​
Recommendations

  • Best accuracy: O3
  • Fastest: llama4 on groq
  • Balanced: fast + cheap + clever: gemini-flash-latest or gpt-4.1-mini

​
OpenAI example

O3 model is recommended for best performance. 
from browser_use import Agent, ChatOpenAI

# Initialize the model
llm = ChatOpenAI(
    model="o3",
)

# Create agent with the model
agent = Agent(
    task="...", # Your task here
    llm=llm
)
Required environment variables:
.env
OPENAI_API_KEY=
You can use any OpenAI compatible model by passing the model name to the ChatOpenAI class using a custom URL (or any other parameter that would go into the normal OpenAI API call).

​
Anthropic example

from browser_use import Agent, ChatAnthropic

# Initialize the model
llm = ChatAnthropic(
    model="claude-sonnet-4-0",
)

# Create agent with the model
agent = Agent(
    task="...", # Your task here
    llm=llm
)
And add the variable:
.env
ANTHROPIC_API_KEY=

​
Azure OpenAI example

from browser_use import Agent, ChatAzureOpenAI
from pydantic import SecretStr
import os

# Initialize the model
llm = ChatAzureOpenAI(
    model="o4-mini",
)

# Create agent with the model
agent = Agent(
    task="...", # Your task here
    llm=llm
)
Required environment variables:
.env
AZURE_OPENAI_ENDPOINT=https://your-endpoint.openai.azure.com/
AZURE_OPENAI_API_KEY=

​
Gemini example

[!IMPORTANT] GEMINI_API_KEY was the old environment var name, it should be called GOOGLE_API_KEY as of 2025-05. 
from browser_use import Agent, ChatGoogle
from dotenv import load_dotenv

# Read GOOGLE_API_KEY into env
load_dotenv()

# Initialize the model
llm = ChatGoogle(model='gemini-flash-latest')

# Create agent with the model
agent = Agent(
    task="Your task here",
    llm=llm
)
Required environment variables:
.env
GOOGLE_API_KEY=

​
AWS Bedrock example

AWS Bedrock provides access to multiple model providers through a single API. We support both a general AWS Bedrock client and provider-specific convenience classes.

​
General AWS Bedrock (supports all providers)

from browser_use import Agent, ChatAWSBedrock

# Works with any Bedrock model (Anthropic, Meta, AI21, etc.)
llm = ChatAWSBedrock(
    model="anthropic.claude-3-5-sonnet-20240620-v1:0",  # or any Bedrock model
    aws_region="us-east-1",
)

# Create agent with the model
agent = Agent(
    task="Your task here",
    llm=llm
)

​
Anthropic Claude via AWS Bedrock (convenience class)

from browser_use import Agent, ChatAnthropicBedrock

# Anthropic-specific class with Claude defaults
llm = ChatAnthropicBedrock(
    model="anthropic.claude-3-5-sonnet-20240620-v1:0",
    aws_region="us-east-1",
)

# Create agent with the model
agent = Agent(
    task="Your task here",
    llm=llm
)

​
AWS Authentication

Required environment variables:
.env
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_DEFAULT_REGION=us-east-1
You can also use AWS profiles or IAM roles instead of environment variables. The implementation supports:
  • Environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION)
  • AWS profiles and credential files
  • IAM roles (when running on EC2)
  • Session tokens for temporary credentials
  • AWS SSO authentication (aws_sso_auth=True)

​
Groq example

from browser_use import Agent, ChatGroq

llm = ChatGroq(model="meta-llama/llama-4-maverick-17b-128e-instruct")

agent = Agent(
    task="Your task here",
    llm=llm
)
Required environment variables:
.env
GROQ_API_KEY=

​
Ollama

  1. Install Ollama: https://github.com/ollama/ollama
  2. Run ollama serve to start the server
  3. In a new terminal, install the model you want to use: ollama pull llama3.1:8b (this has 4.9GB)
from browser_use import Agent, ChatOllama

llm = ChatOllama(model="llama3.1:8b")

​
Langchain

Example on how to use Langchain with Browser Use.

​
Qwen example

Currently, only qwen-vl-max is recommended for Browser Use. Other Qwen models, including qwen-max, have issues with the action schema format. Smaller Qwen models may return incorrect action schema formats (e.g., actions: [{"go_to_url": "google.com"}] instead of [{"go_to_url": {"url": "google.com"}}]). If you want to use other models, add concrete examples of the correct action format to your prompt. 
from browser_use import Agent, ChatOpenAI
from dotenv import load_dotenv
import os

load_dotenv()

# Get API key from https://modelstudio.console.alibabacloud.com/?tab=playground#/api-key
api_key = os.getenv('ALIBABA_CLOUD')
base_url = 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1'

llm = ChatOpenAI(model='qwen-vl-max', api_key=api_key, base_url=base_url)

agent = Agent(
    task="Your task here",
    llm=llm,
    use_vision=True
)
Required environment variables:
.env
ALIBABA_CLOUD=

​
ModelScope example

from browser_use import Agent, ChatOpenAI
from dotenv import load_dotenv
import os

load_dotenv()

# Get API key from https://www.modelscope.cn/docs/model-service/API-Inference/intro
api_key = os.getenv('MODELSCOPE_API_KEY')
base_url = 'https://api-inference.modelscope.cn/v1/'

llm = ChatOpenAI(model='Qwen/Qwen2.5-VL-72B-Instruct', api_key=api_key, base_url=base_url)

agent = Agent(
    task="Your task here",
    llm=llm,
    use_vision=True
)
Required environment variables:
.env
MODELSCOPE_API_KEY=

​
Other models (DeepSeek, Novita, X…)

We support all other models that can be called via OpenAI compatible API. We are open to PRs for more providers. Examples available: