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 learning-based reasoning, enabling robust action planning and execution across virtual interfaces. This model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.

ChatByteDance128k tokens$0.109 / $0.218 · 1M

bytedance/ui-tars-1.5-7b

Context
128k tokens
Completion cap
2,048
Tools
No
JSON
Yes
Released
2025-07-22

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bytedance/ui-tars-1.5-7b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 learning-based reasoning, enabling robust action planning and execution across virtual interfaces. This model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints. UI-TARS 7B runs on the Geek Hub API (OpenAI-compatible). Model id: bytedance/ui-tars-1.5-7b.
Is UI-TARS 7B free?
No. Input is $0.109 per 1M tokens and output is $0.218 per 1M tokens on Geek Hub (markup included).
What is the context length of UI-TARS 7B?
UI-TARS 7B has a 128k tokens context window. It supports up to 2,048 completion tokens.
Does UI-TARS 7B support tool calling and structured outputs?
UI-TARS 7B does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was UI-TARS 7B released?
UI-TARS 7B was released on 2025-07-22.