Supported Models

Browser Use natively supports 15+ LLM providers. Most providers accept any model string. Check each provider’s docs to see which models are available.

Which model should I use? See our benchmark results and recommendations for detailed comparisons across real-world browser tasks.

Browser Use example

ChatBrowserUse() is our optimized in-house model, matching the accuracy of top models while completing tasks 3-5x faster. See our blog post→

Read the bu-2-0 model card for details on intended use, inputs and outputs, tools, benchmarks, judge setup, and limitations.

from browser_use import Agent, ChatBrowserUse

# Initialize the model - defaults to bu-latest (bu-2-0)
llm = ChatBrowserUse()

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

Required environment variables:

.env

BROWSER_USE_API_KEY=

Get your API key from the Browser Use Cloud. New users get 5 free tasks.

Pricing

ChatBrowserUse offers competitive pricing per 1 million tokens: bu-2-0 / bu-latest (Default)

Token Type	Price per 1M tokens
Input tokens	$0.60
Cached tokens	$0.06
Output tokens	$3.50

bu-1-0 Since May 20, 2026, bu-1-0 is priced the same as bu-2-0:

Token Type	Price per 1M tokens
Input tokens	$0.60
Cached tokens	$0.06
Output tokens	$3.50

Google Gemini example

Available models. Also supports Gemma models and Vertex AI via ChatGoogle(model="...", vertexai=True).

GEMINI_API_KEY is deprecated and should be named 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-2.5-flash')

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

Required environment variables:

.env

GOOGLE_API_KEY=

OpenAI example

Available models

from browser_use import Agent, ChatOpenAI

# Initialize the model
llm = ChatOpenAI(
    model="gpt-5",
)

# 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

Available models. Coordinate clicking is automatically enabled for claude-sonnet-4-* and claude-opus-4-* models.

from browser_use import Agent, ChatAnthropic

# Initialize the model
llm = ChatAnthropic(
    model="claude-sonnet-4-6",
)

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

And add the variable:

.env

ANTHROPIC_API_KEY=

Azure OpenAI example

Available models

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=

Using the Responses API (for GPT-5.1 Codex models)

Azure OpenAI now requires api_version >= 2025-03-01-preview for certain models like gpt-5.1-codex-mini. These models only support the Responses API instead of the Chat Completions API.

Browser Use automatically detects and uses the Responses API for these models:

gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max
gpt-5-codex, codex-mini-latest
computer-use-preview

from browser_use import Agent, ChatAzureOpenAI

# Auto-detection (recommended) - uses Responses API for gpt-5.1-codex-mini
llm = ChatAzureOpenAI(
    model="gpt-5.1-codex-mini",
    api_version="2025-03-01-preview",  # Required for Responses API
)

# Or explicitly enable/disable Responses API for any model
llm = ChatAzureOpenAI(
    model="gpt-4o",
    api_version="2025-03-01-preview",
    use_responses_api=True,  # Force Responses API (True/False/'auto')
)

agent = Agent(
    task="...",
    llm=llm
)

The use_responses_api parameter accepts:

'auto' (default): Automatically uses Responses API for models that require it
True: Force use of the Responses API
False: Force use of the Chat Completions API

AWS Bedrock example

Available models. 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. Install with pip install "browser-use[aws]".

General AWS Bedrock (supports all providers)

from browser_use import Agent
from browser_use.llm import 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
from browser_use.llm import 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

Available models

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=

Oracle Cloud Infrastructure (OCI) example

Available models. OCI provides access to various generative AI models including Meta Llama, Cohere, and other providers through their Generative AI service. Install with pip install "browser-use[oci]".

from browser_use import Agent, ChatOCIRaw

# Initialize the OCI model
llm = ChatOCIRaw(
    model_id="ocid1.generativeaimodel.oc1.us-chicago-1.amaaaaaask7dceya...",
    service_endpoint="https://inference.generativeai.us-chicago-1.oci.oraclecloud.com",
    compartment_id="ocid1.tenancy.oc1..aaaaaaaayeiis5uk2nuubznrekd...",
    provider="meta",  # or "cohere"
    temperature=0.7,
    max_tokens=800,
    top_p=0.9,
    auth_type="API_KEY",
    auth_profile="DEFAULT"
)

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

Required setup:

Set up OCI configuration file at ~/.oci/config
Have access to OCI Generative AI models in your tenancy
Install the OCI Python SDK: uv add oci or pip install oci

Authentication methods supported:

API_KEY: Uses API key authentication (default)
INSTANCE_PRINCIPAL: Uses instance principal authentication
RESOURCE_PRINCIPAL: Uses resource principal authentication

Ollama

Available models.

