AI Agent Hub
Back to models
🤖

ByteDance: UI-TARS 7B

Closed Source bytedance
0.0 / 10 128K context Proprietary

About this model

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...

Technical Specs

  • Architecture: text+image->text
  • Context Window: 128,000 tokens
  • Input Modalities: text

Hardware Requirements

  • API-only (no local hardware needed)

Pricing

Input Output Currency
0.1 / 1M tokens 0.2 / 1M tokens USD