ByteDance: UI-TARS 7B

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.

Context
128K
Max output
2K
Input price
$0.1/1M tokens
Output price
$0.2/1M tokens

Capabilities

Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDbytedance/ui-tars-1.5-7b
Provider OpenRouter
Creator ByteDance Seed
Family—
License—
Status—
Type—
Input modalitiesimage, text
Output modalitiestext
Open weight—
Parameters7B
Architecture—
Context window128K tokens
Max input—
Max output2K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Pricing

Input
$0.1
Output
$0.2
Cache write
—
Cache read
$0.1
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/bytedance/ui-tars-1.5-7b

ByteDance: UI-TARS 7B

bytedance/ui-tars-1.5-7b

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games.

Changes · 4 entries
bytedance/ui-tars-1.5-7bupdateca7a400Nov 2, 2026, 03:02 AM
capabilitiesstructured outputyesjson modeyes
bytedance/ui-tars-1.5-7bupdate1867defApr 14, 2026, 10:11 AM
pricingcached input$0.1
bytedance/ui-tars-1.5-7bupdate2b100acMar 23, 2026, 05:30 AM
parameters7
release_date2025-07-22
taglineUI-TARS-1.5 is a multimodal vision-language agent optimiz...
bytedance/ui-tars-1.5-7bcreate7f5c66fMar 21, 2026, 05:16 AM