> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Browser Use

> Run Browser Use agents with TokenLab models

## Overview

Browser Use can call TokenLab through `ChatOpenAILike`, the OpenAI-compatible chat model wrapper.

<Note>
  **Type**: Browser automation agent framework

  **Primary Path**: OpenAI-compatible Chat Completions

  **Support Confidence**: Supported OpenAI-compatible path
</Note>

## Environment

```bash theme={null}
export TOKENLAB_API_KEY="sk-your-tokenlab-key"
```

## Example

```python theme={null}
import os

from browser_use import Agent
from browser_use.llm.openai.like import ChatOpenAILike

llm = ChatOpenAILike(
    model="claude-sonnet-5",
    api_key=os.environ["TOKENLAB_API_KEY"],
    base_url="https://api.tokenlab.sh/v1",
)

agent = Agent(
    task="Compare the top search results for TokenLab integrations",
    llm=llm,
)
```

## Endpoint Notes

Use this page for Browser Use workflows that call Chat Completions through an OpenAI-compatible client. If your workflow needs TokenLab native Responses, Anthropic Messages, or Gemini endpoints, use a client path in Browser Use that speaks that protocol directly.