> For the complete documentation index, see [llms.txt](https://docs.nebulablock.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nebulablock.com/core-services/overview-1.md).

# GPU Instances

> **Note:** This section describes GPU Instances, their use cases, and how to manage them for compute-intensive workloads.

## Overview

Welcome to Nebula Block's GPU Instances, the ideal solution for high-performance computing tasks such as AI model training, data analysis, and complex simulations. With Nebula Block, you can rent GPU-powered virtual machines, containers and bare metal servers tailored to your needs, featuring NVIDIA H100, A100, L40s, and RTX series GPUs.

### Key Features

* **High-Performance GPUs**
  * Access the latest NVIDIA GPUs, including H200, H100 and L40S.
  * Ideal for AI model training, real-time inference, and complex simulations.
* **Low Latency**
  * Deploy instances in geographically optimized locations for ultra-low latency.
  * Benefit from direct access to high-speed GPU resources with minimal delays.
* **Secure Access**
  * Use SSH Key or Password Authentication for secure and seamless server access.
  * Integrated firewalls and security groups to protect your data and workloads.
* **High-Speed Networking**
  * Leverage dedicated bandwidth and optimized networking to transfer large datasets efficiently.

### Pricing and Billing

* **Pay-As-You-Go:** Billing is based on the selected hardware and duration of use.
* Check the [pricing page](https://www.nebulablock.com/pricing/serverless-ai) for details.

### See Also

* [Glossary](/glossary.md)
* [API Reference - GPU Instances](/overview/platform_api/list_images.md)