# ByteDance: UI-TARS 7B 

Provider: bytedance  
Category: llm  
Model ID: `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. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

## Specs

- Context length: 128000 tokens
- Max output: 2048 tokens
- Modalities: image, text
- Released: 2025-07-22

## Pricing

- Input: $0.10 per million tokens
- Output: $0.20 per million tokens

## Providers

- **bytedance** — ctx 128000, input $0.10/M, output $0.20/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/ui-tars-1-5-7b