The best free AI OCR and document extraction tools (20)

Every option in the catalog for when you need to pull clean structured data out of PDFs and scans — 20 AI OCR and document extraction tools, 20 of them free or freemium, with the pricing tier printed on every row.

20tools listed
20free or freemium
10with no paid plan at all
1sub-categories covered

Best Free AI OCR and document extraction tools — straight answers

What are the best free AI OCR and document extraction tools?

Flocci AI Tools lists 20 of them, ordered free tiers first: dots.ocr (dots.mocr), LangExtract (Google), MinerU, olmOCR and PaddleOCR-VL. Every one of them is free or has a free tier. Each entry states what it uniquely does rather than a score.

Which of these are completely free?

10 on this page are marked fully free with no paid plan at all: dots.ocr (dots.mocr), LangExtract (Google), MinerU, olmOCR and PaddleOCR-VL. The remaining 10 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.

How is this list ordered?

Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.

Best Free AI OCR and document extraction tools — quick picks

Which AI OCR and document extraction tools work in a browser with no install?

dots.ocr (dots.mocr), LangExtract (Google), MinerU, olmOCR and PaddleOCR-VL all work in a browser tab with no install needed — just open the site and go. 14 of the 20 free AI OCR and document extraction tools listed here are browser-based.

Which AI OCR and document extraction tools let you sign in with Google?

AskYourPDF supports Google sign-in, so you can start without creating a new account. That's 1 of the 20 free AI OCR and document extraction tools on this page.

Which AI OCR and document extraction tools have a mobile app?

AskYourPDF and Mathpix have an iOS or Android app. 2 of the 20 free AI OCR and document extraction tools here can run on your phone.

Which AI OCR and document extraction tools can you self-host or run offline?

DeepSeek-OCR, Docling, Dolphin (ByteDance), Marker and MarkItDown can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 5 of the 20 free AI OCR and document extraction tools here run offline.

All 20 tools, free tiers first

Browse AI OCR & Document Extraction →
Best Free AI OCR and document extraction tools: pricing tier, category and the capability each tool is listed for.
ToolPricingTypeListed for
dots.ocr (dots.mocr)FreeAI OCR & Document Extraction3B vision-language model for layout parsing across many scripts
LangExtract (Google)FreeAI OCR & Document ExtractionPython library extracting structured data from unstructured text with LLMs
MinerUFreeAI OCR & Document ExtractionParses PDFs, images and Office files into Markdown, JSON, HTML or LaTeX
olmOCRFreeAI OCR & Document ExtractionApache 2.0 open-source OCR toolkit from Ai2, 19.3k GitHub stars
PaddleOCR-VLFreeAI OCR & Document Extraction1B-parameter document parsing VLM (NaViT encoder + ERNIE-4.5-0.3B)
DeepSeek-OCRFreeAI OCR & Document ExtractionVision-language OCR that compresses document context optically
DoclingFreeAI OCR & Document ExtractionMIT-licensed, 64.7k GitHub stars, IBM Research-originated, now under LF AI & Data Foundation
Dolphin (ByteDance)FreeAI OCR & Document ExtractionTwo-stage document-type and layout analysis then element parsing
MarkerFreeAI OCR & Document ExtractionApache-2.0 code, 38.7k GitHub stars, converts PDFs/DOCX/PPTX/XLSX to markdown/JSON
MarkItDownFreeAI OCR & Document ExtractionConverts PDF, Office files, images, audio and HTML into LLM-friendly Markdown
AskYourPDFFreemiumAI OCR & Document ExtractionChat with any PDF plus auto-fill PDF forms
Chandra OCRFreemiumAI OCR & Document ExtractionConverts images and PDFs to HTML, Markdown or JSON with layout
HumataFreemiumAI OCR & Document ExtractionFree tier: 60 pages, 10 answers, no card
LlamaParseFreemiumAI OCR & Document ExtractionParses 90+ formats incl. complex tables/charts/handwriting into clean markdown
MathpixFreemiumAI OCR & Document ExtractionSpecializes in STEM: equations, chemistry structures, handwriting to LaTeX/text
PDF.aiFreemiumAI OCR & Document ExtractionChat-with-PDF product plus a separate parse/extract/split PDF API
ReductoFreemiumAI OCR & Document Extraction15,000 free starter credits, no card required
Surya OCRFreemiumAI OCR & Document Extraction650M-parameter OCR VLM covering 90+ languages
Upstage Document AIFreemiumAI OCR & Document ExtractionParse/Extract/Classify/Instruct pipeline billed per page
Mistral OCR 4FreemiumAI OCR & Document ExtractionSelf-hostable single-container OCR model for regulated industries

dots.ocr (dots.mocr)

AI OCR & Document Extraction
freeNew
  • 3B vision-language model for layout parsing across many scripts
  • Converts charts and diagrams into SVG code
  • Scores 83.9 on olmOCR-bench
  • MIT licensed with free live demo

LangExtract (Google)

