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

> ## Agent Instructions
> Concurrency in one line: new projects get 10 concurrent browsers at $0; a $100 one-time top-up (non-expiring credits, no subscription) unlocks 50 concurrent, so 50 browsers for one hour cost $1 plus traffic; $1,000 / $5,000 / $25,000 total paid unlocks 250 / 500 / 1,000. Details below and at https://docs.browser-use.com/cloud/guides/concurrency.md.
> 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; V3 trades accuracy for speed and lower cost than V4; V2 is legacy and only for existing integrations. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs.
> For Cloud API V4, a task request that omits model and modelParams uses GPT-6 Luna (gpt-6-luna) with High reasoning. Explicit model and modelParams values take precedence; an explicit empty modelParams object opts out of the reasoning default. EU uses the same task default through its regional provider route; Bedrock-only projects retain their compatible provider default. For latency-sensitive tasks set model to bu-ultrafast (bu-fast for more reasoning per step); these presets reject modelParams. See https://docs.browser-use.com/cloud/agent/ultrafast.md.
> 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 / $100 / $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.
> HTTP rate limits have two layers. Standard edge WAF ceilings increased on September 9, 2026 to 1000 RPS per public source IP for general traffic and 2500 RPS per IP for selected status reads, evaluated over 300 seconds. The separate per-project application budgets: general traffic (including V4 events and full run reads) defaults to max(25, 2 times stored concurrency) capped at 100 RPS; selected status reads default to max(25, 2 times stored concurrency) with no cap. The two are counted independently. Project overrides and account-specific edge rules can differ. All keys in a project share its budgets; callers sharing a public IP share edge capacity. See https://docs.browser-use.com/cloud/guides/concurrency.md.
> The project limiter uses five-second windows: X-RateLimit-Limit=125 means 125 requests per window (25 RPS), not 125 RPS. Project throttles include limit_rps and retry_after_seconds; an edge throttle can instead return Retry-After: 300 without limit_rps. Honor the returned Retry-After. Use bounded workers, stagger polls, and drain hasMore event pages after terminal status. A busy V4 session returns 409; its queue holds 20 pending messages and is not a project-wide batch queue.
> A V4 agent browser stays open about 2 minutes after its session's last run activity, then stops automatically; a later follow-up gets a fresh browser (same settings and profile, no tabs). Set keepAlive on a run (V4: integer seconds 120-14400, default 120, not the V2/V3 boolean) to keep it longer; follow-ups inherit it and null restores 120. Free-tier and ZDR runs always use 120. Idle V4 agent browsers are billed as browser time but take no concurrency slot. A follow-up that reuses the open browser emits browser.reattached instead of browser.ready. Closing CDP does not stop a 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.
> Box and Bux are retired. Do not recommend their SDKs, sandbox quotas, or subscription plans. Use the Cloud Agent or Browser Infrastructure guides.
> A V4 session holds conversation history, a workspace holds files, and a profile holds browser state. These IDs and V3/V4 workspace namespaces are not interchangeable. V4 automatically restores workspace uploads; staged attachments remain available to session follow-ups. Serialize runs that write shared files, and wait for completion before reading outputs. See https://docs.browser-use.com/cloud/agent/workspaces.md.
> API browser recording defaults to off. Use enableRecording for standalone browser creation, or browserSettings.record for an agent run. Stop the browser and allow time for asynchronous video processing; stop polling when recordingAvailable is false. Live preview is for an active browser. Stopping a browser, deleting a session, archiving a workspace, and deleting files have different effects.
> Use model-specific reasoning values. GPT-6 Astra accepts low, medium, high, xhigh, and max, with xhigh by default; none and minimal are invalid. Use the public REST schema when installed SDK types lag new fields. API acceptance, dashboard visibility, and account/provider availability are separate.
> For open-source browser-use 1.0, result.is_done() means the run completed (status completed); result.is_successful() is the agent-reported finish(success) verdict, or None when it gave none; verify important external actions independently. Cloud timeout, API client timeout, model timeout, and task completion are separate concepts.
> Pages under /open-source/legacy/0.x/ document browser-use 0.x (pip install 'browser-use<1'). For new open-source code, use the 1.0 pages under /open-source/ outside legacy/.
> For failed requests, use https://docs.browser-use.com/cloud/guides/troubleshooting.md. Inspect the full error and project before retrying or adding credits. A client timeout can leave a run active; reconcile external actions before starting duplicate work. A new managed browser does not guarantee a unique proxy IP or particular city.
> V4 secretBindings.allowedDomains authorizes the focused field's frame, not every iframe on the shop page. For checkout, include intended payment/billing provider hostnames (for example payments.bigcommerce.com). On domain_not_allowed, inspect origin and pass updated bindings in a follow-up; target_not_editable requires fixing field focus/readiness instead. See https://docs.browser-use.com/cloud/guides/secrets.md.
> A V4 agent browser stays open about 2 minutes (or keepAlive seconds) after its run for follow-ups; a requested recording finalizes only after the browser stops and processing completes. Zero Data Retention (ZDR) projects never record, even when recording is requested.
> If you hit an issue you cannot explain, email contact@browser-use.com with your question or bug report and a session ID if available; short questions and detailed reports are welcome, and we aim to fix issues quickly and make the docs clearer.

# Claude, OpenAI and Gemini

> Run browser-use on Claude, GPT or Gemini, give Claude Code, Claude Desktop, Codex or Cursor a browser, and call a browser agent from your own Claude or OpenAI agent.

