Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Financials
Overview
Chunkr is a document intelligence API that turns PDFs, scans and spreadsheets into structured text ready for language models. It handles OCR, layout detection and semantic chunking so retrieval systems receive clean input. Developers use it as the ingestion layer for document-heavy AI applications.
News
Introducing chunkr-layout-1: State Of The Art Document Layout Analysis
A production-ready document layout detection model that accurately extracts tables, images, text blocks, and 16+ layout elements from PDFs across financial, legal, medical, and technical documents-achieving 80.9% mAP@50 and outperforming AWS Textract, Azu
Read more
Report
Introducing chunkr-parse-1-thinking: The best VLM for Document OCR
Introducing chunkr-parse-1-thinking: Purpose Built for Document Understanding
Read more
Report
Building better PDF experiences with Chunkr
How to add Granular citations and in-answer images to RAG with Chunkr
Read more
Report
Why PDFs: From inception to an AI native world (A Brief History)
How a format designed for perfect printing became a huge problem for modern AI.
Read more
Report
Vision RAG sucks - Text is Still King
We benchmarked Vision RAG vs. structured text on 5 top models. Text still reigns, with a 57% lead in accuracy.
Read more
Report
Pro access
Upgrade to see all 7 mentions
Upgrade to a paid plan to read every media mention of this company - funding news, awards, product launches and press releases from all the outlets writing about it.
Every media mention and press release
Funding news, awards and product launches
Fresh coverage from every outlet writing about the company
Upgrade now
Cancel anytime. Secure checkout. Instant activation.
Offices
Where the company hires and what each office is for
Cities
1
Hiring now
0
Countries
1
San Francisco
United States
HQ