UI-TARS Models by ByteDance
1 model2026Up to 128k ctx
Last refreshed 2026-04-27. Next refresh: weekly.
Details
ResearcherByteDance
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context128k
Capabilities
VisionAll models
MultimodalAll models
JSON / Tool useAll models
Links
WebsiteAbout
UI-TARS is ByteDance's multimodal vision-language agent series optimized for GUI automation across desktop, web, and mobile environments.
Decision facts
- Best fit
- agentsvision and multimodal workJSON / Tool use
- Capability starting point
- UI-TARS 1.5 7B with 128k context and JSON / Tool use and multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Seed
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
UI-TARS 1.5 7BCurrent
Use when the workload needs agents, 128k context, and 7B parameters.
2026-02agents128k context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| UI-TARS 1.5 7B | Use when the workload needs agents, 128k context, and 7B parameters. | 2026-02 | agents128k context7B parameters | Current |
Release Timeline
1 release group2026-02
1 current
UI-TARS 1.5 7B
Currentagents128k context7B parameters
Specifications(1 models)
| Model | Released | Context | Parameters | Vision | Multimodal | JSON / Tool use |
|---|---|---|---|---|---|---|
| UI-TARS 1.5 7B | 2026-02 | 128k | 7B | Yes | Yes | Yes |
