> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nebius.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI services in Nebius AI Cloud

Nebius AI Cloud offers AI services for containerized inference and training, experiment tracking, integrations with third-party software and orchestration with external tools.

Different services can help you achieve different goals:

* Use [Serverless AI](/serverless/overview) to run containerized AI workloads either as endpoints that return results immediately, or as background jobs that run in the background and stop when the task is complete.
* Use [Managed Service for MLflow](/mlflow) to manage machine learning experiments by tracking runs, organizing models into versions, comparing metrics and deploying customized models.
* Use [Applications in Nebius AI Cloud](/applications) to work with third-party software and services that help streamline AI and ML workflows.
* Use [third-party integrations](/3p-integrations) to run and orchestrate AI workloads in the Nebius AI Cloud infrastructure.

<CardGroup cols={2}>
  <Card title="Getting started with endpoints in Serverless AI" icon="link" href="/serverless/quickstart/endpoints">
    Deploy an interactive endpoint that listens for requests and returns results immediately
  </Card>

  <Card title="Getting started with jobs in Serverless AI" icon="link" href="/serverless/quickstart/jobs">
    Run a non-interactive workload in the background and stop it automatically after completion
  </Card>

  <Card title="Getting started with MLflow" icon="link" href="/mlflow/quickstart">
    Create your first MLflow cluster and run an experiment in it
  </Card>

  <Card title="Deploying applications" icon="link" href="/applications/deploy">
    Browse the marketplace and choose an application to deploy
  </Card>

  <Card title="Third-party integrations: SkyPilot" icon="link" href="/3p-integrations/skypilot">
    Run, manage and scale AI workloads on Nebius AI Cloud by using SkyPilot
  </Card>

  <Card title="Third-party integrations: Run:ai" icon="link" href="/3p-integrations/run-ai">
    Optimize your GPU resources for ML/AI workloads by using Run:ai and Managed Service for Kubernetes®
  </Card>
</CardGroup>

## Tutorials and examples

Follow our Serverless AI tutorials for step-by-step instructions on setting up specific AI workloads, or explore tutorials that combine multiple Nebius AI Cloud services to build complete solutions.

<CardGroup cols={2}>
  <Card title="Deploying a large language model and chatting with it" icon="link" href="/serverless/tutorials/deploy-model">
    Create your first Serverless AI endpoint with an open-source large language model and send a chat request
  </Card>

  <Card title="Fine-tuning a large language model" icon="link" href="/serverless/tutorials/fine-tuning">
    Fine-tune a large language model by using a Serverless AI job with Axolotl
  </Card>

  <Card title="Speech synthesis" icon="link" href="/serverless/tutorials/tts">
    Convert text to speech by creating a model, running a fine-tuning job and deploying an endpoint
  </Card>

  <Card title="Building solutions with AI services" icon="link" href="/tutorials">
    Explore tutorials that show you how to combine Nebius AI Cloud services to build complete solutions
  </Card>
</CardGroup>

<Card title="Serverless cookbook" icon="link" href="https://github.com/nebius/serverless-ai-cookbook" horizontal>
  Explore runnable examples of Serverless AI workloads on GitHub
</Card>