Skip to main content
Serverless AI is a Nebius AI Cloud service for running containerized AI workloads as interactive Devlabs for coding, jobs that are executed to completion, or endpoints that serve the users. By deploying your workloads in Serverless AI, you can focus on them without worrying about the infrastructure: the service handles resource provisioning and lifecycle, and usage-based, per-second billing. The service is available in all Nebius AI Cloud regions except for eu-north2, eu-south1 and us-north1.

About Serverless AI

Read about how Serverless AI works and how to choose between Devlabs, endpoints and jobs

Getting started with Devlabs

Deploy JupyterLab on your first Devlab and connect to it

Getting started with jobs

Create your first job that runs nvidia-smi and prints information about GPUs in use

Getting started with endpoints

Launch a simple endpoint and send authenticated requests to it

Deploying an LLM

Deploy a large language model on an endpoint and chat with it

Fine-tuning an LLM

Run a job that fine-tunes a large language model by using Axolotl

Monitoring

Track resource utilization to schedule quota increases and to quickly identify anomalies