{"slug": "modelplane-v0-2-more-clouds-and-traffic-you-can-direct", "title": "Modelplane v0.2: more clouds, and traffic you can direct", "summary": "Modelplane released v0.2 of its open-source inference orchestration platform, adding support for Nebius and Azure AKS cloud providers, weighted request routing for canarying and traffic splitting, and cluster taints for capacity reservation and draining. The update aims to unify models, engines, clouds, and accelerators into a single controllable system, building on the project's initial launch three weeks ago.", "body_md": "Modelplane v0.2 is out. We open sourced the project three weeks ago, and since then we've had a lot of traction and some great discussions with people running inference. The mission driving each release is the same: Modelplane brings together the models, engines, clouds, and accelerators that make up the intelligence ecosystem so you can operate them as a single system under your control. And we are building this in the open.\n\nThis release adds two more cloud providers, weighted request routing, and cluster taints for reserving and draining capacity. Here's what's new.\n\n## More providers[#](#more-providers)\n\nAt launch, Modelplane provisioned inference clusters on GKE and EKS, or ran on any\nKubernetes you brought yourself. v0.2 adds two more providers, [Nebius](https://nebius.com) and\n[Azure AKS](https://azure.microsoft.com/en-us/products/kubernetes-service). A Nebius\ncluster is about as much YAML as it sounds like it should be. You name it, point it at\nNebius, and Modelplane provisions the rest from the credentials you already configured:\n\nBoth work the same way as GKE: an `InferenceClass`\n\ndescribes the hardware, an\n`InferenceCluster`\n\nprovisions it, and the same `nodePools`\n\nmodel applies. On GKE, the\nGPU node pools Modelplane creates now cold-start from zero, so an idle pool stops\nbilling you when nothing is running on it.\n\nYou can also still bring your own cluster on any Kubernetes, on any cloud or on-prem,\nfor providers Modelplane doesn't provision yet. If you want a provisioner for a\nparticular cloud, upvote or open an\n[issue](https://github.com/modelplaneai/modelplane/issues).\n\n## Weighted routing[#](#weighted-routing)\n\nA `ModelService`\n\ncan now split traffic across its endpoints by weight:\n\nWeights are relative, and an endpoint with no weight defaults to 1. The endpoint stays fixed while you change the split, which covers canarying a new model version, shifting traffic between two deployments, and splitting between a hosted provider and your own deployment. Weights are the first step here, and there's a lot more routing functionality on the way.\n\n## Taints and draining clusters[#](#taints-and-draining-clusters)\n\nv0.2 also lets you decide which clusters take work, using the same taints and\ntolerations that Kubernetes already uses for nodes, lifted up to the cluster. You taint\nan `InferenceCluster`\n\n, and only models that tolerate the taint will schedule onto it:\n\nThis is useful for keeping a sovereign cluster, or one with scarce hardware, for the workloads that need it. A deployment opts in with a matching toleration under its template:\n\nThe same mechanism drains a cluster. Taint it with `NoExecute`\n\ninstead of `NoSchedule`\n\nand Modelplane moves the running replicas off onto other clusters in the fleet, so you\ncan take a cluster out for maintenance without hand-migrating what's on it. Remove the\ntaint and it takes work again.\n\nThe full release notes are on\n[GitHub](https://github.com/modelplaneai/modelplane/releases/tag/v0.2.0), and the\n[getting-started guide](https://docs.modelplane.ai/getting-started/) now covers\ndeploying on AKS and Nebius. Questions and feedback are welcome in\n[Slack](https://slack.modelplane.ai).", "url": "https://wpnews.pro/news/modelplane-v0-2-more-clouds-and-traffic-you-can-direct", "canonical_source": "https://modelplane.ai/blog/modelplane-v0-2", "published_at": "2026-07-16 00:00:00+00:00", "updated_at": "2026-07-20 19:03:27.408692+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "developer-tools", "mlops"], "entities": ["Modelplane", "Nebius", "Azure AKS", "GKE", "EKS", "Kubernetes"], "alternates": {"html": "https://wpnews.pro/news/modelplane-v0-2-more-clouds-and-traffic-you-can-direct", "markdown": "https://wpnews.pro/news/modelplane-v0-2-more-clouds-and-traffic-you-can-direct.md", "text": "https://wpnews.pro/news/modelplane-v0-2-more-clouds-and-traffic-you-can-direct.txt", "jsonld": "https://wpnews.pro/news/modelplane-v0-2-more-clouds-and-traffic-you-can-direct.jsonld"}}