UI-TARS 72B

About UI-TARS 72B

UI-TARS 72B is an open-source multimodal AI model designed specifically for automating browser and desktop tasks through visual interaction and control. The model is built with a specialized vision architecture enabling accurate interpretation and manipulation of on-screen visual data. It supports automation tasks within web browsers as well as desktop applications, including Microsoft Office and VS Code. Core capabilities include intelligent screen detection, predictive action modeling, and efficient handling of repetitive interactions. UI-TARS employs supervised fine-tuning (SFT) tailored explicitly for computer control scenarios. It can be deployed locally or accessed via Hugging Face for demonstration purposes. Intended use cases encompass workflow automation, task scripting, and interactive desktop control applications.

Model Specifications

ByteDance Model Lineup

Compare all models from ByteDance to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Gemma 3n 4B

Google

Input: Free

Output: Free

Context: 33k

Qwen2.5-VL 7B Instruct

Alibaba Qwen

Input: Free

Output: Free

Context: 33k

FLUX.2 Max

Black Forest Labs

Input: Free

Output: Free

Context: 47k

Riverflow V2 Max Preview

Other

Input: Free

Output: Free

Context: 8k

🚀 Quick Start

Get started with UI-TARS 72B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="bytedance-research/ui-tars-72b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision