Pass IndexThe State of AISign in

RolmOCR

Earlier this year, the Allen Institute for AI released olmOCR, an open-source tool that performs document OCR using the Qwen2-VL-7B vision language model (VLM).

text + image → text · made by Reducto

$0.2$0.2per Mtok in / out
Fireworks AI

Sold by 1 way

SellerLaneRate
Fireworks AI aggregatorstandard$0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16

About

RolmOCR — a text model from Reducto, sold by one company from $0.2 in and $0.2 out per million tokens.

It takes text and images and returns text. It was published in April 2025. The catalogue files it under ocr. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest. Only Fireworks AI sells it, at $0.2 in and $0.2 out per million tokens.

Every current figure

Maker
Reducto
Register
model
Takes
text + image
Returns
text
Published
April 2025
Parameters
8.3 billion · read from its own weights
Licence
apache-2.0
Sellers
1
Maker's own price
not read
Price
$0.2 in and $0.2 out per million tokens — Fireworks AI

Known as 1 name

reducto/RolmOCR