL/Kuadrant (Authorino for authentication, Limitador for rate limiting), MaaS controller, MaaS API, and MaaS gateway. Deploy a model using the LLMInferenceService CRD. Then apply a MaaSSubscription to define access tiers and a MaaSAuthPolicy to require API key authentication. The MaaS controller reconciles these CRDs into Kuadrant AuthPolicies and RateLimitPolicies. API keys are minted via the MaaS API using Kubernetes service account tokens.

## Takeaways

- MaaS governance on AKS requires external tools like Helm, cert-manager, and an OIDC provider (Azure AD) because vanilla Kubernetes lacks OpenShift’s built-in OLM, CA, and OAuth server.
- Without MaaSSubscription and MaaSAuthPolicy, the model endpoint is open to anyone; applying these two YAML files activates authentication and rate limiting.
- Rate limiting is enforced by Limitador at the gateway before requests reach vLLM, preventing wasted GPU compute on rejected requests.

## FAQ

### What happens if I call the MaaS gateway without an API key?

The request returns 401 Unauthorized because Authorino rejects requests without a valid API key or JWT.

### How do I obtain an API key for MaaS?

Authenticate with a Kubernetes service account token (e.g., \`kubectl create token default -n models-as-a-service\`) and call the MaaS API endpoint \`/v1/api-keys\` with the token to mint a one-time \`sk-oai-\*\` key.

### What is the difference between the inference gateway and the MaaS gateway?

The inference gateway serves models directly without authentication; the MaaS gateway adds policy enforcement (authentication and rate limiting) and uses a different path format (\`/v1/chat/completions\` with namespaced model identifier).

**Tags:** [AI Governance](https://yomu.fyi/topic/ai-governance), [AKS](https://yomu.fyi/topic/aks), [Kubernetes](https://yomu.fyi/topic/kubernetes), [Rate Limiting](https://yomu.fyi/topic/rate-limiting), [Red Hat AI](https://yomu.fyi/topic/red-hat-ai)

- Source: [Red Hat](https://developers.redhat.com/articles/2026/10/13/red-hat-ai-inference-3-5-maas-governance-aks)
- Source URL: https://developers.redhat.com/articles/2026/10/13/red-hat-ai-inference-3-5-maas-governance-aks
- Ingested by Yomu: 2026-10-13T15:00:16.784Z

[Read original post](https://developers.redhat.com/articles/2026/10/13/red-hat-ai-inference-3-5-maas-governance-aks)