UI-TARS 7B is cataloged under Bytedance / Ui with canonical ID bytedance/ui-tars-1.5-7b.

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. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

Compare

Model information

Released

2025-07-22

Context window

128K

Max output

Model parameters

8.3B

Weights

Open

Modalities

Input

ImageText

Output

Text

Identity

Version: ui-tars-1.5-7b
Knowledge cutoff: 2025-01-31
License: Apache-2.0

Resources

Hugging Face

Capabilities

Open weightStructuredTemperature

Providers

Provider	Provider model ID	Protocol	Context	Max output	Capabilities	Notes	Pricing	Streaming
OpenRouter	bytedance/ui-tars-1.5-7b	openai_chat	128K	2K	AttachmentsStructuredTemperature	Hugging Face: ByteDance-Seed/UI-TARS-1.5-7B	input $0.1/M · output $0.2/M cache read $0.1/M	Yes
Kilo Gateway	bytedance/ui-tars-1.5-7b	openai_chat	128K	2K	AttachmentsStructuredTemperature	-	input $0.1/M · output $0.2/M cache read $0.1/M	Yes
Volcengine Ark	ui-tars-1.5-7b	custom	128K	2K	-	-	-	Yes

Model information

Modalities

Identity

Resources

Capabilities

Providers

FAQ

What is UI-TARS 7B?

Where can I access UI-TARS 7B?

What are the context and output limits?

What can UI-TARS 7B handle?