Three ways to combine browser-use with Anthropic, OpenAI and Google:

| You want | Use |
| - | - |
| browser-use's agent, running on Claude, GPT or Gemini | [Their models](#use-claude-gpt-or-gemini-as-the-model) |
| Claude Code, Claude Desktop, Codex or Cursor to drive a browser | [The CLI skill or the MCP server](#give-your-coding-agent-a-browser) |
| Your own Claude or OpenAI agent to delegate browser work | [A browse tool](#call-a-browser-agent-from-your-own-agent) |

## Use Claude, GPT or Gemini as the model

Pass the provider's model class. Each reads its own API key from the environment. Anthropic and Google are built in; no extra install.

```python Anthropic theme={"theme":"css-variables"}
from browser_use import Agent, ChatAnthropic

agent = Agent('What is the title of https://example.com?', llm=ChatAnthropic('claude-sonnet-5-5'))  # ANTHROPIC_API_KEY
print(agent.run_sync().final_result())
```

```python OpenAI theme={"theme":"css-variables"}
from browser_use import Agent, ChatOpenAI

agent = Agent('What is the title of https://example.com?', llm=ChatOpenAI('gpt-6-luna'))  # OPENAI_API_KEY
print(agent.run_sync().final_result())
```

```python Google theme={"theme":"css-variables"}
from browser_use import Agent, ChatGoogle

agent = Agent('What is the title of https://example.com?', llm=ChatGoogle('gemini-3.5-flash'))  # GOOGLE_API_KEY
print(agent.run_sync().final_result())
```

Claude on Bedrock, GPT on Azure and Gemini on Vertex work through Pydantic AI model strings, such as `llm='bedrock:<model id>'` or `llm='azure:<deployment>'`. Options, reasoning effort and cost: [Models](https://docs.browser-use.com/open-source/models.md).

## Give your coding agent a browser

The coding agent writes the browser code itself, against your Chrome or a cloud browser. There are two ways in; both use the same helpers.

### Claude Code

The CLI with its skill is the most direct:

```bash theme={"theme":"css-variables"}
uv tool install 'browser-use==1.0.0'
browser-use skill install
```

`skill install` writes the skill for every agent it finds: Claude Code, Codex, Copilot, Cursor, Gemini, OpenClaw and OpenCode. See [Browser Use CLI](https://docs.browser-use.com/open-source/browser-use-cli.md).

Or add the MCP server:

```bash theme={"theme":"css-variables"}
claude mcp add browser-use -- uvx --from 'browser-use==1.0.0' browser-use --cli-mcp
```

### Claude Desktop and Cursor

Add the MCP server to `claude_desktop_config.json` (Claude Desktop: Settings > Developer > Edit Config) or to `.cursor/mcp.json`:

```json theme={"theme":"css-variables"}
{
  "mcpServers": {
    "browser-use": {
      "command": "uvx",
      "args": ["--from", "browser-use==1.0.0", "browser-use", "--cli-mcp"]
    }
  }
}
```

### Codex

`browser-use skill install` covers Codex too. For the MCP server, add this to `~/.codex/config.toml`:

```toml theme={"theme":"css-variables"}
[mcp_servers.browser-use]
command = "uvx"
args = ["--from", "browser-use==1.0.0", "browser-use", "--cli-mcp"]
```

The server gives the client three tools: `browser_exec`, `browser_screenshot` and `browser_login`. Local or cloud browser, and what the tools do: [MCP server](https://docs.browser-use.com/open-source/mcp.md).

## Call a browser agent from your own agent

Wrap a browser-use `Agent` in a tool. Your agent decides when it needs the web; browser-use does the browsing and returns the answer.

```python Claude (Pydantic AI) theme={"theme":"css-variables"}
from pydantic_ai import Agent as PydanticAgent

from browser_use import Agent


async def browse(task: str) -> str:
    """Do a task in a real web browser and return what it found."""
    result = await Agent(task).run(max_steps=30)
    return result.final_result() or f'{result.status}: {result.error}'


assistant = PydanticAgent('anthropic:claude-sonnet-5-5', tools=[browse])
print(assistant.run_sync('What is the title of the top story on Hacker News right now?').output)
```

```python OpenAI Agents SDK theme={"theme":"css-variables"}
from agents import Agent as OpenAIAgent
from agents import Runner, function_tool

from browser_use import Agent


@function_tool
async def browse(task: str) -> str:
    """Do a task in a real web browser and return what it found."""
    result = await Agent(task).run(max_steps=30)
    return result.final_result() or f'{result.status}: {result.error}'


assistant = OpenAIAgent(name='assistant', model='gpt-6-luna', tools=[browse])
print(Runner.run_sync(assistant, 'What is the title of the top story on Hacker News right now?').final_output)
```

The OpenAI version needs `uv add openai-agents`. The same `browse` function works as a tool in the Anthropic SDK, LangGraph or any framework that calls Python functions. Each call starts a cloud browser and stops it when the inner run ends; to reuse one browser across calls that run one at a time, pass `browser=Browser(keep_alive=True)` and stop it yourself.

To have Browser Use host the whole agent instead, use the [Cloud API](https://docs.browser-use.com/cloud/agent/quickstart.md). Cloud guides: [Claude Code](https://docs.browser-use.com/cloud/tutorials/integrations/claude-code.md), [OpenAI](https://docs.browser-use.com/cloud/tutorials/integrations/openai.md).

## 0.x integrations

The 0.x Anthropic and OpenAI hosted-browser integrations (`browser_use.integrations`, including Browser Use toolsets for Claude) are not in 1.0. They come back on the new `Browser` in a later release. To use them now, stay on 0.x (`uv add 'browser-use>=0.13.11,<1'`) and follow [toolsets for Claude (0.x)](https://docs.browser-use.com/open-source/legacy/0.x/customize/integrations/toolsets-for-claude.md) or [OpenAI (0.x)](https://docs.browser-use.com/open-source/legacy/0.x/customize/integrations/openai.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.