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...
With CoreAI, you can start chatting with ByteDance: UI-TARS 7B instantly — no separate subscription needed. CoreAI lets you chat with ByteDance: UI-TARS 7B alongside 300+ other AI models from Bytedance and other providers like OpenAI, Anthropic, Google, Meta, and more.
Measured against all 412 chat models CoreAI serves, ByteDance: UI-TARS 7B sits at #344 for context capacity — 128K tokens, roughly 96,000 words or 192 pages of text in a single conversation. On price, it is the #54 cheapest of 134 budget-tier models by input cost. It joined the catalog on 2025-07-22. It accepts image input alongside text.
Every model in this table is available on CoreAI — open the web app and run the same prompt through ByteDance: UI-TARS 7B and Qwen: Qwen3 30B A3B Instruct 2507 side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00020 on ByteDance: UI-TARS 7B 's raw per-token rates; a heavy session with a 50K-token document costs about $0.006. On CoreAI you don't juggle these numbers — one subscription covers ByteDance: UI-TARS 7B and 300+ other models under a plan usage limit, with no API keys. See plans.
ByteDance: UI-TARS 7B handles 128K tokens of context — roughly 96,000 words, or about 192 pages of text in one conversation.
ByteDance: UI-TARS 7B 's underlying rates are $0.1 per 1M input tokens and $0.2 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
Yes — ByteDance: UI-TARS 7B accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.
No — ByteDance: UI-TARS 7B answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick ByteDance: UI-TARS 7B in the model selector, and chat — no API key, no per-token billing. One subscription covers ByteDance: UI-TARS 7B and 300+ other models.
The closest alternatives on CoreAI are Qwen: Qwen3 30B A3B Instruct 2507, IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with ByteDance: UI-TARS 7B and 300+ other AI models — all in one app.