Open OCR Costs Fall Fivefold in 18 Months to $130 per Million Pages
Hugging Face's Daniel van Strien benchmarked eight open OCR models on identical GPU hardware, finding per-1,000-page cost fell from about 51 cents for April 2025's RolmOCR to under 10 cents for October 2026's LightOnOCR-3-0.8B, a roughly fivefold drop in 18 months. At that rate, digitizing a million pages now costs $65 to $130 in GPU rental, sharply lowering the barrier to large-scale book and archive digitization.
Related Entities
Full Report
OCR models now digitize a million pages for under $130 as costs drop fivefold in 18 months
[Jonathan Kemper](https://the-decoder.com/author/jonathan-kemper/) [View the LinkedIn Profile of Jonathan Kemper](https://www.linkedin.com/in/jonathankemper/) Nov 19, 2026 Pulling text out of scanned books and records has gotten a lot cheaper with freely available AI models. Daniel van Strien of Hugging Face compared eight such models that recognize text in images. He tested them on 850 pages from old natural history books, the 1771 Encyclopaedia Britannica, and typed and printed archival documents. All models ran on the same GPU, an Nvidia RTX PRO 6000 that van Strien rented through Hugging Face for $2.75 per hour. At the same image size, the oldest model from April 2025 (RolmOCR) cost about 51 cents per 1,000 pages. The newest from October 2026 (LightOnOCR-3-0.8B) came in at just under 10 cents. A million pages now runs between $65 and $130 in GPU rental, depending on the source material.
According to van Strien, optimizing how the models ran saved about as much money as switching to newer models did, if not more. That meant feeding pages more evenly, using smaller scans, updating software, and running a faster GPU. The newest model read book pages at least as accurately as the oldest one. Some models, though, hallucinated text on blank pages or repeated the same content over and over.

The cost of scanning 1,000 pages has dropped from 51 cents for the oldest model to just under 10 cents for the newest one; the five models in between are almost on par with each other.