Saturn Cloud의 AI 토큰 팩토리가 vCluster 스택에 도입되어 AI 클라우드 GPU를 토큰 기반 수익으로 전환

With a Saturn Cloud Stack, every new customer's inference service is a single deployment, running in an isolated tenant cluster on the operator's own GPUs. NEW YORK, Oct. 14, 2026 /PRNewswire/ -- Saturn Cloud, the AI token factory platform, and vCluster Labs, the platform operators use to build and run their own AI cloud like a hyperscaler, today announced a partnership to help AI clouds sell managed, per-token inference on their own GPUs. As a first step, Saturn Cloud is coming to vCluster Stack, a single, reusable, pre-validated deployment template that installs the Saturn Cloud platform inside an isolated tenant cluster. The partnership gives AI cloud providers a repeatable way to launch a managed inference service, where each customer gets their own isolated environment and per-token endpoints on the operator's GPUs. This follows Saturn Cloud's integrations with NVIDIA DSX OS and NVIDIA Run:ai, which give operators on NVIDIA infrastructure the same managed platform without building it themselves. "The neoclouds we talk to want to sell inference without reinventing how they isolate each customer," said Sebastian Metti, founder and CEO of Saturn Cloud. "With Saturn Cloud as a vCluster Stack, our token factory, fine-tuning, and per-token billing deploy straight into a tenant the operator already trusts. One deployment instead of a custom integration for every customer." Saturn Cloud Sells the Tokens, vCluster Isolates Each Customer, Stacks Repeats at Scale Saturn Cloud turns GPUs into per-token inference customers can call. Operators get per-token endpoints, fine-tuning, and usage billing in a self-service portal under their own brand. Inference is the first Stack, and the same platform also runs dedicated GPU capacity, managed fine-tuning, and distributed training on the same fleet. vCluster gives every customer an isolated cluster of its own. Each customer gets its own tenant cluster with a virtualized control plane. With Private Nodes, each tenant also runs on dedicated nodes, with network, storage, and compute isolated per tenant. Stacks packages the whole environment so it deploys the same way every time. The Saturn Cloud Stack describes what to install, in what order, and what must be healthy before the next step. Each deployment becomes its own managed environment, with its own health status, logs, and clean removal. One Deployment for Launching Managed Inference Consider an AI cloud that wants to offer enterprise customers private inference. With vCluster and Saturn Cloud, the workflow is straightforward. The operator creates the customer's tenant cluster on Private Nodes, running on GPU servers they already own. They deploy the Saturn Cloud stack into it, and the customer can start calling per-token endpoints. Onboarding the next customer follows the same automated process, consistent every time.