> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fullotto.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Usage

> What drives usage and how to keep it down.

AI models process text as **tokens**. Otto shows token details when the provider reports them, but you're billed for verified usage, not a token-rate formula.

* **Input tokens** are the context sent to the model: the diff and surrounding code, the ticket, instructions, conversation history, and tool results.
* **Output tokens** are what the model writes: review findings, plans, code, and replies.

Some models also report cache or reasoning tokens.

## What drives usage

| Driver | Why it matters |
| - | - |
| Review depth | Deeper reviews explore more of the codebase and reason longer. |
| Large diffs | More code to read and more context to trace. |
| Long conversations | Earlier turns may be needed for continuity. |
| Tool-heavy work | Tool results are added to later model calls. |
| Large tickets | More context is sent with every phase. |

## Keeping usage down

* **Match depth to risk.** Run `standard` by default and raise only critical paths. See [Review depth](/configuration/review-depth).
* **Ignore what doesn't need review.** Snapshots, fixtures, and generated code. See [Ignoring files](/configuration/ignoring-files).
* **Skip PRs that don't need review.** Bot updates and release merges. See [Skipping reviews](/configuration/skipping-reviews).
* **Keep instructions focused.** Include the conventions that matter; leave out unrelated documents.
* **Split large work** into smaller PRs and tickets. They're cheaper and easier to review.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.