UI-Venus-1.5-2B
Compared to our previous version(UI-Venus 1.0), UI-Venus-1.5 introduces three key technical advances: - Mid-Training Stage: 10B tokens across 30+ datasets for foundational GUI semantics - Online RL: Full-trajectory rollouts for long-horizon dynamic navigation - Model Merging: Unified agent combining grounding, web, and mobile specialists.
text + image → text · made by InclusionAI
Sold by
Nobody in the catalogue publishes a price for this yet.
About
UI-Venus-1.5-2B — a text model from InclusionAI.
It takes text and images and returns text. It was published in February 2026. The catalogue files it under search. 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.
Every current figure
- Maker
- InclusionAI
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- February 2026
- Parameters
- 2.4 billion · read from its own weights
- Licence
- apache-2.0
Known as 1 name
inclusionAI/UI-Venus-1.5-2B