UI-TARS 72B – Multimodal AI for Desktop & Browser Automation
UI-TARS 72B is a powerful multimodal AI model from Bytedance, purpose-built for automating desktop and web browser tasks using visual understanding and screen interaction. With 72 billion parameters and a specialized vision architecture, it can intelligently detect UI elements, predict actions, and control applications like Microsoft Office, VS Code, and more. Key capabilities: 🖥️ Screen-aware…
11 subscribers
1 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
UI-TARS 72B – Multimodal AI for Desktop & Browser Automation endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Chat Completions /bytedance-ui/chat |
add your prompt and interact with model |
UI-TARS 72B – Multimodal AI for Desktop & Browser Automation pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $5 / month | — |
|
| ULTRA | $15 / month | — |
|
| MEGA | $30 / month | — |
|
