/document-to-markdown

Convert any document to clean Markdown.

Define formatting options, send your file — get Markdown back.

# Convert any document to clean Markdown
curl -X POST https://api.documentai.dev/document-to-markdown/v1 \
  -H "x-api-key: YOUR_API_KEY" \
  -F "url=https://example.com/invoice.pdf" \
  -F 'options={"headings": true, "tables": true}'

Playground

Try it

Markdown Options

Customize how the Markdown is generated.

headings

lists

nested_lists

tables

bold

italic

code_blocks

links

math

page_delimiters

Copy request as

Reference

Documentation

Endpoint

POSThttps://api.documentai.dev/document-to-markdown/v1

Authentication

Header	Required	Description
x-api-key	Required	Your API key. Get one by signing up.

Request Body

Upload a file, provide a public URL, or send plain text.

Field	Type	Required	Description
url	string	One of three	Publicly accessible URL to a document. Use a signed URL for protected files.
file	file	One of three	Any supported document, as multipart/form-data. Max 30 MB.
text	string	One of three	Raw unstructured text to extract from.
options	object	Optional	JSON configuration for markdown rendering overrides.

Accepted File Types

PDFWord (.doc, .docx)Images (PNG, JPG, WebP, GIF, BMP)PowerPoint (.ppt, .pptx)Excel (.xls, .xlsx, .csv)HTMLRTF / TXTOpenDocument (ODT, ODS, ODP)Code filesPlain text

Options Reference

Customize how the Markdown is generated. Pass this as a JSON string in the options field.

Option	Type	Default	Description
headings	boolean	true	Render text serving as titles or section labels with heading prefixes (#, ##).
lists	boolean	true	Render list items with list markers (-, 1.).
nested_lists	boolean	true	Maintain hierarchical indentation for nested list items.
tables	boolean	true	Extract tabular data using Markdown table syntax.
bold	boolean	true	Apply bold formatting (text) for emphasized text.
italic	boolean	true	Apply italic formatting (text) where appropriate.
code_blocks	boolean	true	Wrap code snippets in triple backticks.
links	boolean	false	Extract URLs as Markdown links [text](url).
math	boolean	true	Render mathematical formulas using LaTeX math syntax.
page_delimiters	boolean	false	Insert `<!-- page N -->` markers instead of unified flat output.

Example Response

200 OK

{
  "status": "success",
  "data": {
    "markdown": "# Invoice #12345\n\n**From:** Acme Corp  \n**Date:** April 28, 2026  \n**Due:** May 15, 2026\n\n### Items:  \n- Widget Pro x5 — $199.99 each  \n- Gadget Lite x10 — $24.50 each\n\n| Description | Amount |\n| --- | --- |\n| Subtotal | $1,244.95 |\n| Tax (8%) | $99.60 |\n| **Total** | **$1,344.55** |\n\n**Status:** *Unpaid*",
    "text": "Invoice #12345\n\nFrom: Acme Corp\nDate: April 28, 2026\nDue: May 15, 2026\n\nItems:\n- Widget Pro x5 — $199.99 each\n- Gadget Lite x10 — $24.50 each\n\nDescription Amount\nSubtotal $1,244.95\nTax (8%) $99.60\nTotal $1,344.55\n\nStatus: Unpaid"
  }
}

Limits

Max Input

Limit	Value
Max file size	30 MB
Max pages per document	1,000
Max input tokens	1,000,000

Max Output

If input is a URL or a file, max output is 2,000 tokens per input page.

If input is text, max output is twice the input tokens count.

Minimum is always 2,000 tokens, absolute maximum is 60,000 tokens per request.

Cost

· File inputs: 1 credit per page.
· Text inputs: 1 credit per 1,000 tokens.
· Only input is billed — output size does not affect cost.
· Failed requests are not charged.