> 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/reference/manifest.md).

# Manifest reference

The guide is [Write your manifest](/running-a-node/manifest.md). This page lists every field.

## Node

| Field         | Required | Meaning                                                                                                   |
| ------------- | -------- | --------------------------------------------------------------------------------------------------------- |
| `node`        | yes      | A name for this node, shown in your reports                                                               |
| `models`      | yes      | List of models, below                                                                                     |
| `tiers`       | no       | Work you accept: `["interactive", "batch"]` (default both)                                                |
| `price`       | no       | Node-wide price, below                                                                                    |
| `power_watts` | no       | Declared full-load power draw, for the [dashboard](/for-operators/dashboard.md) only. Next agent release. |

## Model (`models[]`)

| Field                 | Required | Meaning                                                                                               |
| --------------------- | -------- | ----------------------------------------------------------------------------------------------------- |
| `id`                  | yes      | Model id exactly as your engine's `/v1/models` lists it                                               |
| `slots`               | yes      | Most requests for this model at once                                                                  |
| `quant`               | no       | Precision running: `bf16`, `fp8`, `q4_k_m`, …                                                         |
| `context_max`         | no       | Longest prompt plus output, in tokens                                                                 |
| `speed.single_tps`    | no       | Output tokens/s for one request alone                                                                 |
| `speed.batch_tps`     | no       | Total output tokens/s with all slots busy                                                             |
| `interactive_reserve` | no       | Slots batch work may not use                                                                          |
| `cached_prompts`      | no       | `[{ "name", "sha256", "tokens" }]`; see [Advertise cached prompts](/running-a-node/cached-prompts.md) |
| `price`               | no       | Replaces the node-wide price for this model                                                           |
| `power_watts`         | no       | As above, for this model                                                                              |

## Price (`price`)

All in USD per million tokens.

| Field                | Meaning                                                        |
| -------------------- | -------------------------------------------------------------- |
| `per_mtok_in`        | Input tokens                                                   |
| `per_mtok_out`       | Output tokens                                                  |
| `per_mtok_in_cached` | Input tokens served from cache (default `per_mtok_in`)         |
| `batch`              | Batch-tier price with the same fields (default the main price) |


---

# 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/reference/manifest.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.