# MarkPDFdown/markpdfdown

A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Markdown工具

Repository: https://github.com/MarkPDFdown/markpdfdown
Canonical: https://ross.abutalabs.com/products/markpdfdown
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm, markdown, pdf, pdf-converter, pdf-markdown, pdf2markdown, pdf2md
Last push: 2026-01-25T15:31:43+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 67, longevity 38
- inputs: {"age_days": 537, "days_push": 220, "days_rel": 220, "gap_med": 2.0, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2184, forks 180 (observed 2026-08-28T04:06:23.564740+00:00)

## What it is
MarkPDFDown is a Python CLI tool that converts PDF documents and images into clean Markdown using multimodal large language models via LiteLLM. It preserves formatting such as headings, tables, formulas, and diagrams, and supports OpenAI and OpenRouter providers.

## Use cases
- convert pdf to markdown
- extract tables and formulas from pdfs into markdown
- transcribe scanned documents with a vision llm
- convert images to markdown text
- convert only specific page ranges of a pdf
- batch convert pdfs from the command line

## When to choose
- you need high-fidelity PDF-to-Markdown conversion of complex layouts, tables, and formulas
- you already have an OpenAI or OpenRouter API key and want LLM-based extraction
- you want a scriptable CLI or pipe-based conversion workflow

## When to avoid
- you need fully offline conversion without sending documents to an LLM API
- you want a free tool with no per-page API costs
- you only need simple text extraction that a lightweight parser could handle

## Facets
- artifact type: cli-tool
- maturity: active
- function: ocr, pdf, llm-inference, cli
- domain: pdf, developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: pdf-to-markdown, multimodal-llm, document-conversion, litellm, vision-models, docker

## Member repositories
- MarkPDFdown/markpdfdown (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:23.564740+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:48:12.474612+00:00, confidence not recorded.
  - readme: https://github.com/MarkPDFdown/markpdfdown (fetched 2026-08-28T04:06:23.564740+00:00, sha cbf98ac130af)
- Data as of 2026-08-30T08:39:29.467469+00:00.