Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

SDK docs support, much nicer cloud docs, tiny bugfixes in docs

Gregor Žunič787a041f001c
diff --git a/docs/api-reference/check-balance.mdx b/docs/api-reference/check-balance.mdx
deleted file mode 100644
index a3558c7c0..000000000
--- a/docs/api-reference/check-balance.mdx
+++ /dev/null
@@ -1,62 +0,0 @@
----
-title: "Check Balance"
-api: "GET /api/v1/balance"
-description: "Returns the user's current API credit balance"
----
-
-Returns the user's current API credit balance, which includes both monthly subscription credits and any additional purchased credits.
-
-## Response
-
-<ResponseField name="balance" type="string">
- The current number of API credits available, with the value in cents (0.01 USD
- = 1 credit).
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-response = requests.get(f'{BASE_URL}/balance', headers=HEADERS)
-balance = response.json()['balance']
-print(f"Current API credit balance: {balance}")
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/balance \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "balance": "5000"
-}
-```
-
-</ResponseExample>
-
-## API Credit Usage
-
-Each task execution consumes API credits based on the following factors:
-
-1. **Task Duration**: Longer running tasks consume more credits
-2. **LLM Model**: More powerful models consume more credits
-3. **Browser Features**: Features like proxy usage and adblock may affect credit consumption
-4. **Task Complexity**: More complex tasks with many steps consume more credits
-
-You can monitor your credit usage through the [Browser Use Cloud dashboard](https://cloud.browser-use.com/dashboard) or by using the Check Balance endpoint.
-
-<Note>
- If your balance reaches zero, new task executions will be rejected until you
- add more credits or your subscription renews.
-</Note>{" "}
diff --git a/docs/api-reference/create-browser-profile.mdx b/docs/api-reference/create-browser-profile.mdx
deleted file mode 100644
index 670cab60d..000000000
--- a/docs/api-reference/create-browser-profile.mdx
+++ /dev/null
@@ -1,120 +0,0 @@
----
-title: "Create Browser Profile"
-api: "POST /api/v1/browser-profiles"
-description: "Create a new browser profile with custom settings for ad blocking, proxy usage, and viewport dimensions."
----
-
-Create a new browser profile with custom settings for ad blocking, proxy usage, and viewport dimensions.
-
-<Note>
- Pay-as-you-go users can only have one profile. Subscription users can create
- multiple profiles.
-</Note>
-
-### Request Body
-
-<ParamField body="profile_name" type="string" required>
- Name of the browser profile
-</ParamField>
-<ParamField body="description" type="string" default="">
- Description of the profile
-</ParamField>
-<ParamField body="persist" type="boolean" default="true">
- Save cookies, local storage, and session data between tasks
-</ParamField>
-<ParamField body="ad_blocker" type="boolean" default="true">
- Block ads and popups during automated tasks
-</ParamField>
-<ParamField body="proxy" type="boolean" default="true">
- Route traffic through mobile proxies for better stealth
-</ParamField>
-<ParamField body="proxy_country_code" type="string" default="US">
- Country code for the proxy
-</ParamField>
-<ParamField body="browser_viewport_width" type="integer" default="1280">
- Browser viewport width in pixels
-</ParamField>
-<ParamField body="browser_viewport_height" type="integer" default="960">
- Browser viewport height in pixels
-</ParamField>
-
-### Response
-
-<ResponseField name="profile_id" type="string">
- Unique identifier for the created browser profile
-</ResponseField>
-<ResponseField name="profile_name" type="string">
- Name of the browser profile
-</ResponseField>
-<ResponseField name="description" type="string">
- Description of the profile
-</ResponseField>
-<ResponseField name="persist" type="boolean">
- Save cookies, local storage, and session data between tasks
-</ResponseField>
-<ResponseField name="ad_blocker" type="boolean">
- Block ads and popups during automated tasks
-</ResponseField>
-<ResponseField name="proxy" type="boolean">
- Route traffic through mobile proxies for better stealth
-</ResponseField>
-<ResponseField name="proxy_country_code" type="string">
- Country code for the proxy
-</ResponseField>
-<ResponseField name="browser_viewport_width" type="integer">
- Browser viewport width in pixels
-</ResponseField>
-<ResponseField name="browser_viewport_height" type="integer">
- Browser viewport height in pixels
-</ResponseField>
-
-<RequestExample>
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-profile_data = {
