ByteDance · language model
UI-TARS 7B: pricing, context and benchmarks
UI-TARS 7B is ByteDance's model released on July 22, 2025. It costs $0.1 per million input tokens and $0.2 per million output tokens, with a 128K-token context window. No independent score has been published for it so far.
| Price | 26/30 | |
|---|---|---|
| Context | 3/15 | |
| Features | 7/15 |
What you need to know about UI-TARS 7B
ByteDance, based in China, put UI-TARS 7B online on July 22, 2025. It accepts images and text as input and produces text. Its context window reaches 128,000 tokens, larger than 19 % of the models in the registry, and it can write up to 2,048 tokens in one go.
It has been available for about 15 months, long enough for its prices and scores to have settled.
UI-TARS 7B pricing
On OpenRouter, UI-TARS 7B costs $0.1 per million input tokens and $0.2 per million output tokens. Counting three tokens read for every token written, its average price is $0.125 per million, more expensive than 13 % of paid models (6.1 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0003. At 1,000 tasks a day, budget $9 a month. The price calculator redoes this with your own volumes.
Tokens already sent and cached are billed at $0.1 per million.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for UI-TARS 7B. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at January 2025.
Its weights are open and downloadable from Hugging Face: you can run it on your own machines without sending your data to a third party.
Verdict
Computed score: 60/100, from public data (performance, price, context, features).
Strengths
- Low price: cheaper than 87 % of paid models.
- Open weights: self-hostable, your data stays with you.
Limitations
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
Avoid if…
- you are building an agent that must call tools.
Alternatives
- Reka Flash 3$0.13
- Qwen2.5 7B Instruct$0.13
- Qwen3 32B$0.13
- Schematron V2 Small$0.1
- gpt-oss-safeguard-20b$0.13
- Llama 3.2 3B Instruct$0.12
Comparisons and tools
Learn more
Frequently asked questions
How much does UI-TARS 7B cost?
$0.1 per million input tokens and $0.2 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0003.
How big is UI-TARS 7B's context window?
128,000 tokens, roughly 96,000 words, with a maximum of 2,048 output tokens.
Can UI-TARS 7B run locally?
Yes, its weights are published.
Is UI-TARS 7B suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to UI-TARS 7B?
The closest models on price and performance are Reka Flash 3, Qwen2.5 7B Instruct, and Qwen3 32B.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score