# markitdown.ai — Turn documents into AI-ready Markdown

> Convert PDFs, Office files, images, and HTML into clean Markdown for ChatGPT, Claude, RAG pipelines, and agents — free in the browser, or via API.

## Markdown built for AI

A PDF renders perfectly for a human and falls apart the moment a model reads it: columns merge, tables collapse, reading order breaks. markitdown.ai turns PDFs, Office files, images, and web content into clean Markdown you can preview, download, and reuse in ChatGPT, Claude, RAG pipelines, and agents — free in the browser, or via API for production workflows.

## Documents aren't AI-ready

Most documents were built for people and printers, not for language models. Naive extraction breaks down in predictable ways:

- Reading order breaks — multi-column PDFs, headers, and footnotes interleave, so the text an LLM reads no longer matches the document a human sees.
- Tables and headings flatten — copy-paste collapses tables into runs of numbers and drops the heading hierarchy.
- Scans need OCR — image-based pages carry no text layer until run through optical character recognition.
- Raw text is noisy — ad-hoc extraction leaves page numbers, broken hyphenation, and stray characters that pollute prompts and retrieval.

## Built for AI workflows

- Start with one file, free — see real Markdown in the browser before creating an account.
- Make repeated work manageable — saved history, a paired source-and-output library, and batch conversion.
- Wire it into production — a developer API turns conversion into a step inside ingestion jobs, internal tools, and agents.
- Handle bigger, harder files — higher size and page limits plus asynchronous processing.
- Output built for AI — structure-aware Markdown ready to chunk, embed, and retrieve.

## Made for every team

- RAG and AI pipelines — convert source documents into clean Markdown before chunking, embedding, or agent processing.
- Research and reports — turn papers, whitepapers, and slide decks into editable, searchable Markdown.
- Operations documents — process policies, contracts, and invoices without manual copy-paste cleanup.
- Developer automation — convert files inside ingestion jobs, internal tools, and agent pipelines via the API.

## Structure, not just text

The goal is Markdown that keeps the structure your downstream tools depend on, produced by a server-side parsing pipeline instead of fragile browser copy-paste.

- Preserves headings, lists, tables, and reading order where possible.
- Handles common document formats through a server-side parsing pipeline.
- Built for async workloads, larger files, and future OCR and layout enhancements.

## Browser or API

The web app covers one-off and recurring manual conversion (upload, preview, save history, batch, track credits). The developer API covers everything that should happen automatically: submit jobs by API key, poll or receive callbacks, and feed Markdown into RAG ingestion, CMS workflows, internal tools, and agents.