> ## Documentation Index
> Fetch the complete documentation index at: https://runpod-b18f5ded-public-endpoints.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Runpod

> Explore our guides and examples to deploy your AI/ML application on Runpod.

Runpod is a cloud computing platform built for AI, machine learning, and general compute needs. Whether you're running deep learning models, training AI, or deploying cloud-based applications, Runpod provides scalable, high-performance GPU and CPU resources to power your workloads.

## Get started

If you're new to Runpod, start here to learn the essentials and deploy your first GPU.

<CardGroup>
  <Card title="Quickstart" href="/get-started" icon="bolt" iconType="solid">
    Create an account, deploy your first GPU Pod, and use it to execute code.
  </Card>

  <Card title="Manage accounts" href="/get-started/manage-accounts" icon="users" iconType="solid">
    Learn how to manage your personal and team accounts and set up permissions.
  </Card>

  <Card title="Create an API key" href="/get-started/api-keys" icon="key" iconType="solid">
    Create API keys to manage your access to Runpod resources.
  </Card>

  <Card title="Connection options" href="/get-started/connect-to-runpod" icon="plug" iconType="solid">
    Learn about different methods for connecting to Runpod and managing resources.
  </Card>
</CardGroup>

## Serverless

Serverless offers pay-per-second serverless computing with built-in autoscaling for production workloads.

<CardGroup>
  <Card title="Introduction" href="/serverless/overview" icon="cloud" iconType="solid">
    Learn how Serverless works and how to deploy pre-configured endpoints.
  </Card>

  <Card title="Pricing" href="/serverless/pricing" icon="dollar-sign" iconType="solid">
    Learn how Serverless billing works and how to optimize your costs.
  </Card>

  <Card title="vLLM quickstart" href="/serverless/vllm/get-started" icon="cloud-bolt" iconType="solid">
    Deploy a large language model for text or image generation in minutes using vLLM.
  </Card>

  <Card title="Build your first worker" href="/serverless/workers/custom-worker" icon="code" iconType="solid">
    Build a custom worker and deploy it as a Serverless endpoint.
  </Card>
</CardGroup>

## Pods

Pods allow you to run containerized workloads on dedicated GPU or CPU instances.

<CardGroup>
  <Card title="Introduction" href="/pods/overview" icon="microchip" iconType="solid">
    Understand the components of a Pod and options for configuration.
  </Card>

  <Card title="Choose a Pod" href="/pods/choose-a-pod" icon="server" iconType="solid">
    Learn how to choose the right Pod for your workload.
  </Card>
</CardGroup>

## Support

<Columns cols={3}>
  <Card title="Contact" href="https://contact.runpod.io" icon="headset" iconType="solid">
    Submit a support request using our contact page.
  </Card>

  <Card title="Status page" href="https://uptime.runpod.io/" icon="chart-line" iconType="solid">
    Check the status of Runpod services and infrastructure.
  </Card>

  <Card title="Discord" href="https://discord.gg/cUpRmau42V" icon="discord">
    Join the Runpod community on Discord.
  </Card>
</Columns>