-"profile_name": "Default Profile",
-"description": "Main automation profile",
-"persist": true,
-"ad_blocker": true,
-"proxy": true,
-"proxy_country_code": "US",
-"browser_viewport_width": 1280,
-"browser_viewport_height": 960
-}
-
-response = requests.post(f'{BASE_URL}/browser-profiles', headers=HEADERS, json=profile_data)
-profile = response.json()
-print(profile)
-
-````
-
-```bash curl
-curl --request POST \
- --url https://api.browser-use.com/api/v1/browser-profiles \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{"profile_name": "Default Profile", "description": "Main automation profile", "persist": true, "ad_blocker": true, "proxy": true, "proxy_country_code": "US", "browser_viewport_width": 1280, "browser_viewport_height": 960}'
-````
-
-</RequestExample>
-
-<ResponseExample>
-```json 200
-{
- "profile_id": "profile_1234567890abcdef",
- "profile_name": "Default Profile",
- "description": "Main automation profile",
- "persist": true,
- "ad_blocker": true,
- "proxy": true,
- "proxy_country_code": "US",
- "browser_viewport_width": 1280,
- "browser_viewport_height": 960
-}
-```
-</ResponseExample>
diff --git a/docs/api-reference/create-scheduled-task.mdx b/docs/api-reference/create-scheduled-task.mdx
deleted file mode 100644
index f83fb73e0..000000000
--- a/docs/api-reference/create-scheduled-task.mdx
+++ /dev/null
@@ -1,146 +0,0 @@
----
-title: "Create Scheduled Task"
-api: "POST /api/v1/scheduled-task"
-description: "Create a new scheduled task to run at regular intervals or based on a cron expression"
----
-
-Creates a new scheduled task to run at regular intervals or based on a cron expression. This allows you to automate recurring browser automation tasks.
-
-<Note>
-This endpoint requires an active subscription.
-</Note>
-
-## Request Body
-
-<ParamField body="task" type="string" required>
- Instructions for what the agent should do
-</ParamField>
-<ParamField body="schedule_type" type="string" required>
- Type of schedule: "interval" or "cron"
-</ParamField>
-<ParamField body="interval_minutes" type="integer">
- Minutes between runs (required for interval schedule)
-</ParamField>
-<ParamField body="cron_expression" type="string">
- Cron expression for scheduling (required for cron schedule)
-</ParamField>
-<ParamField body="start_at" type="string">
- When to start the schedule (ISO 8601 format, defaults to now)
-</ParamField>
-<ParamField body="end_at" type="string">
- When to end the schedule (ISO 8601 format, defaults to 1 year from now)
-</ParamField>
-<ParamField body="secrets" type="object">
- Dictionary of secrets to be used by the agent (safely encrypted before storing)
-</ParamField>
-<ParamField body="allowed_domains" type="array">
- List of domains the agent is allowed to visit
-</ParamField>
-<ParamField body="save_browser_data" type="boolean" default="false">
- Whether to save browser cookies and data between runs
-</ParamField>
-<ParamField body="structured_output_json" type="string">
- JSON schema for structured output
-</ParamField>
-<ParamField body="llm_model" type="string" default="gpt-4.1">
- LLM model to use. Available options: gpt-4.1, gpt-4.1-mini, o4-mini, o3, gemini-2.5-flash, gemini-2.5-pro, claude-sonnet-4-20250514
-</ParamField>
-<ParamField body="use_adblock" type="boolean" default="true">
- Whether to use an adblocker
-</ParamField>
-<ParamField body="use_proxy" type="boolean" default="true">
- Whether to use a proxy
-</ParamField>
-<ParamField body="proxy_country_code" type="string" default="us">
- Country code for residential proxy. Must be one of: us, uk, fr, it, jp, au, de, fi, ca, in
-</ParamField>
-<ParamField body="highlight_elements" type="boolean" default="true">
- Whether to highlight elements on the page
-</ParamField>
-<ParamField body="included_file_names" type="array">
- File names to include in the task
-</ParamField>
-<ParamField body="browser_viewport_width" type="integer" default="1280">
- Width of browser viewport in pixels
-</ParamField>
-<ParamField body="browser_viewport_height" type="integer" default="960">
- Height of browser viewport in pixels
-</ParamField>
-<ParamField body="max_agent_steps" type="integer" default="75">
- Maximum number of agent steps (max: 200)
-</ParamField>
-<ParamField body="enable_public_share" type="boolean" default="false">
- Whether to enable public sharing of task executions
-</ParamField>
-
-<ParamField body="metadata" type="object">
- Optional dictionary of string key-value pairs for custom tagging. Max 10 pairs. Keys: strings (max 100 chars, non-empty). Values: strings (max 1000 chars).
