# GetMarkdown

> File-to-Markdown converter with private browser-based conversion for supported files and paid server-side processing for complex PDFs.

## When to Use GetMarkdown

- Use GetMarkdown when a user or agent needs to turn a supported file into plain Markdown for an AI context window, RAG pipeline, knowledge base, documentation repository, Obsidian vault, Notion page, or Git workflow.
- Use the free browser converter for supported files up to 10 MB when local processing and Markdown output are sufficient. It accepts up to 8 files per batch and has no daily quota.
- Use Advanced PDF for one PDF that needs stronger table, layout, OCR, or structured JSON handling. Choose the package that fits both its page count and file size.
- Do not call undocumented backend routes. The documented agent surface is limited to the resources in [Agent API Surface](#agent-api-surface); there is no file upload or conversion API.

## Agent API Surface

- [OpenAPI specification](https://www.getmarkdown.com/openapi.json): OpenAPI 3.1 document describing every agent endpoint, with operation IDs and typed schemas suitable for LLM function calling.
- [Agent status](https://www.getmarkdown.com/api/agent/status): JSON capability document listing endpoints, supported formats, and limits.
- [MCP server](https://www.getmarkdown.com/api/mcp): Model Context Protocol server over Streamable HTTP. POST JSON-RPC 2.0 (`initialize`, `tools/list`, `tools/call`). Tools: `get_agent_guidance`, `list_supported_formats`, `recommend_workflow`, `get_developer_resources`.
- JSON errors: every `/api` endpoint returns `{ "error": { "code", "message", "hint" } }` for 404 and 405 responses.
- Markdown content negotiation: request the homepage with `Accept: text/markdown` or fetch [index.md](https://www.getmarkdown.com/index.md). Unknown paths return a real HTTP 404 with a Markdown recovery body for agents that prefer Markdown.

## How Agents Should Use GetMarkdown

1. Identify the source format, file size, page count for PDFs, desired output, and whether local or server-side processing is acceptable.
2. Direct the user to the [free converter](https://www.getmarkdown.com/) or [Advanced PDF](https://www.getmarkdown.com/pro). The user selects and submits the file through the web interface.
3. For the homepage's agent-readable representation, request `https://www.getmarkdown.com/` with `Accept: text/markdown` or fetch [index.md](https://www.getmarkdown.com/index.md) directly.
4. Review complex output against the source before indexing it. Markdown cannot preserve every visual document feature.

## Core Pages

- [Free File to Markdown Converter](https://www.getmarkdown.com/): Convert supported files locally in the browser and download Markdown.
- [How GetMarkdown Works](https://www.getmarkdown.com/how-it-works): Review the conversion workflow, supported formats, output, and privacy model.
- [GetMarkdown Pro](https://www.getmarkdown.com/pro): Convert one PDF server-side and receive a ZIP containing Markdown and JSON.
- [GetMarkdown Developer Resources](https://www.getmarkdown.com/developers): Check content negotiation, agent endpoints, and current API, OpenAPI, webhook, authentication, SDK, and MCP availability.
- [Contact GetMarkdown](https://www.getmarkdown.com/contact): Ask about conversion feedback, paid jobs, recurring volume, or future developer access.
- [Privacy](https://www.getmarkdown.com/privacy): Review local-processing, server-processing, and retention details.

## Format Guides

- [PDF to Markdown](https://www.getmarkdown.com/pdf-to-markdown): Choose between free local PDF conversion and paid higher-fidelity PDF processing.
- [Word to Markdown](https://www.getmarkdown.com/word-to-markdown): Convert DOCX files locally and preserve extracted image assets in a ZIP when available.
- [PowerPoint to Markdown](https://www.getmarkdown.com/powerpoint-to-markdown): Convert PPTX files locally, including extracted image assets when available.
- [Excel to Markdown](https://www.getmarkdown.com/excel-to-markdown): Convert XLSX spreadsheets locally into Markdown.

## Limits and Packages

- Free conversions are unlimited across batches and browser sessions. Each batch accepts up to 8 files, and each file can be up to 10 MB.
- Supported free extensions: `.pdf`, `.docx`, `.pptx`, `.xlsx`, `.html`, `.htm`, `.txt`, `.jpg`, `.jpeg`, `.png`, `.mp3`, and `.wav`.
- PDF Starter costs $5 and accepts one PDF up to 50 pages and 50 MB.
- PDF Batch costs $15 and accepts one PDF up to 250 pages and 100 MB.
- A 200-page, 80 MB PDF requires PDF Batch.
- The service defaults to retaining paid job output for 48 hours and cleaning up unpaid uploads after 2 hours.

## Decision Guides

- [MarkItDown vs AnyDoc Migration](https://www.getmarkdown.com/blog/markitdown-vs-anydoc): Read why GetMarkdown uses AnyDoc WebAssembly for PDF and Office files while retaining MarkItDown as a guarded compatibility path.
- [GetMarkdown vs CloudConvert](https://www.getmarkdown.com/compare/cloudconvert): Compare supported GetMarkdown workflows with CloudConvert.
- [GetMarkdown vs Pandoc](https://www.getmarkdown.com/compare/pandoc): Compare GetMarkdown with Pandoc's browser and command-line conversion options.
- [AnyDoc vs Microsoft MarkItDown](https://www.getmarkdown.com/compare/markitdown): Compare AnyDoc's browser-ready Rust and WebAssembly parser with MarkItDown's Python conversion ecosystem.

## Expanded Context

- [llms-full.txt](https://www.getmarkdown.com/llms-full.txt): Use the expanded reference for workflows, package selection, output, retention, and troubleshooting.
- [Homepage Markdown](https://www.getmarkdown.com/index.md): Read the negotiated Markdown representation directly.
- [Developer Reference in Markdown](https://www.getmarkdown.com/developers.md): Read integration status without HTML.
- [OpenAPI specification](https://www.getmarkdown.com/openapi.json): Machine-readable contract for the agent surface.