Nebius
by Nebius Group N.V. · nebius.com ↗
AI cloud platform for workloads from training through inference, with NVIDIA GPU instances billed per GPU-hour, managed Kubernetes and Slurm, and token-based inference services.
cloud gpu inference kubernetes infrastructure
- Category
- Platforms & Infrastructure
- Business model
- Paid
- Availability
- Global
- Launched
- 2024
- Record updated
- 2026-09-10
- Pricing
- nebius.com ↗
- Documentation
- docs.nebius.com ↗
- Founded
- 2024
- Headquarters
- NL
- Canonical URL
- https://globalaiproductindex.com/products/nebius/
Overview
Nebius Group N.V. (Nasdaq: NBIS) is an AI cloud company headquartered in Amsterdam, Netherlands, renamed from Yandex N.V. in 2024; the predecessor Yandex dates to 1997. Its AI cloud opened publicly on April 30, 2024 and supports workloads from training through inference, with NVIDIA GPU instances billed per GPU-hour on on-demand and preemptible terms, managed Kubernetes and Slurm, and serverless and managed inference with MLOps tooling. Object storage and networking services are also offered, and inference can be billed on a token basis through Token Factory. Pricing is usage-based, with some services listed as free and promo credits available, but no general free tier.
Key features
- NVIDIA GPU instances billed per GPU-hour, on-demand and preemptible
- Managed Kubernetes and Slurm for orchestration
- Serverless and managed inference with MLOps tooling
- Token-based inference pricing through Token Factory
- Object storage and networking services
Use cases
- Training and fine-tuning models on GPU clusters
- Running production inference for AI applications
- Scaling containerized workloads with managed Kubernetes or Slurm
Pricing
Pricing is usage-based: GPU compute per GPU-hour, plus storage and networking, with token-based inference on Token Factory. Some services are listed as free and promo credits are available, but there is no general free tier.
Frequently asked questions
Where is Nebius based?
Nebius Group N.V. is headquartered in Amsterdam, Netherlands. The company was renamed from Yandex N.V. in 2024.
When did the Nebius AI cloud open?
The Nebius AI cloud opened publicly on April 30, 2024.
How is Nebius billed?
Compute on GPU instances is billed per GPU-hour, storage is charged separately, and inference is billed on a token basis through Token Factory.
Similar products
- Aleph Alpha — German AI company that builds sovereign large language models and enterprise AI platforms for industry, public-sector, and defense customers.
- Amazon Bedrock — Managed AWS service for building applications with foundation models from multiple providers via one API.
- Amazon Nova — AWS portfolio of Amazon-built foundation models and services for text, multimodal, speech, custom model building, and UI-automating agents.
- Baseten — Platform for deploying and serving machine-learning models as scalable APIs.
- Cerebras — AI compute company whose inference cloud serves open language models on wafer-scale hardware.
- Civitai — Community platform for sharing and discovering open image-generation models, LoRAs, and generated art.
All Nebius alternatives → · All Platforms & Infrastructure products →
Sources
This record was last reviewed on 2026-09-10.
Machine-readable record: /api/products/nebius.json · Spot an error? Suggest a correction