跳到正文
The Decoder· Jonathan Kemper·· 11 小時前AI 評分52

OCR 模型數碼化一百萬頁成本低於 $130,18 個月內降至五分之一

OCR models now digitize a million pages for under $130 as costs drop fivefold in 18 months

AI 導讀

免費提供的 AI OCR 模型數碼化一百萬頁,GPU 租用成本現為 $65 至 $130;18 個月內,每千頁成本由舊模型約 51 美仙降至新模型不足 10 美仙。

正文

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.

Liniendiagramm zeigt die Kosten pro 1.000 Seiten für acht offene OCR-Modelle nach Erscheinungsdatum von April 2025 bis Oktober 2026, von 0,51 Dollar bei RolmOCR bis 0,095 Dollar bei LightOnOCR-3-0.8B, dazu eine gestrichelte Trendlinie bis Ende 2027.

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.

AI News Without the Hype – Curated by Humans

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.

來源:The Decoder · the-decoder.com