> ## Documentation Index
> Fetch the complete documentation index at: https://browseruse-0aece648-codex-docs-supported-exports.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use https://docs.browser-use.com/llms.txt and its linked .md pages for current documentation. The managed full bundle is https://docs.browser-use.com/.well-known/llms-full.txt and can be cached for up to 24 hours. Do not use the obsolete /cloud/llms*.txt or /open-source/llms*.txt static exports.
> Choose Cloud API V4 for new agent integrations; V2 is the lower-cost option for simple tasks. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs.
> Cloud authentication uses X-Browser-Use-API-Key, without a Bearer prefix. Install or upgrade browser-use-sdk and use its explicit v4 import for V4. Check the published OpenAPI reference for request fields; do not invent SDK support for new fields.
> Cloud concurrency and HTTP request rate are separate. Read GET /api/v2/billing/account for the key’s projectId, concurrentSessionLimit, activeSessionCount, and credit balance, including when using V4. Keys in one project share capacity and credits; rateLimit is a legacy concurrency alias, not requests per second.
> Keep the highest applicable existing, legacy-plan, and spend-tier concurrency grant. Current spend tiers are 10 / 50 / 250 / 500 / 1000 at $0 / $200 / $1000 / $5000 / $25000 in qualifying project payments. Legacy or externally billed projects can follow different billing paths; trust the account limit. See https://docs.browser-use.com/cloud/guides/concurrency.md.
> Budget polling across the project: the standard general bucket is 25 requests/second, including V4 event reads and full run reads. Selected status reads have a separate higher bucket. Use bounded workers, stagger polls, respect Retry-After, and drain hasMore event pages after terminal status. A busy V4 session returns 409; its queue holds 10 pending messages and is not a project-wide batch queue.
> A completed run or closed CDP connection does not immediately stop its cloud browser. Stop unneeded owned browsers with PATCH /api/v4/browsers/{id} and {"action":"stop"}. A client wait timeout does not cancel the server-side run.
> Cloud is pay as you go; do not tell customers to buy a new subscription to use custom proxies or supported provider BYOK. Usage funding and model eligibility still apply. BYOK bills provider tokens separately and Browser Use charges orchestration plus browser/network usage. See https://docs.browser-use.com/cloud/guides/billing.md.
> Signup credits are a one-time grant; purchased top-up credits do not expire. Check the API key’s project before diagnosing missing credits. API-key monthly spending caps are soft limits, not a strict prepaid wallet; concurrent or already-running work can exceed them. Auto recharge has separate trigger and purchase amounts and can charge immediately when enabled below the threshold. Use https://browser-use.com/pricing for current rates.

# Model Card: bu-2-0

> Browser Use's browser-specialized model for web automation

## Model Details

| Field             | Value                                                                   |
| ----------------- | ----------------------------------------------------------------------- |
| Model name        | `bu-2-0`                                                                |
| Provider          | Browser Use Inc.                                                        |
| Release date      | January 27, 2026                                                        |
| Model type        | Mixture-of-Experts                                                      |
| Modality          | Native multimodal browser-state model                                   |
| Primary interface | `ChatBrowserUse(model="bu-2-0")` in the Browser Use open-source library |

`bu-2-0` is a decision model for browser automation. It is called inside the Browser Use agent loop, where it receives the task, browser state, previous step history, and available tool schemas, then returns the next browser action.

The model is not a general-purpose chat or text-generation model. It is built for web tasks where a browser runtime provides screenshots, DOM state, and executable tools.

## How to Use

Set up Browser Use, install the browser runtime, and provide `BROWSER_USE_API_KEY`.

* Install the package: `uv pip install browser-use`
* Install the browser runtime: `uvx browser-use install`
* Set the API key: `export BROWSER_USE_API_KEY="your-key"`

```python theme={null}
from browser_use import Agent, ChatBrowserUse

agent = Agent(
    task="Search for Browser Use and summarize the first result.",
    llm=ChatBrowserUse(model="bu-2-0"),
)

history = await agent.run()
```

The Browser Use library executes the action, captures the new page state, and calls the model again. The loop stops when the model returns a terminal result or the configured step, time, or failure limit is reached.

## Inputs and Outputs

| Direction | Data                                                                                                                             |
| --------- | -------------------------------------------------------------------------------------------------------------------------------- |
| Input     | User task in natural language                                                                                                    |
| Input     | Current screenshot or viewport image                                                                                             |
| Input     | Serialized DOM, accessibility, and element-index state from Browser Use                                                          |
| Input     | Built-in Browser Use tool schemas                                                                                                |
| Input     | Developer-provided custom tool schemas                                                                                           |
| Input     | Previous model outputs, executed actions, tool results, errors, extracted content, and prior steps from the same browser episode |
| Output    | A structured next action for Browser Use to execute                                                                              |
| Output    | A terminal result when the task is complete                                                                                      |

Typical actions include clicking an element, entering text, scrolling, navigating, extracting content, selecting a file, downloading a file, calling a custom tool, or returning a final answer.

## Intended Use

`bu-2-0` is intended for browser automation tasks in which the user describes a web task in natural language and Browser Use supplies the browser state and tool interface.

In scope:

* Open-ended tasks that require exploring an unfamiliar website.
* Step-by-step natural language instructions for browser automation workflows.
* Multi-step web navigation.
* Form filling and page interaction.
* Browser-based data extraction.
* Website testing and QA workflows.
* Tasks that require both visual grounding and DOM grounding.
* Workflows extended with custom Browser Use tools.