AI OCR & Document Extraction
freeNew
  • Python library extracting structured data from unstructured text with LLMs
  • Maps each extraction to its exact source span
  • Works with Gemini, OpenAI and local Ollama models
  • Interactive HTML visualization of results

MinerU

AI OCR & Document Extraction
freeNew
  • Parses PDFs, images and Office files into Markdown, JSON, HTML or LaTeX
  • Runs fully locally with OCR, table and formula recognition
  • Free hosted web app at mineru.net plus agent-ready outputs
  • Version 4.0 adds four parsing quality tiers

olmOCR

AI OCR & Document Extraction
free
  • Apache 2.0 open-source OCR toolkit from Ai2, 19.3k GitHub stars
  • Vision-language-model based, handles equations/tables/multi-column layout
  • Runs at a fraction of commercial OCR cost on a 7B model

PaddleOCR-VL

AI OCR & Document Extraction
freeNew
  • 1B-parameter document parsing VLM (NaViT encoder + ERNIE-4.5-0.3B)
  • Handles text, tables, formulas, charts and handwriting
  • Supports 109 languages including Hindi and Arabic
  • Apache 2.0; newer PaddleOCR-VL-1.6 available

DeepSeek-OCR

AI OCR & Document Extraction
freeNew
  • Vision-language OCR that compresses document context optically
  • Document-to-Markdown, layout detection and figure parsing
  • Multiple resolution modes up to 1280x1280
  • MIT license; DeepSeek-OCR2 released Jan 2026

Docling

AI OCR & Document Extraction
free
  • MIT-licensed, 64.7k GitHub stars, IBM Research-originated, now under LF AI & Data Foundation
  • Advanced PDF layout + table structure recognition, local execution
  • Exports to Markdown/HTML/JSON, integrates with LangChain/LlamaIndex

Dolphin (ByteDance)

AI OCR & Document Extraction
freeNew
  • Two-stage document-type and layout analysis then element parsing
  • Page-level and element-level parsing modes
  • Hugging Face Transformers integration
  • MIT licensed; Dolphin-v2 released Dec 2025

Marker

AI OCR & Document Extraction
free
  • Apache-2.0 code, 38.7k GitHub stars, converts PDFs/DOCX/PPTX/XLSX to markdown/JSON
  • 76.0% accuracy on the olmocr-bench benchmark
  • Runs on GPU, CPU, or Apple Silicon; optional LLM-boosted accuracy mode

MarkItDown

AI OCR & Document Extraction
freeNew
  • Converts PDF, Office files, images, audio and HTML into LLM-friendly Markdown
  • Ships an MCP server for agents
  • Open-source Python package and CLI
  • Optional LLM-based image description

AskYourPDF

AI OCR & Document Extraction
freemium
  • Chat with any PDF plus auto-fill PDF forms
  • Embeddable document chatbot for websites
  • 5M+ users including MIT/Harvard/Oxford/Stanford

Chandra OCR

AI OCR & Document Extraction
freemiumNew
  • Converts images and PDFs to HTML, Markdown or JSON with layout
  • Handles tables, forms and handwriting in 90+ languages
  • 85.8% on olmOCR benchmark (Chandra 2, Mar 2026)
  • Free playground at datalab.to; open weights under modified OpenRAIL-M

Humata

AI OCR & Document Extraction
freemium
  • Free tier: 60 pages, 10 answers, no card
  • Cited answers across many uploaded files at once
  • Paid tiers priced per extra page rather than per seat

LlamaParse

AI OCR & Document Extraction
freemium
  • Parses 90+ formats incl. complex tables/charts/handwriting into clean markdown
  • 300,000+ users, 1B+ documents processed
  • Free trial credits via LlamaCloud, then usage-based

Mathpix

AI OCR & Document Extraction
freemium
  • Specializes in STEM: equations, chemistry structures, handwriting to LaTeX/text
  • Desktop Snip app plus Convert/Files developer APIs
  • 50B+ pages processed, 5M+ users

PDF.ai

AI OCR & Document Extraction
freemium
  • Chat-with-PDF product plus a separate parse/extract/split PDF API
  • Popular ChatPDF-category alternative with API access for developers

Reducto

AI OCR & Document Extraction
freemium
  • 15,000 free starter credits, no card required
  • Citation-ready structured JSON across 30+ file types
  • Edits extracted data back into original PDF/DOCX layout

Surya OCR

AI OCR & Document Extraction
freemiumNew
  • 650M-parameter OCR VLM covering 90+ languages
  • Layout analysis, reading order and table recognition
  • 83.3% on olmOCR-bench
  • Free playground at datalab.to; weights free for research, personal use and small startups

Upstage Document AI

AI OCR & Document Extraction
freemium
  • Parse/Extract/Classify/Instruct pipeline billed per page
  • Classify and Instruct currently free in beta
  • Free 1-year access to Document Parse for schools/hospitals/nonprofits

Mistral OCR 4

AI OCR & Document Extraction
freemium
  • Self-hostable single-container OCR model for regulated industries
  • 170 languages, bounding boxes and per-field confidence scores
  • Low per-thousand-page API pricing; free to try inside Le Chat

Related collections

All collections →