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

# Acasia Cloud

> The web platform for the capacity your organization holds — telemetry, hardware alerting, credentials, and, where the control plane is installed, clusters and model deployments.

Acasia Cloud is where your organization sees what its GPU hardware is doing and acts on it. It is one platform for every customer, but what it reports and controls depends on how you hold the hardware.

## What you see, by customer type

|                                        | Bare metal                                                     | Marketplace                       |
| -------------------------------------- | -------------------------------------------------------------- | --------------------------------- |
| **What is in scope**                   | The machines reserved for your organization                    | Only the GPUs you rented          |
| **Telemetry depth**                    | Node level, and GPU level where the control plane is installed | GPU level                         |
| **Machine access**                     | Root access — you run your own stack                           | Managed through the control plane |
| **Hardware alerting**                  | Included                                                       | Included                          |
| **Model library and cluster controls** | Where the control plane is installed                           | Included                          |
| **Credentials, users, and billing**    | Included                                                       | Included                          |

Bare metal customers hold root access and run their own stack on the machines, so Acasia reports at the node level unless the control plane is installed. Marketplace rentals always run the control plane, installed automatically at checkout. See [The control plane](/marketplace/control-plane).

## Where each task lives

| Task                                                     | Where it lives                                         |
| -------------------------------------------------------- | ------------------------------------------------------ |
| Review GPU, cluster, and deployment status at a glance   | [Dashboard](/developer-portal/dashboard)               |
| Inspect the machines allocated to your organization      | [Machines](/developer-portal/machines)                 |
| Create, resize, and wind down clusters                   | [Clusters](/developer-portal/clusters)                 |
| Deploy a model from the library as an inference endpoint | [Inference Models](/developer-portal/inference-models) |
| Create credentials for programmatic access               | [API Keys](/developer-portal/api-keys)                 |
| Manage profile, security, billing, SSH keys, and users   | [Settings](/settings/overview)                         |

## How Cloud is organized

| Section              | Purpose                                                                                                      |
| -------------------- | ------------------------------------------------------------------------------------------------------------ |
| **Getting Started**  | Short, task-focused walkthroughs — deploy an endpoint, create an API key, connect over SSH, connect your IDE |
| **Developer Portal** | The organization-scoped workspace for machines, clusters, model deployments, and API keys                    |
| **Settings**         | Account and organization administration — profile, security, billing, SSH keys, and users                    |

All three are scoped to the active organization. Confirm the organization shown in the lower-left corner before creating clusters, deploying models, or generating credentials.

## Your first hour

1. Confirm the active organization.
2. Review the machines allocated to you and their available capacity.
3. Create a cluster sized to your workload.
4. Deploy a model from the library, or connect to the cluster over SSH.
5. Create an API key and call the endpoint from your application.

## Start here

<CardGroup cols={2}>
  <Card title="Deploy your first inference endpoint" icon="rocket" href="/get-started/deploy-inference-endpoint">
    Stand up a working inference endpoint in five minutes.
  </Card>

  <Card title="Create an API key" icon="key" href="/get-started/create-api-key">
    Generate, name, and store a credential for programmatic access.
  </Card>

  <Card title="Connect with SSH" icon="terminal" href="/get-started/connect-cluster-ssh">
    Authorize a public key and connect to an active cluster.
  </Card>

  <Card title="Connect your IDE" icon="code" href="/get-started/connect-ide-to-cluster">
    Use VS Code, Cursor, JetBrains, or Jupyter against a remote cluster.
  </Card>
</CardGroup>