Nebius AI Cloud documentation
Explore what Nebius AI Cloud has to offer, and learn how to make the most out of its resources and address any potential issues.
Getting started
Everything you need to deploy, scale and manage your applications on Nebius AI Cloud.
Sign up
Create your account and get started with Nebius AI Cloud in minutes
Host a model
Deploy and run your AI models on high-performance VMs with GPU support
Deploy a Kubernetes cluster
Set up and manage scalable Kubernetes clusters for containerized workloads
Launch a container virtual machine
Run Docker containers directly on virtual machines with full control
Platform services
All cloud infrastructure services to build, deploy, and scale your applications.
Compute
Virtual machines
Cloud-hosted VMs with NVIDIA GPU support for ML/AI workloads
GPU clusters
InfiniBand™ networks for high-speed distributed computing
Soperator clusters
Slurm workload manager clusters for ML/AI experiments
Kubernetes clusters
Containerized application deployment with support for GPUs and InfiniBand
Disks and shared filesystems
Block and file storage for Compute VMs and Managed Kubernetes nodes
Storage
Object Storage buckets
AWS S3-compatible storage for ML/AI datasets and model artifacts
PostgreSQL® clusters
Database clusters for ML/AI datasets and application data
Container Registry
Docker image storage and distribution for containerized workloads
AI services
Serverless AI
Endpoints and jobs that run your containerized AI workloads
MLflow clusters
Managed clusters for experiment tracking and model registry
Applications
Turnkey applications for ML/AI workflows: JupyterLab®, vLLM, Open WebUI, etc.
Third-party integrations
Tools to run and orchestrate AI workloads on the Nebius AI Cloud infrastructure
Observability
Metrics and alerts
Metrics visualization and threshold-based alerting for resources
Logs
Log collection, search, export and custom ingestion
Traces
Distributed tracing for application performance monitoring
Network
Virtual Networks
Private networks, subnets, security groups, routing and site-to-site VPN
Nebius Tunnels
Public access to local services without opening firewall ports
Overview and management
Signup
Account creation and billing setup for individuals and companies
Billing
Payment methods, invoices, taxes and discounts
Identity and Access Management (IAM)
Centralized management of users, service accounts and permissions
Quotas
Resource limits with workflows to request increases
Support
Submitting technical support tickets, bug reports and feature requests
Regions
Locations where Nebius AI Cloud hosts resources and data
Digital rights
Data portability and data deletion in compliance with the EU GDPR and Data Act
Changelog
New features and updates to Nebius AI Cloud services
Security and cryptography
Audit Logs
User and service activity records for security and compliance
Key Management Service
Cryptographic keys for data encryption and decryption
SecretStash (formerly MysteryBox)
Secrets for storing and reusing sensitive keys and tokens
Tutorials
Tutorials
Step-by-step tutorials to build solutions with services and applications
Developer tools
CLI
Managing resources in the command line
Provider for Terraform
Declarative approach to resource management
gRPC API
Programmatic resource management over HTTP/2 with Protocol Buffers
REST API
Programmatic resource management over HTTP with JSON
SDKs
Client libraries for Go, Python and JavaScript
Agent Resources
Resources to use AI agents with Nebius documentation