Serverless AI
Nebius AI Cloud's on-demand GPU runtime that runs containerised AI workloads as Jobs and hosts custom models behind HTTP Endpoints without provisioning or managing clusters.
Find alternatives to Serverless AI
What it does
- Model inference
- Model hosting
- GPU cloud
Features 3
- DevlabsInteractive dev environments with preinstalled tools like Jupyter and VS Code.
- JobsRuntime for executing containerized finite workloads that start, run and complete.
- EndpointsInference environment for deploying custom models behind HTTP endpoints.
Sources
- Pricing
-
Official documentation · 6 Sep 2026
'Serverless AI does not have its own quotas and pricing; the service applies the quotas and pricing of Compute.' Endpoints and jobs count toward Compute VM quotas and billing.
- Sold within
-
Official documentation · 6 Sep 2026
Explicitly has no independent quota or price and bills through AI Cloud Compute; reachable only from the Nebius console. No standalone signup or separate checkout exists.
- URL
-
Official documentation · 6 Sep 2026
Title 'Serverless AI on Nebius | Run GPU Workloads On Demand', H1 'Run AI workloads, skip the infrastructure'. Own page under the Products nav; independently re-fetched.
- Interfaces
-
Official documentation · 12 Oct 2026
Page: 'by creating an account via the Nebius web console or CLI'.
Also from Nebius Group
-
Nebius AI Cloud Infrastructure service
Rented GPU clusters with storage and networking for training and serving models, billed by the GPU-hour.
-
Nebius Token Factory Model API
Managed inference endpoint serving open-weight models on Nebius hardware, billed per token.
-
Managed Soperator Infrastructure service
Nebius-managed Kubernetes operator that runs Slurm clusters on GPU infrastructure for fault-tolerant large-scale AI training, with topology-aware scheduling and automatic node health checks and recovery.
-
Managed Service for MLflow Developer tool
Fully managed MLflow deployment on Nebius AI Cloud for tracking experiments, metrics and artifacts across the machine-learning lifecycle without maintaining tracking-server infrastructure.
Open Nebius Group in the directory
Something wrong here? Send a correction — quote this product id: nebius-serverless-ai.