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

# Overview

> As a Service Consumer, you run computational workloads on the distributed Dispersed Network — from large-scale data processing and inference-based tasks to SSH-accessible GPU machines.

## What You'll Need

* An [OTOY account](https://account.otoy.com)
* For SSH access: an SSH key pair
* For programmatic API access: an API Key (see [Authenticate Requests](/service-consumers/service-consumers-authenticate-requests))

Once you've created an OTOY account, sign in to the [Dispersed Console](https://console.dispersed.com).

***

## Process Overview

| Step | Action                                         | Guide                                                                                             |
| ---- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| 1    | Launch your first Job using a Recipe (easiest) | [Quick Start: For Service Consumers](/service-consumers/service-consumers-quick-start-job-recipe) |
| 2    | Learn to authenticate API requests             | [Authenticate Requests](/service-consumers/service-consumers-authenticate-requests)               |
| 3    | Create custom Jobs with the API                | [Create a Job](/service-consumers/service-consumers-create-job)                                   |

***

## Two Ways to Launch Jobs

### 1. Job Recipes (Recommended)

**Job Recipes** are pre-configured templates that you can launch repeatedly with minimal effort. Use recipes for workloads you expect to run more than once.

**Why use Job Recipes?**

* **Easy re-launches** — Run the same workload again without resubmitting the full configuration
* **Iterative development** — Tweak inputs and re-launch quickly
* **Pre-tested configs** — Hardware requirements and container settings already validated
* **Forkable** — Fork official recipes to create your own customized versions with different hardware specs, Docker images, or pre-filled inputs

Available recipe types include:

* **Base:** Linux with SSH access (ubuntu, debian)
* **Inference:** GenAI model inference environments (comfyui, pytorch)
* **Training:** Fine-tuning and reinforcement learning (unsloth, jupyter)

[**Quick Start with Job Recipes →**](/service-consumers/service-consumers-quick-start-job-recipe)

### 2. Direct API (One-Off Workloads)

Create Jobs directly via the API when you need full control or have a one-off workload that you don't expect will be repeated.

* Specify exact hardware requirements
* Configure custom Docker images
* Full control over container parameters

<Tip>
  If you find yourself submitting the same Job payload repeatedly, consider creating a Job Recipe instead — it's much easier to re-launch a recipe than to manage full Job payloads.
</Tip>

[**Create Jobs via API →**](/service-consumers/service-consumers-create-job)

## How Job Execution Works

1. **Submit Job** specifying hardware requirements and container config
2. **Network Matches** your Job to an available Node
3. **Node Executes** your Job in an isolated Docker container
4. **Connect** to the running container (e.g. SSH)
5. **Stop Job** when finished (or let it complete for BATCH jobs)

<Note>
  Jobs are billed based on compute time. **PERSISTENT** jobs bill hourly until stopped. **BATCH** jobs bill for the configured execution duration.
</Note>

## Monitor Your Jobs

Track job status, view logs, and manage active job runs through the [Dispersed Console](https://console.dispersed.com).