UI-TARS 7B
UI-TARS 7B is ByteDance's language model with a 131K context window and up to 2K output tokens, starting at $0.100 / 1M input and $0.200 / 1M output. A 7-billion-parameter multimodal vision-language agent from ByteDance optimized for GUI automation across desktop, web, mobile, and gaming environments.
ByteDance's language model with a 131K context window and up to 2K output tokens, starting at $0.100 / 1M input and $0.200 / 1M output. A 7-billion-parameter multimodal vision-language agent from ByteDance optimized for GUI automation across desktop, web, mobile, and gaming environments.Capabilities
Input2/5
✓
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 OpenRouter | $0.100 | $0.200 | $0.100 |
Cost Calculator
Preset:
Compares every provider & tier in USD