modelhub.help

UI-TARS 7B

ByteDanceOpen-weight

128K context · — params · —

bytedance/ui-tars-1-5-7b

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...

Cheapest blended: ¥0.125 / 1M tokens on ByteDance Doubao (Volcengine)Get custom quote

Reachability & verification

Live reachability

Probing…

Target (ByteDance Doubao (Volcengine)): https://ark.cn-beijing.volces.com/api/v3

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Pricing across providers

1

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

ProviderInput /1MOutput /1MBlendedCtxp50 latencyAPIVerified
ByteDance Doubao (Volcengine)ui-tars-1.5-7b¥0.1¥0.2¥0.125128K OAI119d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

Code samplesExample usingByteDance Doubao (Volcengine)— the cheapest hosting for this model as of last verification. Swapbase_urlandmodelto use a different provider from the matrix above.PythoncURLNode.jsCopyfrom openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://ark.cn-beijing.volces.com/api/v3", ) response = client.chat.completions.create( model="ui-tars-1.5-7b", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)

Code samples

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://ark.cn-beijing.volces.com/api/v3",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="ui-tars-1.5-7b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
cURL
curl https://ark.cn-beijing.volces.com/api/v3/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ui-tars-1.5-7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://ark.cn-beijing.volces.com/api/v3",
  apiKey: "YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "ui-tars-1.5-7b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Technical specs

Context

128K

Max output

2K

Parameters

Release

Training cutoff

License

Similar models

Frequently asked questions

How much does UI-TARS 7B cost?

The cheapest tracked blended price is ¥0.125 per 1M tokens on ByteDance Doubao (Volcengine). See the pricing matrix above for input/output splits per provider.

Can I use UI-TARS 7B from outside China?

Availability depends on the hosting provider. Use our Path Planner on the ByteDance Doubao (Volcengine) page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is UI-TARS 7B open source?

Yes — UI-TARS 7B is open-weight under the — license. You can self-host it or use any listed inference provider.

Is UI-TARS 7B OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

UI-TARS 7B supports up to 128K tokens of context with a maximum output of 2K tokens.

Need verified access to UI-TARS 7B?

We broker vetted intros to ByteDance Doubao (Volcengine) — payment, KYC and endpoint verification handled.

Request a brokerage intro