-</ParamField>
-
-*Either `interval_minutes` or `cron_expression` is required depending on the `schedule_type`.
-
-## Response
-
-<ResponseField name="id" type="string">
- The unique identifier for the created scheduled task.
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-from datetime import datetime, timedelta
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-start_time = datetime.utcnow().isoformat() + 'Z'
-end_time = (datetime.utcnow() + timedelta(days=30)).isoformat() + 'Z'
-
-task_data = {
- "task": "Visit example.com and check if the site is up",
- "schedule_type": "interval",
- "interval_minutes": 60,
- "start_at": start_time,
- "end_at": end_time,
- "use_adblock": True,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
-
-response = requests.post(f'{BASE_URL}/scheduled-task', headers=HEADERS, json=task_data)
-task_id = response.json()['id']
-print(f"Scheduled task created with ID: {task_id}")
-```
-
-```bash curl
-curl --request POST \
- --url https://api.browser-use.com/api/v1/scheduled-task \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{
- "task": "Visit example.com and check if the site is up",
- "schedule_type": "interval",
- "interval_minutes": 60,
- "use_adblock": true,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
- }'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "id": "scheduled_task_1234567890abcdef"
-}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/delete-browser-profile.mdx b/docs/api-reference/delete-browser-profile.mdx
deleted file mode 100644
index e1955b307..000000000
--- a/docs/api-reference/delete-browser-profile.mdx
+++ /dev/null
@@ -1,45 +0,0 @@
----
-title: "Delete Browser Profile"
-api: "DELETE /api/v1/browser-profiles/{profile_id}"
-description: "Deletes a browser profile. This will remove the profile and all associated browser data."
----
-
-Deletes a browser profile. This will remove the profile and all associated browser data. This action cannot be undone!
-
-### Path Parameters
-
-<ParamField path="profile_id" type="string" required>
- ID of the browser profile to delete
-</ParamField>
-
-### Response
-
-A successful deletion returns an empty object.
-
-<RequestExample>
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-profile_id = 'profile_1234567890abcdef'
-response = requests.delete(f'{BASE_URL}/browser-profiles/{profile_id}', headers=HEADERS)
-print(response.json())
-
-````
-
-```bash curl
-curl --request DELETE \
- --url https://api.browser-use.com/api/v1/browser-profiles/profile_1234567890abcdef \
- --header 'Authorization: Bearer <token>'
-````
-
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {}
- ```
-</ResponseExample>
diff --git a/docs/api-reference/delete-scheduled-task.mdx b/docs/api-reference/delete-scheduled-task.mdx
deleted file mode 100644
index 6316e0494..000000000
--- a/docs/api-reference/delete-scheduled-task.mdx
+++ /dev/null
@@ -1,81 +0,0 @@
----
-title: "Delete Scheduled Task"
-api: "DELETE /api/v1/scheduled-task/{task_id}"
-description: "Deletes a scheduled task"
----
-
-Deletes a scheduled task. This will prevent any future runs of this task. Any currently running instances of this task will be allowed to complete.
-
-## Path Parameters
-
-<ParamField path="task_id" type="string" required>
- ID of the scheduled task to delete
-</ParamField>
-
-## Response
-
-The endpoint returns an empty response body with a 200 status code on success.
