AI cloud and model platform
How to use
Nebius AI.
Evaluating and serving open models through managed APIs or dedicated endpoints, and running controlled training and inference workloads on GPU VMs, containers, or Kubernetes.
Nebius AI is a AI cloud and model platform for managed inference, fine-tuning, serverless endpoints, and GPU infrastructure. Evaluating and serving open models through managed APIs or dedicated endpoints, and running controlled training and inference workloads on GPU VMs, containers, or Kubernetes. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Nebius AI
Get into the official Nebius AI experience with the right account and a setup you understand.
- 01
Start at https://nebius.com/ and confirm the domain before entering account or payment information.
- 02
Availability: Nebius is a browser-managed cloud service with console, CLI, SDK, gRPC, and OpenAI-compatible model APIs rather than a consumer desktop application.
- 03
A Nebius tenant and project, scoped credentials, approved region and data path, a licensed model, representative evaluation data, budget limits, and cloud security and operations ownership.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Nebius AI session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define the task, data class, region, model license, quality, safety, latency, context, throughput, retention, availability, cost, and rollback requirements.
- 02
Choose Token Factory or another managed endpoint for API inference, Serverless AI for a custom container, or GPU infrastructure only when the added operational control is justified.
- 03
Create least-privilege project credentials, pin the model or container revision, and run a versioned benchmark with representative inputs, bounded outputs, usage, latency, and failure capture.
- 04
Review quality, safety, privacy path, license, performance, scaling, and total cost, then canary the selected deployment, monitor it, and retain a tested fallback and deletion plan.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Nebius AI output
Establish that a change is safe to run in production and reversible if it is not.
- 01
Restate the intended end state and the blast radius before applying anything.
- 02
Review the generated configuration line by line against the provider's current documentation.
- 03
Apply to a non-production environment first and confirm the observed result matches the intended one.
- 04
Confirm the rollback path works by actually exercising it, not by assuming it exists.
- 05
Check cost, scaling limits, and network exposure before the change reaches production traffic.
- Test the rollback, do not assume it.
- Check what a configuration exposes to the public internet.
- Watch cost and rate limits as closely as correctness.
Privacy & permissions
Use Nebius AI safely
Keep credentials, network exposure, and cost under deliberate control.
- 01
Use scoped, short-lived credentials, and never paste production secrets into a prompt or config file.
- 02
Confirm what each change exposes publicly before applying it, especially storage, databases, and admin endpoints.
- 03
Separate environments so a mistake in development cannot reach production data.
- 04
Set billing alerts and hard quotas before enabling autoscaling or usage-based services.
- 05
Review audit logs and revoke access for integrations that are no longer in use.
- OpenAI-compatible endpoints preserve familiar request shapes, not identical model behavior, moderation, licensing, or reliability. Treat cloud projects, secrets, networks, images, datasets, logs, and GPU resources as separate security boundaries; pin versions, restrict ingress and roles, encrypt data, set quotas, verify region and retention, and delete idle endpoints, disks, and credentials.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Nebius AI for the work it does best.
Each workflow below has its own outcome, steps and review checkpoints.
Evaluate an exact managed model on the real task before relying on a familiar API shape or moving production traffic.
↓ 02 WorkflowOperate a secure Nebius GPU inference workloadDeploy a custom model with explicit project, network, image, secret, scaling, storage, and teardown controls.
↓Workflow 01
Benchmark and integrate a Nebius managed model
Evaluate an exact managed model on the real task before relying on a familiar API shape or moving production traffic.
Outcome: Select a licensed, pinned model with measured quality, safety, latency, cost, and a tested fallback.
- 01
Define users, task, languages, data class, success and failure metrics, safety, schema, context, latency, traffic, retention, region, license, cost, and rollback limits.
- 02
List current models and record exact IDs, capabilities, licenses, context, pricing, rate limits, supported parameters, lifecycle state, and dedicated-endpoint options.
- 03
Create a project-scoped key, keep it server-side, and run a frozen representative set with equal prompts, bounded output, captured usage, errors, latency, and repeat trials.
- 04
Score correctness, grounding, safety, refusals, bias, schema validity, tail latency, failure rate, privacy path, and task cost, investigating item-level regressions.
- 05
Pin the winner and fallback, add rate and budget controls, canary the integration, monitor model changes, and rerun the benchmark before any migration.
What good use looks like
- Record exact model IDs and licenses.
- Measure task cost and tail latency.
- Never silently switch models.
Workflow 02
Operate a secure Nebius GPU inference workload
Deploy a custom model with explicit project, network, image, secret, scaling, storage, and teardown controls.
Outcome: Run reproducible inference without exposing credentials, datasets, management surfaces, or unbounded cloud spend.
- 01
Define model and data rights, region, endpoint contract, GPU and memory needs, threat model, ingress, storage, scaling, observability, SLO, budget, and teardown evidence.
- 02
Separate environments and roles, create scoped service credentials, restrict network access, encrypt storage, pin the image and model digest, and scan dependencies before deployment.
- 03
Deploy privately with explicit health checks, timeouts, concurrency, replica bounds, secret mounts, non-sensitive logs, quotas, and no unnecessary management or shell exposure.
- 04
Load-test cold start, queueing, autoscaling, memory, malformed input, model failure, key rotation, regional failure, output parity, privacy, and cost under representative traffic.
- 05
Canary changes, retain a prior deployment and recovery manifest, export approved outputs, delete retired endpoints and disks, revoke credentials, and reconcile billing.
What good use looks like
- Pin images and model revisions.
- Restrict ingress and project roles.
- Verify teardown and stopped billing.
Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.
- Nebius AI Cloud documentation ↗
- Serverless AI model tutorial ↗
- Token Factory API introduction ↗
- Nebius inference API reference ↗