bytedance

UI-TARS 7B

bytedance/ui-tars-1.5-7b

Ratings & Rankings

Input Cost

$0.1000

84/100

Output Cost

$0.2000

89/100

Context Window

128K

12/100

Overall

62/100

Key Specifications

Context Window128K

Max Output2K

TokenizerOther

Input Modalitiesimage, text

Output Modalitiestext

Pricing

Input (per M tokens)$0.1000per million tokens

Output (per M tokens)$0.2000per million tokens

Input & Output

You send

imagetext

You get

text

Capabilities

✗Function calling

✗Structured outputs

✓Unmoderated

About

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...

Supported parameters

frequency_penaltylogit_biasmax_tokenspresence_penaltyrepetition_penaltyseedstoptemperaturetop_ktop_p