-
-<RequestExample>
-
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-task_id = 'scheduled_task_1234567890abcdef'
-
-response = requests.delete(f'{BASE_URL}/scheduled-task/{task_id}', headers=HEADERS)
-
-if response.status_code == 200:
- print("Scheduled task deleted successfully")
-else:
- print(f"Error deleting scheduled task: {response.status_code}")
-```
-
-```bash curl
-curl --request DELETE \
- --url https://api.browser-use.com/api/v1/scheduled-task/{task_id} \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{}
-```
-
-```json 404
-{
- "detail": "Scheduled task not found"
-}
-```
-
-```json 422
-{
- "detail": [
- {
- "loc": ["path", "task_id"],
- "msg": "field required",
- "type": "value_error.missing"
- }
- ]
-}
-```
-
-</ResponseExample>
-
-## Usage Notes
-
-- Deletion is permanent and cannot be undone
-- Any currently running instances of this task will be allowed to complete
-- Future scheduled runs will be prevented
-- The task will be removed from the scheduled tasks list immediately
-
-<Warning>
-Deleting a scheduled task is irreversible. Make sure you want to permanently remove the task before proceeding.
-</Warning>
diff --git a/docs/api-reference/get-browser-profile.mdx b/docs/api-reference/get-browser-profile.mdx
deleted file mode 100644
index 798af507e..000000000
--- a/docs/api-reference/get-browser-profile.mdx
+++ /dev/null
@@ -1,82 +0,0 @@
----
-title: "Get Browser Profile"
-api: "GET /api/v1/browser-profiles/{profile_id}"
-description: "Returns information about a specific browser profile and its configuration settings."
----
-
-Returns information about a specific browser profile and its configuration settings.
-
-### Path Parameters
-
-<ParamField path="profile_id" type="string" required>
- ID of the browser profile to retrieve
-</ParamField>
-
-### Response
-
-<ResponseField name="profile_id" type="string">
- Unique identifier for the browser profile
-</ResponseField>
-<ResponseField name="profile_name" type="string">
- Name of the browser profile
-</ResponseField>
-<ResponseField name="description" type="string">
- Description of the profile
-</ResponseField>
-<ResponseField name="persist" type="boolean">
- Save cookies, local storage, and session data between tasks
-</ResponseField>
-<ResponseField name="ad_blocker" type="boolean">
- Block ads and popups during automated tasks
-</ResponseField>
-<ResponseField name="proxy" type="boolean">
- Route traffic through mobile proxies for better stealth
-</ResponseField>
-<ResponseField name="proxy_country_code" type="string">
- Country code for the proxy
-</ResponseField>
-<ResponseField name="browser_viewport_width" type="integer">
- Browser viewport width in pixels
-</ResponseField>
-<ResponseField name="browser_viewport_height" type="integer">
- Browser viewport height in pixels
-</ResponseField>
-
-<RequestExample>
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-profile_id = 'profile_1234567890abcdef'
-response = requests.get(f'{BASE_URL}/browser-profiles/{profile_id}', headers=HEADERS)
-profile = response.json()
-print(profile)
-
-````
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/browser-profiles/profile_1234567890abcdef \
- --header 'Authorization: Bearer <token>'
-````
-
-</RequestExample>
-
-<ResponseExample>
-```json 200
-{
- "profile_id": "profile_1234567890abcdef",
- "profile_name": "Default Profile",
- "description": "Main automation profile",
- "persist": true,
- "ad_blocker": true,
- "proxy": true,
- "proxy_country_code": "US",
- "browser_viewport_width": 1280,
- "browser_viewport_height": 960
-}
-```
-</ResponseExample>
diff --git a/docs/api-reference/get-scheduled-task.mdx b/docs/api-reference/get-scheduled-task.mdx
deleted file mode 100644
index df258b605..000000000
--- a/docs/api-reference/get-scheduled-task.mdx
+++ /dev/null
@@ -1,139 +0,0 @@
----
-title: "Get Scheduled Task"
-api: "GET /api/v1/scheduled-task/{task_id}"
-description: "Returns detailed information about a specific scheduled task"
----
-
-Returns detailed information about a specific scheduled task, including its schedule configuration and current status.
