> For the complete documentation index, see [llms.txt](https://docs.ai.neevcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ai.neevcloud.com/api-reference/gpu-instance.md).

# GPU Instance API

The GPU Instance API creates and manages **GPU Instances** (also called AI Runtimes) — container-based compute environments backed by one or more GPUs. A GPU Instance is ideal for interactive and GPU-accelerated workloads such as Jupyter notebooks, model fine-tuning, custom inference servers, or any application you want to run inside your own container.

GPU Instances are launched from **Templates**: pre-built container configurations that bundle a base image, exposed applications (e.g. JupyterLab, SSH), and optional default environment variables. NeevAI publishes a curated catalog of **Platform Templates**, and organizations can register **Custom Templates** built from their own private images to standardize a team's environment. Once an instance reaches `Running`, you connect to it through the browser (Jupyter, custom UIs) or over SSH, and you can attach Network Volumes for persistent storage.

## What you can do

* **GPU Instances** — create an instance on a chosen GPU configuration (for example, JupyterLab on 1× H200, or a custom training container on 4× H200 with persistent storage), list instances and their states, fetch a single instance's access details, read utilization metrics, and delete an instance.
* **Platform Templates** — browse NeevAI's curated template catalog and fetch a template by ID. Use a template's `id` as the `templateID` when creating an instance.
* **Custom Templates** — create organization-scoped templates from your own private container images, list them, fetch one by ID, and delete them.

Use the interactive reference below to inspect the create payloads, status fields, and response schemas, and to try each endpoint directly.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.ai.neevcloud.com/api-reference/gpu-instance.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.