BROWSER USE

Products:
- [Browser Harness](https://browser-harness.com)
- [Stealth Browsers](https://browser-use.com/stealth-browsers)
- [Browser Use Box](https://browser-use.com/bux)
- [Web Agents](https://browser-use.com/web-agents)
- [Custom Models](https://browser-use.com/custom-models)
- [Proxies](https://browser-use.com/proxies)

[Pricing](https://browser-use.com/pricing)
[Blog](https://browser-use.com/posts)
[Cloud Docs](https://docs.cloud.browser-use.com)
[Open Source Docs](https://docs.browser-use.com)

[GET STARTED](https://cloud.browser-use.com)
[GITHUB](https://github.com/browser-use/browser-use)

---

# Our First Open-Source LLM

**Date:** 2025-12-16
> 30B params, 3B active. 200 tasks per $1.

---

![BU-30B-A3B-Preview benchmark](https://browser-use.com/images/changelog/bu-30b-benchmark.png)

BU-30B-A3B-Preview is here. 

- **30B total parameters** with only **3B active** at inference time
- **200 tasks per $1** — 4x more cost-efficient than BU 1.0
 
Try it out on the library or on our cloud:

```python
from browser_use import Agent
from browser_use.llm import ChatBrowserUse
 
# Initialize with the new model
llm = ChatBrowserUse(model="bu-30b-a3b-preview")
 
agent = Agent(
    task="Your task here",
    llm=llm
)
 
result = await agent.run()
```
 
Download from [Hugging Face](https://huggingface.co/browser-use/bu-30b-a3b-preview).