Mistral AI has released OCR 4, a new model that reads text from documents like PDFs, Word files, and PowerPoint presentations.
Unlike earlier versions, OCR 4 doesn't just pull raw text. It also identifies where each element sits on the page and what role it plays - whether it's a title, a table, an equation, or a signature. This block classification helps break documents into meaningful sections automatically, useful for feeding them into search systems or letting AI agents process them. The model also outputs confidence scores, giving an estimate of how certain it is about each word or page it reads.
OCR 4 supports 170 languages and works well even with less common ones, according to Mistral. In a blind test with over 600 documents, independent reviewers preferred OCR 4's results 72 percent of the time over competing models, the company says. The model is available through the API, Mistral Studio, and Microsoft Foundry. It costs $4 per 1,000 pages, or $2 in batch mode.
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。