ByteDance
UI-TARS 7B
Multimodal model for analyzing text, images, documents, and rich media
Model facts
- Context window
- 128K tokens
- Maximum output
- 2K tokens
- Cheapest paid input
- $0.1 per 1M tokens
- Cheapest paid output
- $0.2 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
structured output, attachments, temperature control, open weights, text, image.
Observed price history
- 2026-08-24: $0.1 input / $0.2 output per 1M tokens
API providers
- OpenRouter — model id bytedance/ui-tars-1.5-7b; $0.1 input / $0.2 output per 1M tokens; provider documentation
- Kilo Gateway (ByteDance) — model id bytedance/ui-tars-1.5-7b; $0.1 input / $0.2 output per 1M tokens; provider documentation