> This page is for version v2026-02-09 (default).
> For other versions, use one of these documentation indexes:
> - v2026-02-09 (default): https://docs.extend.ai/2026-02-09/llms.txt
> - v2025-04-21: https://docs.extend.ai/2025-04-21/llms.txt
> - v2024-12-23: https://docs.extend.ai/2024-12-23/llms.txt

> ## Documentation Index
> Fetch the complete documentation index at: https://docs.extend.ai/llms.txt
> Use this file to discover all available pages before exploring further.
>
> ## API version
> The current API version is `2026-02-09`, served at the site root (no version prefix in URLs).
> If this page URL contains `/2025-04-21/` or `/2024-12-23/`, you are reading an older API version.
> Prefer the current docs at https://docs.extend.ai/llms.txt unless the user explicitly needs that older version.
> Do not treat older-version pages as the source of truth for new integrations.

# Overview

> Official documentation for Extend, the AI document processing platform. API reference, SDKs, and guides for parsing, extraction, classification, splitting, and editing.

Welcome to the Extend documentation. Extend is a platform for building, iterating on, evaluating, and deploying AI-powered document processing infrastructure. We provide parsing, extraction, classification, splitting, and editing so you can focus on building the features that matter for your business. Extend uses a mix of trained-in-house and frontier models to balance accuracy, latency, and cost for your use case.

## What do you need to do?

| You need to…                                                                               | Start here                                 |
| ------------------------------------------------------------------------------------------ | ------------------------------------------ |
| Turn documents into clean markdown or blocks for RAG and agents                            | [Parsing](/parsing/overview)               |
| Pull specific fields into structured JSON (invoices, IDs, contracts)                       | [Extraction](/extraction/overview)         |
| Route incoming documents to the right downstream process                                   | [Classification](/classification/overview) |
| Split a multi-document PDF into separate files by type                                     | [Splitting](/splitting/overview)           |
| Fill forms or generate completed PDFs programmatically                                     | [Editing](/editing/overview)               |
| Build multi-step document pipelines with chained classification, splitting, and extraction | [Workflows](/workflows/overview)           |

## Start building

We have quickstarts for a few different integration paths. Pick the on-ramp that fits how you work:

#### [API & SDKs](/api-quickstart)

Integrate directly into your app using our API. Call Extend from SDKS in Python, TypeScript, Java, and Go or REST.

#### [Dashboard](/dashboard-quickstart)

Build, test, and iterate in the browser – then copy the API call straight into your code.

#### [AI Agents](/agent-quickstart)

Point a coding agent at Extend with ready-made context files and a machine-readable docs index.