CCloud Releases
Home
Following

Cloud Releases

Service catalogues and updates come from each provider's public product listing and announcements.

Explore

  • Home
  • Latest updates
  • Following

About

  • About
  • Contact
  • Privacy Policy
  • Terms of Use

Providers

  • Amazon Web Services
  • Microsoft Azure
  • Google Cloud
  • Cloudflare

Not affiliated with any cloud provider. Product names and logos belong to their owners.

  1. Providers
  2. ›Microsoft Azure
  3. ›Azure Kubernetes Service (AKS)
  4. ›Update

Preview•Jun 24, 2026

Public Preview: Application Gateway for Containers – Inference gateway

Azure Kubernetes Service (AKS)Azure · Compute

Application Gateway for Containers is extending its ingress gateway feature set with new AI gateway capabilities. The new inference gateway capability brings the Kubernetes Gateway API Inference Extension to Application Gateway for Containers, enabling load and model-aware routing for self-hosted generative AI workloads on AKS.

Application Gateway for Containers' inference gateway capability is purpose-built for serving LLMs and other inference workloads, routing requests based on model server signals rather than generic load balancing — improving Time to First Token (TTFT) and reducing timeouts under load.

  • Managed Body-Based Router (BBR): A fully managed router that inspects the request body (such as the model field on OpenAI-compatible APIs) to drive model-aware routing — no custom proxy tier required.
  • Bring your own Endpoint Picker (EPP): Choose the EPP implementation that fits your workload to drive metrics-aware endpoint selection across your InferencePool.
  • Secure inference: Pairs natively with the existing web application firewall (WAF) capability in Application Gateway for Containers, applying OWASP-aligned protections to AI traffic before it reaches your model servers.
  • Improved performance and reliability: Routes around saturated replicas and leverages model server state to lower TTFT, reduce timeouts, and improve GPU utilization.

Learn more:

  • Application Gateway for Containers – AI gateway - Inference gateway
  • Application Gateway for Containers - Overview

Read the original announcement↗

More from Azure Kubernetes Service (AKS)

All Azure Kubernetes Service (AKS) updates →

  1. Generally Available: Managed StandardV2 NAT Gateway for AKS

    AKS will now provision and manage a StandardV2 NAT Gateway for clusters using an AKS-managed virtual network.

    Azure Kubernetes Service (AKS)•Generally available•Oct 8, 2026

  2. Generally Available: Anyscale on Azure

    Anyscale on Azure is now Generally Available. Anyscale on Azure is a managed platform for running distributed Python workloads on Ray. It deploys directly onto your Azure Kubernetes Service (AKS) cluster and integrates with the Azure services your team already uses.

    Azure Kubernetes Service (AKS)•Generally available•Oct 7, 2026

  3. Retirement: Pod name dimension in AKS pod platform metrics

    Beginning September 30, 2027, support for the pod name dimension on the following Azure Monitor platform metrics is retiring, and these metrics are transitioning to aggregate pod counters: Number of pods by phase (kube_pod_status_phase)

    Azure Kubernetes Service (AKS)•Deprecation•Oct 6, 2026

  4. Public Preview: AKS on bare metal now on Ubuntu

    Running Kubernetes on-premises often means adding a virtualization layer, adapting to unfamiliar infrastructure, or giving up control over the hardware and software your applications depend on.

    Azure Kubernetes Service (AKS)•Preview•Oct 6, 2026

  5. Public Preview: Ubuntu 26.04 support in AKS

    Teams running Ubuntu node pools on AKS need to stay current with Ubuntu LTS releases, but each OS transition can introduce package footprint, security, and compatibility concerns.

    Azure Kubernetes Service (AKS)•Preview•Sep 30, 2026