Modelplane v0.5: an AI gateway and fleet telemetry

Modelplane released version 0.5, turning its fleet gateway into an AI gateway built on Agent Router that authenticates callers, reads the model named in each request body, and fails over between backends using new priority settings alongside weight. The release adds an OpenTelemetry collector on every inference cluster that renames engine-specific series such as vLLM's `vllm:num_requests_waiting` and SGLang's `sglang:num_queue_reqs` into a single `modelplane_*` vocabulary, with `TelemetryDestination` and `MetricMapping` resources controlling where metrics go and how units convert. Modelplane 0.5 also lets a `ModelDeployment` scale to zero replicas and adds Civo to the clouds it can provision an `InferenceCluster` on, joining EKS, AKS, GKE, Nebius and Vultr.

Modelplane v0.5 is out. The fleet gateway is now an AI gateway. It authenticates callers and reads the model a request asks for, then fails over between the backends that serve it. Modelplane also collects your fleet's metrics under one set of names, whatever engine produced them. And Civo joins the clouds Modelplane can provision a cluster on. A ModelDeployment can also scale to zero replicas now, so one you aren't serving from costs you no GPUs. Here's what's new. The fleet gateway is an AI gateway the-fleet-gateway-is-an-ai-gateway The fleet gateway used to be an HTTP router on the control plane. It understood nothing about the requests it forwarded. A caller reached a ModelService by path prefix, nothing authenticated them, and the hop out to each cluster crossed the public internet in plain HTTP. It's now Agent Router https://theagentrouter.ai/ , running on an InferenceCluster you name rather than on the control plane, and the same one every cluster already runs at its edge. We run a build from before the project left the Envoy family and took that name, so you'll still see envoy-ai-gateway-system on a cluster. It reads the model a request names in its body and resolves the ModelService that serves it. For the backend it picks, it rewrites the model name, the credential and the path, so a backend sees the name it knows and a caller's key never reaches a third party. ModelService gains priority alongside weight . Weight splits traffic between backends at one priority; priority fails over to the next when they go unhealthy. Every request meters a token count per caller, streams included. You can now run more than one InferenceGateway . Each names the cluster it runs on, so a fleet can have one per region for residency, or two in a region for availability: Traffic from a fleet gateway to a cluster gateway is now mutually authenticated and encrypted. It used to cross the public internet as plain HTTP. One vocabulary for a fleet's metrics one-vocabulary-for-a-fleets-metrics Modelplane doesn't own your engine. You bring the image and the command, and a ModelDeployment runs vLLM, SGLang, or anything else that speaks the OpenAI API, without Modelplane knowing anything about it. That freedom is what makes a fleet hard to watch. vLLM publishes vllm:num requests waiting . SGLang calls the same measurement sglang:num queue reqs . DCGM https://developer.nvidia.com/dcgm , NVIDIA's GPU exporter, reports framebuffer memory in mebibytes under a name that says bytes, and energy in millijoules under a name that says joules. A dashboard written against one engine is wrong on the next, and a fleet running both has no fleet-wide number at all. Standardising on one engine would cost you the choice that made Modelplane worth using, so Modelplane normalises the names where it collects them instead. Modelplane now runs an OpenTelemetry collector on every inference cluster. It discovers every component Modelplane installs, renames each one's series into a single modelplane vocabulary, and exports them wherever you say. Two new kinds. A TelemetryDestination says where metrics go, and nothing is collected until one exists: A MetricMapping says what a component emits and what Modelplane calls it. Modelplane comes with mappings for vLLM, SGLang, the gateway, the endpoint picker and DCGM, so those need nothing from you. Write one for an engine Modelplane has never seen and its numbers join the same surface: fromUnit is the one to get right. A metric's name is no guide to its unit, so the mapping says what the source measures in and Modelplane converts, histogram buckets and all. Skip it and a series named seconds holding milliseconds reads a thousand times fast, with nothing downstream to catch it. Civo civo Civo https://www.civo.com/ joins EKS, AKS, GKE, Nebius and Vultr as a cloud Modelplane can provision an InferenceCluster on, with the same spec you'd write for any of them. Two things about Civo needed handling underneath. Its GPU images carry no NVIDIA driver, so the serving stack installs the GPU Operator to supply one, with the toolkit and device plugin switched off so the DRA driver stays the only thing allocating GPUs. And Civo has no server-side autoscaler, so a pool with a maxNodeCount is scaled by the upstream cluster-autoscaler running on the cluster itself. Civo's volumes are ReadWriteOnce, so ModelCache isn't available there yet. Scaling to zero scaling-to-zero A ModelDeployment can now scale to zero replicas. spec.replicas used to carry a floor of one, so kubectl scale --replicas=0 was rejected at admission. That is awkward when scaling to zero is most of the reason to put KEDA in front of a GPU workload in the first place. There was no way to park a deployment either: withdrawing its endpoints while keeping the object meant tainting the cluster hosting it. Dropping the floor on its own would have made a parked deployment look broken. Zero desired replicas against an empty schedule reads as none of them scheduled, and on a control plane with no clusters it reads as having nowhere to run, so a deployment you had deliberately parked would sit there permanently not ready. Zero now takes a path of its own. Nothing is composed, so the deployment's ModelReplicas and ModelEndpoints are pruned, status.replicas reports 0 to the scale subresource, and readiness reports true with a ScaledToZero reason, the way a Deployment at zero replicas still reports Available. A parked deployment reads as parked rather than as failing, which is what makes it safe for an autoscaler to do on your behalf. Try it try-it The getting-started guide https://docs.modelplane.ai/getting-started/ covers standing up a fleet, and Monitor the Fleet https://docs.modelplane.ai/platform/telemetry/ covers pointing telemetry at a backend you already run. Modelplane is Apache 2.0 and moving fast at github.com/modelplaneai/modelplane https://github.com/modelplaneai/modelplane , and questions are welcome in Slack https://slack.modelplane.ai .