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

# Introduction

> Levanto Sage documentation — structured decision API for routing, scoring, and classification.

Levanto Sage is a decision model for workflows where software needs to **decide, not write**. It turns content plus a question into a structured decision with a probability or confidence signal.

It behaves like a general-purpose classifier, but one that weighs context and meaning instead of matching on similarity alone — no training needed, ready to use immediately for your use case.

Use Sage when an application needs to route, approve, block, score, rank, tag, or escalate. Unlike LLMs that return text, Sage always returns a machine-actionable decision signal.

## Supported decision kinds

<Columns cols={2}>
  <Card title="Yes/No" icon="circle-check" href="/decision-model/yesno">
    Binary questions with probability and confidence.
  </Card>

  <Card title="Choice" icon="list" href="/decision-model/choice">
    Pick the best option from a set.
  </Card>

  <Card title="Scale" icon="gauge" href="/decision-model/scale">
    Rubric scoring with expectation and confidence.
  </Card>

  <Card title="Sort" icon="arrow-down-up" href="/decision-model/sort">
    Rank items by a criterion.
  </Card>

  <Card title="Tags" icon="tags" href="/decision-model/tags">
    Apply independent yes/no labels.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/decision-model/quickstart">
    Make your first `/decide` call.
  </Card>
</Columns>

## Documentation sections

* [**Use cases**](/use-cases) — Agents, operations, guardrails, moderation, and risk & fraud.
* [**Decision model**](/decision-model/quickstart) — HTTP API for Yes/No, Choice, Scale, Sort, and Tags decisions.
* [**Authentication**](/decision-model/authentication) — API key headers and error codes for `/decide` calls.
* [**Limits**](/decision-model/limits) — Per-kind size limits and the content and question token budget.
* [**Errors**](/decision-model/errors) — Status codes and error response bodies.
* [**Pricing**](/pricing) — Token pricing (\$3 / 1M input), grounding surcharges, and enterprise volume discounts.