PDF Chunker for LLM Processing

Split large PDFs into manageable chunks for LLM processing

API Documentation Previous Splits

Upload PDF URL

Enter a URL to a publicly accessible PDF file. ArXiv papers work well!
Recommended: 1,500-2,000 tokens ≈ 2,000-3,000 characters.

Physical PDF Splitting

Split a PDF into smaller PDFs while preserving all content including images and formatting:

Enter a URL to a publicly accessible PDF file.
Number of pages to include in each split PDF file.

Recent PDF Splits

View All
Whispers%20in%20the%20Fog.pdf
2025-10-27 13:11

10 pages split into 1 files

Pages 1-10
Nova_Outlaw_Chapter_1.pdf
2025-10-24 20:50

2 pages split into 1 files

Pages 1-2
Nova_Outlaw_Chapter_1.pdf
2025-10-24 19:45

2 pages split into 1 files

Pages 1-2
The_Starblade_and_the_Whispering_Forest.pdf
2025-10-24 17:32

22 pages split into 1 files

Pages 1-22
fantasy_storybook.pdf
2025-10-21 13:26

5 pages split into 1 files

Pages 1-5

API Usage

You can also use our API to process PDFs programmatically:

Text Extraction API:
curl -X POST -H "Content-Type: application/json" \
    -d '{"pdf_url": "https://arxiv.org/pdf/1706.03762.pdf", "chunk_strategy": "fixed", "chunk_size": 2000}' \
    https://pdf.betadev.biz/api/process
Physical PDF Splitting API:
curl -X POST -H "Content-Type: application/json" \
    -d '{"pdf_url": "https://arxiv.org/pdf/1706.03762.pdf", "pages_per_split": 200}' \
    https://pdf.betadev.biz/api/split-pdf
Retrieving Previous Splits:
curl https://pdf.betadev.biz/api/splits
View Full API Documentation:
API Documentation