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

# API Overview

The Prime Intellect API provides programmatic access to our full platform. Get started by [setting up an API Key](./api-keys).

## Inference API

Access frontier models via an OpenAI-compatible API.

<CardGroup cols={2}>
  <Card title="List models" icon="list" href="/api-reference/inference-models">
    View available models and their capabilities
  </Card>

  <Card title="Chat completions" icon="message" href="/api-reference/inference-chat-completions">
    Generate text with frontier models
  </Card>
</CardGroup>

## Compute API

Provision and manage GPU instances across providers.

<CardGroup cols={2}>
  <Card title="Check GPU availability" icon="magnifying-glass" href="/api-reference/check-gpu-availability">
    View GPU resources and availability across providers
  </Card>

  <Card title="Provision GPUs" icon="rocket" href="/api-reference/provision-gpu">
    Deploy GPU instances with customizable configurations
  </Card>

  <Card title="Manage instances" icon="list-check" href="/api-reference/managing-pods">
    Monitor and control your active GPU instances
  </Card>

  <Card title="Manage storage" icon="hard-drive" href="/api-reference/managing-disks">
    Create persistent network-attached disks
  </Card>
</CardGroup>

## Sandboxes API

Run code securely in isolated containers.

<CardGroup cols={2}>
  <Card title="Sandboxes overview" icon="box" href="/sandboxes/overview">
    Learn about sandboxes and their use cases
  </Card>

  <Card title="Sandboxes SDK" icon="code" href="/sandboxes/sdk">
    Create and manage sandboxes programmatically
  </Card>
</CardGroup>