# Get Started On Your Instance
This tutorial explains how to launch a new instance. Follow the steps below to complete the setup.
#### 1. Select instance type
On the `Deploy` page, choose the GPU model you desire to start.
You can select the GPU based on configuration details, including the GPU count, memory, CPU pairing, available units, virtual CPUs, RAM, storage, and the hourly price in Credits.
#### 2. Select an image or snapshot
Once the hardware has been chosen, you can define the environment source:
You can start with an `Official Image` with a prebuilt, standardized setup, or a `Snapshot` that restores a previously saved instance, enabling continuity of prior configurations.
The selected item’s details will be displayed on the right panel, such as:
#### 3. Unit quantity
Define how many units to allocate with`Unit Qty`. Each unit contains a fixed resource package (GPU, VRAM, etc.), and increasing the count scales resources proportionally.
#### 4. Mount Data Hub
To attach a storage volume, click `Storage Capacity` to configure the following options:
* **Data Drive List** – shows all available drives.
* **Region** – e.g., `1`.
* **Usage** – displays used and total capacity (e.g., `0/2 GB`).
* **Mount Path** – default is `/datadrive` (not editable).
* **Permissions** – choose **Read only** or **Read & write** access.
Once configured, your data drive will be successfully mounted.
#### 5. Verify specifications and pricing details
After finishing the setup, select `Show Detail` to see more information, your configuration summary will be shown at the bottom of the page.
#### 6. Create the instance
Click `Complete Checkout` to confirm and launch your instance.
You can name your instance in the following window.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://gata-1.gitbook.io/gata-docs/use-guide/gata-decentralized-ai-cloud/get-started-on-your-instance.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.