Install Ollama: https://github.com/ollama/ollama
Run ollama serve to start the server
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: [{"navigate": "google.com"}] instead of [{"navigate": {"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=

Vercel AI Gateway example

Available models. Vercel AI Gateway provides an OpenAI-compatible API endpoint that acts as a proxy to various AI providers, with features like rate limiting, caching, and monitoring.

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

load_dotenv()

# Get API key (https://vercel.com/ai-gateway)
api_key = os.getenv('VERCEL_API_KEY')
if not api_key:
    raise ValueError('VERCEL_API_KEY is not set')

# Basic usage
llm = ChatVercel(
    model='openai/gpt-4o',
    api_key=api_key,
)

# With provider options - control which providers are used and in what order
# This will try Vertex AI first, then fall back to Anthropic if Vertex fails
llm_with_provider_options = ChatVercel(
    model='anthropic/claude-sonnet-4',
    api_key=api_key,
    provider_options={
        'gateway': {
            'order': ['vertex', 'anthropic']  # Try Vertex AI first, then Anthropic
        }
    },
)

agent = Agent(
    task="Your task here",
    llm=llm
)

Required environment variables:

.env

VERCEL_API_KEY=

DeepSeek example

Available models

from browser_use import Agent, ChatDeepSeek

llm = ChatDeepSeek(model="deepseek-chat")

agent = Agent(
    task="Your task here",
    llm=llm
)

Required environment variables:

.env

DEEPSEEK_API_KEY=

Mistral example

Available models

from browser_use import Agent, ChatMistral

llm = ChatMistral(model="mistral-large-latest")

agent = Agent(
    task="Your task here",
    llm=llm
)

Required environment variables:

.env

MISTRAL_API_KEY=

Cerebras example

Available models

from browser_use import Agent, ChatCerebras

llm = ChatCerebras(model="llama3.3-70b")

agent = Agent(
    task="Your task here",
    llm=llm
)

Required environment variables:

.env

CEREBRAS_API_KEY=

OpenRouter example

Available models. Access 300+ models from any provider through a single API.

from browser_use import Agent, ChatOpenRouter

llm = ChatOpenRouter(model="anthropic/claude-sonnet-4-6")

agent = Agent(
    task="Your task here",
    llm=llm
)

Required environment variables:

.env

OPENROUTER_API_KEY=

LiteLLM

Requires separate install (pip install litellm). Supports any LiteLLM model string — useful when you need a provider not covered by the native integrations above.

from browser_use import Agent
from browser_use.llm.litellm import ChatLiteLLM

llm = ChatLiteLLM(model="openai/gpt-5")

agent = Agent(
    task="Your task here",
    llm=llm
)

Other OpenAI-Compatible Providers

Any provider with an OpenAI-compatible endpoint works via ChatOpenAI with a custom base_url: Examples available:

Novita

Get Started

Customize

Examples

Development

Browser Use example

Pricing

Google Gemini example

OpenAI example

Anthropic example

Azure OpenAI example

Using the Responses API (for GPT-5.1 Codex models)

AWS Bedrock example

General AWS Bedrock (supports all providers)

Anthropic Claude via AWS Bedrock (convenience class)

AWS Authentication

Groq example

Oracle Cloud Infrastructure (OCI) example

Ollama

Langchain

Qwen example

ModelScope example

Vercel AI Gateway example

DeepSeek example

Mistral example

Cerebras example

OpenRouter example

LiteLLM

Other OpenAI-Compatible Providers

​Browser Use example

​Pricing

​Google Gemini example

​OpenAI example

​Anthropic example

​Azure OpenAI example

​Using the Responses API (for GPT-5.1 Codex models)

​AWS Bedrock example

​General AWS Bedrock (supports all providers)

​Anthropic Claude via AWS Bedrock (convenience class)

​AWS Authentication

​Groq example

​Oracle Cloud Infrastructure (OCI) example

​Ollama

​Langchain

​Qwen example

​ModelScope example

​Vercel AI Gateway example

​DeepSeek example

​Mistral example

​Cerebras example

​OpenRouter example

​LiteLLM

​Other OpenAI-Compatible Providers

Browser Use example

Pricing

Google Gemini example

OpenAI example

Anthropic example

Azure OpenAI example

Using the Responses API (for GPT-5.1 Codex models)

AWS Bedrock example

General AWS Bedrock (supports all providers)

Anthropic Claude via AWS Bedrock (convenience class)

AWS Authentication

Groq example

Oracle Cloud Infrastructure (OCI) example

Ollama

Langchain

Qwen example

ModelScope example

Vercel AI Gateway example

DeepSeek example

Mistral example

Cerebras example

OpenRouter example

LiteLLM

Other OpenAI-Compatible Providers