UI-TARS
language modelByteDance
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...
Key facts
| Made by | ByteDance |
|---|---|
| Type | language model |
| Released | July 22, 2025 |
| Reads at once | 128,000 tokens |
| Price (API, per million tokens) | $0.1 in · $0.2 out |
| Input → output | image, text → text |
| Sizes | 7B |
Questions about UI-TARS
Who makes UI-TARS?
UI-TARS is made by ByteDance.
When was UI-TARS released?
We first saw UI-TARS listed on July 22, 2025.
How much does UI-TARS cost?
Through OpenRouter it costs $0.1 per million input tokens and $0.2 per million output tokens. Prices change, so check the provider before you build on it.
How much text can UI-TARS read at once?
Up to 128,000 tokens, roughly 96K words.
More from ByteDance
SDXL-LightningByteDance · image model
Feb 20, 2024released
Seed 2.1 TurboByteDance · language model
Aug 12, 2026released
Seed-2.0-CodeByteDance · coding model
Aug 12, 2026released
Seed-2.0-LiteByteDance · language model
Mar 10, 2026released
Seed-2.0-MiniByteDance · language model
Feb 26, 2026released
Seed 1.6 FlashByteDance · language model
Dec 23, 2025released
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with ByteDance.