UI-TARS 7B
Summary
UI-TARS 7B is an open-weight language model from Bytedance, released on 22 Jul 2025. It accepts images and text and generates text, with a 128K-token context window and up to 2K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $0.10 per million input tokens and $0.20 per million output tokens (OpenRouter), across 1 provider we track.
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...
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Bytedance |
|---|---|
| Release date | 22 Jul 2025 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 8.3B [Hugging Face] |
| Context window | 128K (128,000 tokens) [OpenRouter] |
| Max output | 2K tokens [OpenRouter] |
| Knowledge cutoff | 31 Jan 2025 [OpenRouter] |
| Input | Images and text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | No [OpenRouter] |
| Tool calling | No [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Hugging Face | ByteDance-Seed/UI-TARS-1.5-7B [Hugging Face] |
UI-TARS 7B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter bytedance/ui-tars-1.5-7b | $0.10 | $0.20 | $0.10 | 128K | OpenRouter, 19 Nov 2026 |
Running UI-TARS 7B locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 5.0 GB | 6.3 GB | 7.7 GB |
| Q8_0 (8-bit) | 8.8 GB | 10 GB | 11 GB |
| FP16 / BF16 (16-bit) | 17 GB | 18 GB | 19 GB |
At 4-bit with an 8K conversation, UI-TARS 7B needs about 6.3 GB, so it fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. Check your own hardware, or see Running local LLMs on an 8 GB GPU on our sister site AIPCs.
Frequently asked questions
What is the context window of UI-TARS 7B?
UI-TARS 7B has a context window of 128,000 tokens (128K) and can generate up to 2,048 tokens in a single response, according to OpenRouter.
How much does the UI-TARS 7B API cost?
UI-TARS 7B is listed from $0.10 per million input tokens and $0.20 per million output tokens (OpenRouter). Prices last verified 19 Nov 2026.
Is UI-TARS 7B open source?
UI-TARS 7B is an open-weight model: its weights are published on Hugging Face as ByteDance-Seed/UI-TARS-1.5-7B under the apache-2.0 license. Check the license terms before commercial use.
When was UI-TARS 7B released?
Bytedance released UI-TARS 7B on 22 Jul 2025, according to OpenRouter.
How much VRAM does UI-TARS 7B need?
About 6.3 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 10 GB at 8-bit. The 4-bit model fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Nvidia Nemotron Nano 9B V2 | NVIDIA | 18 Aug 2025 | 131K | $0.06 | $0.23 | Open |
| ERNIE 4.5 21B A3B | Baidu | 30 Jun 2025 | 120K | $0.07 | $0.28 | Open |
| GPT OSS 120B | OpenAI | 5 Aug 2025 | 131K | $0.04 | $0.17 | Open |
| GPT OSS Safeguard 20B | OpenAI | 29 Oct 2025 | 131K | $0.07 | $0.20 | Open |
| Baichuan M2 32B | Baichuan | 13 Aug 2025 | 131K | $0.07 | $0.07 | Open |
| Llama Guard 4 12B | Meta | 29 Apr 2025 | 164K | $0.18 | $0.18 | Open |
Change history
No changes detected since we started tracking this model. We re-check every source daily.