ns
← All models

olmOCR 2 7B

olmocr

Vision-language OCR model from Ai2 (Allen Institute for AI) that extracts text from documents where tables, equations, and poor-quality scans defeat traditional OCR

Family
olmocr
Providers
1
Context
16,384
Output
—
Knowledge
-
Weights
Open
Input
textimage
Output
text
Release date
2025-10-22
Updated
2025-10-22

Providers

Source: models.dev