> For the complete documentation index, see [llms.txt](https://docs.podtorrent.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podtorrent.com/running-a-node/requirements.md).

# What you need

## An OpenAI-compatible engine

vLLM, TensorRT-LLM, SGLang, llama.cpp server, Ollama, or anything else that speaks the OpenAI API. The agent needs to reach it, for example at `http://127.0.0.1:8000`. It must support:

* `GET /v1/models`, listing the models you'll offer.
* `POST /v1/chat/completions`, with and without `"stream": true`.
* Token counts in `usage`, including in the last stream chunk when the request has `"stream_options": {"include_usage": true}`. The network sets this on every streamed request to count tokens.

If your engine reports cached tokens (`usage.prompt_tokens_details.cached_tokens`), you can also be paid the cached-input price. See [Advertise cached prompts](/running-a-node/cached-prompts.md).

## A way to reach the network

Usually that's just outbound HTTPS on port 443. If that's not allowed, there are private options. See [Choose a connection mode](/running-a-node/connection-modes.md).

## A node token

The PodTorrent team gives you one per node. It's how the network knows which node is connecting. Keep it secret, and ask for a new one if it leaks.

## What the agent does not need

No GPU access, no root, no host disk and no host networking. It never downloads models. It only talks to your engine and to the network.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.podtorrent.com/running-a-node/requirements.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.