Hacker News new | ask | show | jobs
by dontlikeyoueith 469 days ago
AWS Textract works pretty well for this and is much cheaper than running LLMs.
1 comments

Textract is more expensive than this (for your first 1M pages per month at least) and significantly more than something like Gemini Flash. I agree it works pretty well though - definitely better than any of the open source pure OCR solutions I've tried.