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

# Overview

> 16 recipes for using ScaleDown's four models on voice, messages, documents and web pages.

Cookbooks are end-to-end recipes: real input, a ScaleDown call, and the response you get back, in Python. There are 16, one for each pairing of **data type** and **model**. Run them from [scaledown.ai/cookbooks](https://scaledown.ai/cookbooks); you need an API key (see the [quickstart](/quickstart)).

## The four models

Each model has its own job. Compress runs before your LLM; the other three each stand in for an LLM call.

<CardGroup cols={2}>
  <Card title="Compress" icon="compress" href="/api-reference/compress-overview">
    **Runs in front of your LLM.** Trims retrieved or pasted context down to what the question needs, so the LLM call uses fewer tokens and returns faster. Endpoint: `POST /compress/raw/`.
  </Card>

  <Card title="Summarize" icon="align-left" href="/api-reference/summarize-overview">
    **Replaces an LLM call.** Turns long, messy text such as transcripts, threads and filings into a short abstractive summary. Model: `summarize` on `POST /v1/chat/completions`.
  </Card>

  <Card title="Extract" icon="magnifying-glass" href="/api-reference/extract-overview">
    **Replaces an LLM call.** Pulls the fields you define out of unstructured text and returns them as structured data, exactly as written in the source. Model: `extract` on `POST /v1/chat/completions`.
  </Card>

  <Card title="Classify" icon="tags" href="/api-reference/classify-overview">
    **Replaces an LLM call.** Scores text against labels you define with a yes/no rubric and returns a probability for each, plus a `top_label` for routing. Endpoints: `POST /v1/scaledown` (Decisions) and `POST /classify`.
  </Card>
</CardGroup>

## Every recipe has the same five parts

| Part | What it tells you |
| - | - |
| **The move** | What the model does here, in one line |
| **Model role** | Whether it sits in front of your LLM or replaces a call |
| **Why it fits** | The constraint that makes this the right model |
| **How it goes** | The pipeline, step by step |
| **Payoff** | The result. Only two recipes quote measured benchmarks: Voice Summarize (QMSum) and Documents Compress (FinanceBench). The rest are described qualitatively. |

## Browse by data type

<CardGroup cols={2}>
  <Card title="Voice & Calls" icon="phone" href="/cookbooks/voice">Call recaps, caller routing, CRM fields from sales calls.</Card>
  <Card title="Chats & Tickets" icon="comments" href="/cookbooks/messages">Thread digests, triage and action items.</Card>
  <Card title="Files & Docs" icon="file-lines" href="/cookbooks/documents">Briefs, document tagging and clause extraction.</Card>
  <Card title="Web Pages" icon="globe" href="/cookbooks/web">Boilerplate stripping, relevance filtering and enrichment.</Card>
</CardGroup>

[Browse all cookbooks](https://scaledown.ai/cookbooks): Filter by data type or model on scaledown.ai.


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