## Tools

`bu-2-0` does not directly control a browser process. It selects actions from the tools exposed by Browser Use, and the Browser Use library executes those tools in the browser.

The Browser Use tools documentation lists the basic built-in tools: [Tools: Basics](/open-source/customize/tools/basics).

Common tool categories include:

* Navigation.
* Clicks and text input.
* Scrolling and keyboard actions.
* Page extraction.
* File upload and download.
* Completion with a final answer.
* Developer-defined custom tools.

Custom tools are part of the model input for that run. This lets teams expose deterministic operations, private APIs, authentication helpers, or workflow-specific actions without changing the base model.

## Benchmarks

<img className="block" src="https://mintcdn.com/browseruse-0aece648-codex-docs-supported-exports/pg6YX8jO9xwCWYaf/open-source/images/bu-2-0-benchmark-scores.png?fit=max&auto=format&n=pg6YX8jO9xwCWYaf&q=85&s=ab9f7a47a0e458afc768114266c12a2c" alt="BU Bench V1 success-rate comparison for bu-2-0" width="1800" height="900" data-path="open-source/images/bu-2-0-benchmark-scores.png" />

BU Bench V1 is a browser-agent benchmark, not a generic language benchmark. The public benchmark draws challenging but completable browser tasks from five sources:

| Source     | Weight | Area                                                                  |
| ---------- | -----: | --------------------------------------------------------------------- |
| Custom     |    20% | Page interaction, including iframes, drag-and-drop, and complex forms |
| WebBench   |    20% | Web browsing tasks                                                    |
| Mind2Web 2 |    20% | Multi-step web navigation                                             |
| GAIA       |    20% | Web-grounded assistant tasks                                          |
| BrowseComp |    20% | Browser comprehension                                                 |

The benchmark contains 100 tasks in total.

In the public BU Bench V1 model table, `bu-2-0` is reported as `OSS + BU LLM (ChatBrowserUse-2)` with a **63.3%** success rate when used through the open-source Browser Use library.

## Judge

BU Bench V1 uses binary task success. A task is run through the browser-agent loop and then judged as complete or incomplete based on whether the final agent output satisfies the user's intent.

The judge primarily rates agent outcomes. It checks whether the requested task was fulfilled from the user's perspective, using the final agent output and the run trace. This means failures caused by external circumstances can still count as failures. For example, if a target website is unavailable, has changed, or blocks access, the browser agent may behave correctly at the computer-control level but still fail the benchmark task because the user intent was not completed.

Public judge details:

* 100 tasks.
* Multiple runs per model.
* Standard error bars in the original plots.
* 200 hand-labeled traces used to estimate evaluator quality.
* 87% reported agreement with human labels, with most disagreements on partial successes and technicalities.

Browser Use also evaluates `bu-2-0` on internal suites with thousands of tasks across many domains and websites. These evaluations are used to optimize accuracy, cost, latency, recovery behavior, task coverage, and error patterns.

## Known Limitations

* This model is for browser automation and is not intended for token-heavy generation workflows, such as long code generation.
* Heavily client-rendered pages, cross-origin iframes, canvas-only interfaces, and hidden state can reduce observability and make interactions less reliable.
* Pages with thousands of interactive elements can overload the CPU in sandbox environments. This can cause screenshot or DOM capture timeouts inside the Browser Use library, leading to missing model context, timeouts, or other model-call errors.
* The model can only choose from tools made available by Browser Use or the developer. For example, if no drag-and-drop tool is available, the model may not be able to perform a drag-and-drop action reliably.
* A website can change while the model is deciding on the next action, which can lead to an incorrect action.
* High-impact tasks should use features such as domain allowlists, step limits, tool allowlists, and custom human-approval tools for irreversible actions such as purchases.
* BU Bench V1 is useful but not exhaustive. It does not cover every language, website type, authentication flow, or production constraint.
* Because the web changes constantly, measured performance can change over time.

## Sources

* Browser Use library: [https://github.com/browser-use/browser-use](https://github.com/browser-use/browser-use)
* `ChatBrowserUse` source: [https://github.com/browser-use/browser-use/blob/main/browser\_use/llm/browser\_use/chat.py](https://github.com/browser-use/browser-use/blob/main/browser_use/llm/browser_use/chat.py)
* Open-source docs: [https://docs.browser-use.com/open-source/introduction](https://docs.browser-use.com/open-source/introduction)
* Tools docs: [https://docs.browser-use.com/open-source/customize/tools/basics](https://docs.browser-use.com/open-source/customize/tools/basics)
* API keys: [https://cloud.browser-use.com/new-api-key](https://cloud.browser-use.com/new-api-key)
* BU Bench V1 blog post: [https://browser-use.com/posts/ai-browser-agent-benchmark](https://browser-use.com/posts/ai-browser-agent-benchmark)
* WebBench: [https://github.com/Halluminate/WebBench](https://github.com/Halluminate/WebBench)
* Mind2Web 2: [https://osu-nlp-group.github.io/Mind2Web-2/](https://osu-nlp-group.github.io/Mind2Web-2/)
* GAIA: [https://arxiv.org/abs/2311.12983](https://arxiv.org/abs/2311.12983)
* BrowseComp: [https://openai.com/index/browsecomp/](https://openai.com/index/browsecomp/)