Show HN: Open-weight OCR got so cheap I had to share it

A developer built a production-ready OCR service using PaddleOCR-VL-1.6 after finding no trusted provider, achieving a cost of roughly $1 per 1,000 pages. The service undercuts competitors like Mistral OCR 4, which is 4x more expensive, and offers higher quality than Azure Read. The endpoints and a simple dashboard are now publicly available.

This was not supposed to become a product. When PaddleOCR-VL-1.6 dropped, independent benchmarks put it at the top of document parsing models. I had to try it. I needed a provider, but there simply isn't one ready for production that I would trust. So i set one up myself. I assumed that even after getting it running, serving a vision-language model would be expensive. It turns out the opposite is true. Once I had it running properly, the cost was absurdly low. At proper GPU utilization, the cost is only around $1 per 1,000 pages. The nearest competitors are either much lower quality Azure Read or absurdly expensive Extend or Reducto . Even Mistral OCR 4 which is really good and pretty cheap is still 4x more expensive. So I had to share it. I made the endpoitns public, and vibe-coded a simple dashboard. Let me know what you think Comments URL: https://news.ycombinator.com/item?id=49041317 https://news.ycombinator.com/item?id=49041317 Points: 2 Comments: 0