Browser Use Model - BU 2.0
+12% accuracy. Same speed. No tradeoffs.
BU 2.0 is here.
- +12% accuracy over BU 1.0 (74.7% → 83.3%)
- Similar speed — ~62s average task duration
- Matches Claude Opus 4.5 accuracy while being 40% faster
Benchmark Results
| Model | Accuracy | Avg Task Duration |
|---|---|---|
| BU 2.0 | 83.3% | 62s |
| BU 1.0 | 74.7% | 58s |
| Claude Opus 4.5 | 82.3% | 104s |
| Gemini 3 Pro | 81.7% | 143s |
| GPT-5.2 | 70.9% | 196s |
Pricing
| Model | Input | Cached | Output |
|---|---|---|---|
| bu-1-0 / bu-latest | $0.20/1M | $0.02/1M | $2.00/1M |
| bu-2-0 | $0.60/1M | $0.06/1M | $3.50/1M |
Quick Start
import asyncio
from browser_use import Agent
from browser_use.llm import ChatBrowserUse
async def main():
# Use the new bu-2-0 model
llm = ChatBrowserUse(model="bu-2-0")
agent = Agent(
task="Your task here",
llm=llm
)
result = await agent.run()
return result
asyncio.run(main())Get your API key at cloud.browser-use.com.