-
-## Path Parameters
-
-<ParamField path="task_id" type="string" required>
- ID of the scheduled task to retrieve
-</ParamField>
-
-## Response
-
-<ResponseField name="id" type="string">
- The unique identifier for the scheduled task
-</ResponseField>
-
-<ResponseField name="task" type="string">
- Instructions for what the agent should do
-</ResponseField>
-
-<ResponseField name="save_browser_data" type="boolean">
- Whether to save browser cookies and data
-</ResponseField>
-
-<ResponseField name="structured_output_json" type="string">
- JSON schema for structured output
-</ResponseField>
-
-<ResponseField name="llm_model" type="string">
- LLM model to use
-</ResponseField>
-
-<ResponseField name="use_adblock" type="boolean">
- Whether to use an adblocker
-</ResponseField>
-
-<ResponseField name="use_proxy" type="boolean">
- Whether to use a proxy
-</ResponseField>
-
-<ResponseField name="highlight_elements" type="boolean">
- Whether to highlight elements on the page
-</ResponseField>
-
-<ResponseField name="schedule_type" type="string">
- Type of schedule: "interval" or "cron"
-</ResponseField>
-
-<ResponseField name="interval_minutes" type="integer">
- Minutes between runs
-</ResponseField>
-
-<ResponseField name="cron_expression" type="string">
- Cron expression for scheduling
-</ResponseField>
-
-<ResponseField name="start_at" type="string">
- When to start the schedule
-</ResponseField>
-
-<ResponseField name="next_run_at" type="string">
- When the next run is scheduled
-</ResponseField>
-
-<ResponseField name="end_at" type="string">
- When to end the schedule
-</ResponseField>
-
-<ResponseField name="is_active" type="boolean">
- Whether the scheduled task is active
-</ResponseField>
-
-<ResponseField name="created_at" type="string">
- When the scheduled task was created
-</ResponseField>
-
-<ResponseField name="updated_at" type="string">
- When the scheduled task was last updated
-</ResponseField>
-
-<ResponseField name="metadata" type="object | null">
- Custom metadata key-value pairs associated with the scheduled task
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/scheduled-task/{task_id}"
-
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("GET", url, headers=headers)
-
-print(response.text)
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/scheduled-task/{task_id} \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "id": "scheduled_task_1234567890abcdef",
- "task": "Visit example.com and check if the site is up",
- "save_browser_data": false,
- "structured_output_json": null,
- "llm_model": "gpt-4o",
- "use_adblock": true,
- "use_proxy": true,
- "highlight_elements": true,
- "schedule_type": "interval",
- "interval_minutes": 60,
- "cron_expression": null,
- "start_at": "2023-01-01T00:00:00Z",
- "next_run_at": "2023-01-01T01:00:00Z",
- "end_at": "2023-12-31T23:59:59Z",
- "is_active": true,
- "created_at": "2023-01-01T00:00:00Z",
- "updated_at": "2023-01-01T00:00:00Z",
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/get-task-media.mdx b/docs/api-reference/get-task-media.mdx
deleted file mode 100644
index 4e9325c1c..000000000
--- a/docs/api-reference/get-task-media.mdx
+++ /dev/null
@@ -1,60 +0,0 @@
----
-title: "Get Task Media"
-api: "GET /api/v1/task/{task_id}/media"
-description: "Get media files generated during task execution"
----
-
-Returns links to any recordings or media generated during task execution, such as browser session recordings. Only available for completed tasks.
-
-<ParamField path="task_id" type="string" required>
- ID of the task to retrieve media for
-</ParamField>
-
-<ResponseField name="recordings" type="array">
- List of recording URLs generated during task execution
-</ResponseField>
-
-<RequestExample>
-```python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-task_id = 'task_1234567890abcdef'
-response = requests.get(f'{BASE_URL}/task/{task_id}/media', headers=HEADERS)
-media = response.json()
-print(f"Found {len(media['recordings'])} recordings")
-```
-</RequestExample>
-
-<ResponseExample>
-```json
-{
- "recordings": [
- "https://media.browser-use.com/recordings/task_1234567890abcdef/session.mp4",
- "https://media.browser-use.com/recordings/task_1234567890abcdef/screen.webm"
- ]
-}
-```
-</ResponseExample>
-
-## Media Types
-
-The following types of media files may be generated:
-
-- **Session recordings**: Full browser session recordings in MP4 format
-- **Screen recordings**: Screen capture videos in WebM format
-- **Audio recordings**: Audio tracks if microphone access was used
-
-## Availability
-
-- Media files are only available for completed tasks
-- Recordings are generated automatically during task execution
-- Files are available for download for 30 days after task completion
-- Media generation can be disabled in task settings to save storage
-
-<Note>
-Media files are only generated for tasks that have been configured to record sessions. This feature may not be available for all task types.
