Agents · Apr 2025

UI-TARS 1.5 7B

GUI agent model that can operate computer interfaces autonomously.

By ByteDance · Text + Vision · Apache 2.0

Context

128K tokens

Modality

Text + Vision

Architecture

Dense

License

Apache 2.0

Per 1M tokens $0.10 in · $0.20 out
Model details

Specs & substance

Developed by
ByteDance
Model family
UI-TARS
Use case
Agents
Modality
Text + Vision
Context window
128K tokens
Architecture
Dense
Version
1.5
License
Apache 2.0
Pricing
$0.10 in · $0.20 out · $0.10 cache read
Released
Apr 2025
Endpoint
parasail-ui-tars-1p5-7b

GUI agent model that can operate computer interfaces autonomously.

UI-TARS 1.5 7B is part of the UI-TARS family by ByteDance, and sits in the agents category. It supports a 128K tokens context window and is built on a Dense architecture.

Key strengths: agentic, gui. Parasail serves UI-TARS 1.5 7B on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.

Integrate

Drop-in via the OpenAI SDK

Point any OpenAI-compatible client at Parasail and change the model name. That's it.

python parasail · UI-TARS 1.5 7B
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parasail.io/v1"
)

response = client.chat.completions.create(
    model="parasail-ui-tars-1p5-7b",
    messages=[
        {"role": "user", "content": "Hello, what can you do?"}
    ],
    stream=True,
    max_tokens=1000
)

for chunk in response:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)
More models

Explore the library

All models

Start building today

Instantly run any open model — popular or specialized.