> ## 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
> 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 / $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 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.
> 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, is_done only reports a terminal done action. is_successful is the agent-reported outcome; verify important external actions independently. Cloud timeout, API client timeout, model timeout, and task completion are separate concepts.
> 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.
# 1Password & 2FA
> Auto-fill passwords and TOTP codes from 1Password in API tasks.
## Setup
### 1. Create a dedicated vault
Create a new vault in 1Password for Browser Use. Add the credentials you want the agent to access (usernames, passwords, and 2FA/TOTP codes).
### 2. Create a service account token
1. Go to [1Password Developer Tools - Service Accounts](https://my.1password.eu/developer-tools/active/service-accounts)
2. Click **New Service Account**, name it "Browser Use Cloud"
3. Grant **read access** to the dedicated vault
4. Copy the generated token
### 3. Connect to Browser Use Cloud
1. Go to [Browser Use Cloud Settings - Secrets](https://cloud.browser-use.com/settings?tab=secrets)
2. Click **Create Integration**
3. Paste your service account token
## Use a vault in a v4 run
Pass the vault id and the domains where its credentials may be typed. Browser Use finds the project's connected 1Password integration and makes the vault's username, password, and TOTP fields available to the run. You do not need the integration, item, or field ids.
Every supported credential field in the vault is made available to the run. Use a dedicated vault containing only the accounts the agent needs.
```bash theme={null}
curl -X POST https://api.browser-use.com/api/v4/runs \
-H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"task": "Open amazon.com, log in, and check my recent orders",
"opVaultId": "",
"opVaultAllowedDomains": ["amazon.com"]
}'
```
* `opVaultAllowedDomains` is required with `opVaultId`. Use bare hostnames; a hostname also covers its subdomains.
* Vault items become aliases based on their titles, with `_username`, `_password`, or `_bu_2fa_code` suffixes.
* Vault fields and explicit `secretBindings` share a limit of 10 bindings per run. The API returns `422` if the combined total exceeds 10.
* Vault access requires exactly one active 1Password integration on the project and is unavailable for zero-data-retention projects.
These fields work through the v4 REST API. The currently published Python and TypeScript SDK types do not expose them yet; use the REST request above until those clients are regenerated.
## Bind individual fields in a v4 run
For least-privilege access, use **secret bindings** instead of exposing every credential field in a vault. Each binding names one field of one 1Password item, gives it an alias the agent can ask for, and lists the hosts where it may be typed. The server types the value into the focused field when the agent asks for the alias on an allowed domain. This keeps the raw value out of your task text, but does not make it inaccessible to the agent: once entered, it is available to the page and to browser/CDP access. Bindings are run-scoped, so a follow-up run that needs the same login must send them again.
```python Python theme={null}
from browser_use_sdk.v4 import BrowserUse
with BrowserUse() as client:
run = client.runs.create(
"Log into Jira and create a ticket for the Q4 release",
secret_bindings=[
{
"alias": "jira_password",
"source": {
"type": "onepassword",
"integrationId": "",
"vaultId": "",
"itemId": "- ",
"fieldId": "password",
},
"allowedDomains": ["atlassian.net"],
}
],
)
print(client.runs.wait_for_completion(run.id).result)
```
```typescript TypeScript theme={null}
import { BrowserUse } from "browser-use-sdk/v4";
const client = new BrowserUse();
const run = await client.runs.create({
task: "Log into Jira and create a ticket for the Q4 release",
secretBindings: [
{
alias: "jira_password",
source: {
type: "onepassword",
integrationId: "",
vaultId: "",
itemId: "
- ",
fieldId: "password",
},
allowedDomains: ["atlassian.net"],
},
],
});
```
* `integrationId` is the 1Password integration you connected under **Settings → Secrets**.
* `vaultId` and `itemId` are the 1Password UUIDs of the vault and item (copy them from 1Password).
* `fieldId` is the field's id, not its label: `username`, `password`, or `one-time-password` for a TOTP field, which resolves to the current code.
* `allowedDomains` are bare hostnames; a host covers its subdomains.
In the chat UI at cloud.browser-use.com both options live under **Run settings → Credentials**. **Use a whole vault** asks for the vault and the allowed sites and sends `opVaultId` + `opVaultAllowedDomains`; **Add a credential** walks vault, item, and field, takes an alias and the domains, and sends one binding. The **Agents** page has a **1Password** section with the same vault + allowed-sites pair, and its REST snippet shows the resulting request.
## Use a vault in a v2 or v3 task
```python Python theme={null}
from browser_use_sdk import AsyncBrowserUse
client = AsyncBrowserUse()
result = await client.run(
"Log into my Jira account and create a new ticket",
op_vault_id="your-vault-id",
allowed_domains=["*.atlassian.net"],
)
print(result.output)
```
```typescript TypeScript theme={null}
import { BrowserUse } from "browser-use-sdk";
const client = new BrowserUse();
const result = await client.run(
"Log into my Jira account and create a new ticket",
{
opVaultId: "your-vault-id",
allowedDomains: ["*.atlassian.net"],
},
);
console.log(result.output);
```
For SSO/OAuth redirects, include all required domains:
```python Python theme={null}
result = await client.run(
"Log into Jira and create a ticket for the Q4 release",
op_vault_id="your-vault-id",
allowed_domains=["*.atlassian.net", "*.okta.com"],
)
```
```typescript TypeScript theme={null}
const result = await client.run(
"Log into Jira and create a ticket for the Q4 release",
{
opVaultId: "your-vault-id",
allowedDomains: ["*.atlassian.net", "*.okta.com"],
},
);
```
## How it works
When the agent encounters a login form:
1. It identifies the service (e.g., Twitter, GitHub, LinkedIn)
2. Retrieves matching credentials from your 1Password vault
3. Fills in the username and password
4. If 2FA is required and a TOTP code is stored, it generates and enters the code automatically
The agent never sees your actual credentials. The actual username, password, and 2FA codes are filled in programmatically — keeping your secrets hidden from the AI model.