Nscale Launches Serverless Inference Platform for Instant AI Access

Nscale, Europe’s AI hyperscaler, announced the launch of its Serverless Inference Platform, a new public, on-demand cloud service that enables developers and businesses to quickly deploy leading AI models at scale—without the complexity of managing infrastructure.

This marks Nscale’s first public offering within its broader AI infrastructure suite, complementing its existing private cloud solutions designed for large-scale enterprise workloads.

With a token-based, pay-as-you-go model, the Serverless Inference Platform offers cost-effective access to compute resources, automatically provisioning capacity across users to ensure consistent performance. By removing idle infrastructure costs, the platform lowers financial barriers for deploying and experimenting with generative AI.

“Launching our Serverless Inference Platform marks Nscale’s expansion into public, on-demand AI services, making AI model deployment simple and cost-effective,” said Daniel Bathurst, Chief Product Officer at Nscale. “While our private cloud remains ideal for large enterprise workloads, this new serverless option enables more developers to experiment with and scale inference workloads. With upcoming features set to include dedicated endpoints, fine-tuning capabilities and the ability to support custom model hosting, we're proud to offer sovereign, European AI infrastructure to meet rapidly growing inference demand.”

Key Platform Features:

• Cost-efficient compute: Users only pay for the resources they use via a flexible token system.

• Immediate access: Popular models including Meta’s Llama, Alibaba’s Qwen, and DeepSeek through OpenAI-compatible APIs or via Nscale’s intuitive web console are available instantly.

• Developer-friendly tools: OpenAI-compatible APIs and a user-friendly web console cater to both technical and non-technical users.

• Enterprise-grade functionality: Integrated orchestration tools (Slurm, Kubernetes), observability, and multi-tenant security ensure reliable performance and compliance.

The platform sets the stage for upcoming enhancements, including dedicated endpoints, fine-tuning capabilities, and custom model hosting.

Users can register now to start deploying AI models directly through the Nscale ecosystem.

About Nscale

Nscale is the AI hyperscaler for Europe, delivering scalable compute infrastructure to the generative AI market. Its fully integrated AI platform operates from a 60MW renewable-powered data centre in Norway, with over 1.3GW of greenfield capacity in development across Europe and North America. Nscale enables customers to run efficient and scalable AI training, fine-tuning, and inferencing workloads.

What This Means

The launch of Nscale’s Serverless Inference Platform positions the company as a flexible alternative in the AI infrastructure space—bridging enterprise-grade performance with ease of access for smaller teams and developers. With its European footprint and commitment to sustainable compute, Nscale is stepping into the growing demand for accessible, sovereign AI solutions.

Editor’s Note: This article is based on an official press release issued by NScale and has been adapted by AiNews.com for clarity and context. The original release can be found on the company’s website.