Saturn Cloud has announced that it has built support for NVIDIA DSX OS into its platform. Saturn Cloud packages NVIDIA DSX OS, which provides inference serving, scheduling, and fleet operations, together with its own tenant, metering, and billing layer, so neocloud operators can run a production inference service on NVIDIA infrastructure without assembling the stack themselves.
Saturn Cloud integrates NVIDIA DSX OS with tenant metering and billing.
Runs NVIDIA Dynamo for inference, KAI Scheduler for GPU-aware scheduling, and Fleet Intelligence for health monitoring.
Adds per-token metering, quotas, and billing per tenant.
Supports dedicated single-tenant and shared multi-tenant serving.
Deploys across public cloud, private cloud, and on-premises.
Available now for AI cloud operators to evaluate.
NVIDIA DSX OS gives an operator the building blocks for inference, scheduling, and fleet operations, from NVIDIA Dynamo and NVIDIA Grove to KAI Scheduler, NVSentinel, and Fleet Intelligence. Neoclouds are seeking a commercial layer on top: the per-token metering, per-tenant billing, and chargeback that turn served tokens into something an operator can price and sell. That layer is inherently the operator's to build, and it is the part Saturn Cloud provides. Saturn Cloud runs NVIDIA Dynamo as the distributed inference and serving layer, with disaggregated prefill and decode, while NVIDIA Grove orchestrates multi-node workloads and NVIDIA KAI Scheduler places workloads with GPU awareness.
Saturn Cloud runs an operator's open and partner models in production on a single, production-grade control plane that's versioned and managed. Customers fine-tune on the operator's own infrastructure and serve the results alongside the base models. Operators serve each model the way the workload demands with dedicated single-tenant for isolation or shared multi-tenant for density, and Saturn Cloud handles the tenant boundary, quotas, and per-tenant metering either way. Data and inference stay inside the operator's boundary under the security and governance controls that regulated customers require. Usage is tracked per tenant against quotas, so faster hardware and better utilization turn into margin rather than a lower hourly rate.
"NVIDIA DSX OS gives AI cloud operators a strong foundation for serving models," said Sebastian Metti, founder of Saturn Cloud. "We add the piece that lets them turn it into a service they can sell to their own customers, instead of just renting out GPU hours."
"AI factories are moving into production, and operators are looking to expand their offerings with value-added services," said Warren Barkley, vice president of product management at NVIDIA. "Saturn Cloud's integration with NVIDIA DSX OS, including per-token metering and tenant billing, gives customers AI production-ready services customers want, without the complexity of assembling and integrating the stack themselves."
About Saturn Cloud
Saturn Cloud is the AI token factory platform for AI clouds and enterprises. It turns GPU infrastructure into managed services for fine-tuning, model serving, and per-token billing. Enterprise security and governance are built in, across public, private, and on-premises environments. Saturn Cloud is an NVIDIA portfolio company.
