Zerox — Zero-Shot PDF OCR for AI Pipelines

What is Zerox?

Zerox is a zero-shot PDF OCR tool that replaces traditional OCR with vision-language models. Converts PDF pages to images and uses GPT-4o or Claude to extract clean Markdown.

In one sentence: Vision model OCR — PDF to Markdown with GPT-4o/Claude/Gemini, handles complex layouts and tables — 7k+ stars.

For: Teams building RAG pipelines or handling PDFs.

Core Features

1. Multi-Model Support

Works with GPT-4o, Claude, and Gemini.

2. Page Selection

Process specific pages.

3. Custom Prompts

Customize extraction format.

FAQ

Q: How much does it cost? A: About $0.01 per page with GPT-4o-mini.

Q: Does it handle scans? A: This is its main use case — vision models read scanned text and handwriting.