granite-vision-3.2-2b
Model Summary: granite-vision-3.2-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
text + image → text · made by IBM Granite
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| IBM watsonx cloud | standard | $0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-10-31 |
About
granite-vision-3.2-2b — a text model from IBM Granite, sold by one company from $0.1 in and $0.1 out per million tokens.
It takes text and images and returns text. It was published in February 2025. The catalogue files it under ocr and extract. 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 IBM watsonx sells it, at $0.1 in and $0.1 out per million tokens.
Every current figure
- Maker
- IBM Granite
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- February 2025
- Parameters
- 3 billion · read from its own weights
- Licence
- apache-2.0
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.1 in and $0.1 out per million tokens — IBM watsonx
Known as 1 name
ibm-granite/granite-vision-3.2-2b