UltraGPT
ByteDance: UI-TARS 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...
Intelligence overview
128K tok
Context window
2.0K tok
Max output
What ByteDance: UI-TARS 7B can do.
Multimodal
Image understanding
Reads and reasons over images alongside text in the same prompt.
Development
Structured output
Returns responses constrained to a JSON schema, ready to parse without cleanup.
Streaming
Streams tokens as they're generated instead of waiting on the full response.
Pay for what you use.
Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.
$0.1 / 1M tok
$0.2 / 1M tok
Built for serious work.
Build
Generate and refactor code, with the ability to return structured, parseable output.
Research
Holds up to 128K tokens of source material in context without losing the thread.
Create
Reads images alongside a prompt to ground creative and design work in what's actually on screen.
Ask ByteDance: UI-TARS 7B anything.
A preview of the real UltraGPT composer — the model you see here is the model you get.
Continues in the UltraGPT app — one login, every model.
How ByteDance: UI-TARS 7B stacks up.
The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.
Technical details.
Specification
- Context window
- 128K tokens
- Max output
- 2.0K tokens
- Input modalities
- Image + Text
- Output modalities
- Text
- Knowledge cutoff
- Jan 31, 2025
- Release date
- Jul 22, 2025
- Streaming
- Supported
- Tool calling
- Not supported
- JSON mode
- Supported
More from ByteDance, and everything else.
This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.