UI-TARS-1.5-7B

Open weights Active Multimodal Dense ui-tars-1-5-7b

Open 7B vision-language GUI agent model trained with RL for computer, browser and game control.

Released
Apr 16, 2025
Context window
Not disclosed
Max output
Not disclosed
Parameters
7B
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

No first-party API. This is an open-weights release you can run yourself.

Specifications

Developer
ByteDance
Model type
Multimodal
Architecture
Dense
Parameters
7B
Input
Text Image
Output
Text
Knowledge cutoff
Not disclosed
License
Apache License 2.0
API access
No first-party API
Capabilities
Agentic Small LM Vision