Model dossier

ByteDance: UI-TARS 7B

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

ProviderByteDance Start comparison

Context128,000

Max output2,048

Pricing viewTVP price

Identity

ByteDance: UI-TARS 7B

Model ID: bytedance/ui-tars-1.5-7b
Canonical slug: bytedance/ui-tars-1.5-7b
Knowledge cutoff: 2025-01-31
Created: 7/22/2025

Capabilities

imagetext

Modalities

text+image->textimagetext

Capacity

Context128,000

Max output2,048

TokenizerOther