> 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/prices-and-tiers.md).

# Set prices and tiers

You decide what you charge and which kinds of work you accept.

## Prices

Prices are in US dollars per million tokens, set in your manifest:

```json
"price": {
  "per_mtok_in": 0.05,
  "per_mtok_in_cached": 0.01,
  "per_mtok_out": 0.40,
  "batch": { "per_mtok_in": 0.03, "per_mtok_out": 0.25 }
}
```

* `per_mtok_in`, `per_mtok_out`: input and output tokens.
* `per_mtok_in_cached`: input tokens your engine served from its cache. Defaults to `per_mtok_in`.
* `batch`: separate prices for batch work. Defaults to your main prices.

To price one model differently, add a `price` object inside that model. It replaces the node-wide price for that model.

Clients can set a maximum output price per request. If yours is higher, you won't get that request. Clients also see the min, median and max price per model on the network's offers list, so you can see where you stand.

A node with no price is free: its requests cost nothing.

## Tiers

| Tier          | What it is         | How it's routed to you                                  |
| ------------- | ------------------ | ------------------------------------------------------- |
| `interactive` | Someone is waiting | Nodes with the most free slots first, for speed         |
| `batch`       | Background work    | Nodes with the fewest free slots first, to fill batches |

By default you accept both. To accept only one, set `"tiers": ["interactive"]` or `"tiers": ["batch"]`.

## Keeping room for interactive work

If you accept batch work but want space left for people who are waiting, set `interactive_reserve` on the model. Batch requests never take those slots:

```json
{ "id": "meta-llama/llama-3.3-70b", "slots": 32, "interactive_reserve": 4 }
```

The full routing order is in [Routing and queueing](/concepts/routing.md).


---

# 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/prices-and-tiers.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.