-</Note>
diff --git a/docs/api-reference/get-task-output-file.mdx b/docs/api-reference/get-task-output-file.mdx
deleted file mode 100644
index f861388f0..000000000
--- a/docs/api-reference/get-task-output-file.mdx
+++ /dev/null
@@ -1,63 +0,0 @@
----
-title: "Get Task Output File"
-api: "GET /api/v1/task/{task_id}/output-file/{file_name}"
-description: "Returns a presigned URL for downloading a file from the task output files"
----
-
-Returns a presigned URL for downloading a file from the task output files. This endpoint is useful for retrieving files that were generated or modified during task execution.
-
-## Path Parameters
-
-<ParamField path="task_id" type="string" required>
- ID of the task
-</ParamField>
-<ParamField path="file_name" type="string" required>
- Name of the output file
-</ParamField>
-
-## Response
-
-<ResponseField name="download_url" type="string">
- A presigned URL for downloading the file.
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-task_id = 'task_1234567890abcdef'
-file_name = 'results.csv'
-
-response = requests.get(f'{BASE_URL}/task/{task_id}/output-file/{file_name}', headers=HEADERS)
-download_url = response.json()['download_url']
-
-# Download the file
-file_response = requests.get(download_url)
-with open('downloaded_results.csv', 'wb') as file:
- file.write(file_response.content)
-
-print("File downloaded successfully")
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/task/{task_id}/output-file/{file_name} \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "download_url": "https://storage.browser-use.com/output-files/task_1234567890abcdef/results.csv?signature=..."
-}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/get-task-screenshots.mdx b/docs/api-reference/get-task-screenshots.mdx
deleted file mode 100644
index 1db64654c..000000000
--- a/docs/api-reference/get-task-screenshots.mdx
+++ /dev/null
@@ -1,74 +0,0 @@
----
-title: "Get Task Screenshots"
-api: "GET /api/v1/task/{task_id}/screenshots"
-description: "Get screenshots generated during task execution"
----
-
-Returns any screenshot URLs generated during task execution. Screenshots are automatically captured at key moments during the automation process.
-
-<ParamField path="task_id" type="string" required>
- ID of the task to retrieve screenshots for
-</ParamField>
-
-<ResponseField name="screenshots" type="array">
- List of screenshot URLs generated during task execution
-</ResponseField>
-
-<RequestExample>
-```python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-task_id = 'task_1234567890abcdef'
-response = requests.get(f'{BASE_URL}/task/{task_id}/screenshots', headers=HEADERS)
-screenshots = response.json()
-print(f"Found {len(screenshots['screenshots'])} screenshots")
-
-# Download the first screenshot
-if screenshots['screenshots']:
- screenshot_url = screenshots['screenshots'][0]
- img_response = requests.get(screenshot_url)
- with open('screenshot.png', 'wb') as f:
- f.write(img_response.content)
-```
-</RequestExample>
-
-<ResponseExample>
-```json
-{
- "screenshots": [
- "https://media.browser-use.com/screenshots/task_1234567890abcdef/step_1.png",
- "https://media.browser-use.com/screenshots/task_1234567890abcdef/step_2.png",
- "https://media.browser-use.com/screenshots/task_1234567890abcdef/step_3.png"
- ]
-}
-```
-</ResponseExample>
-
-## Screenshot Details
-
-Screenshots are captured automatically during task execution:
-
-- **Step-by-step captures**: Screenshots taken at each major step
-- **Error captures**: Screenshots captured when errors occur
-- **Final result**: Screenshot of the final state when task completes
-- **High resolution**: Screenshots are captured at full browser resolution
-
-## File Format
-
-- All screenshots are saved in PNG format
-- Screenshots maintain the original browser viewport dimensions
-- File names include the task ID and step number for easy identification
-
-## Availability
-
-- Screenshots are available immediately after capture
-- Files are stored for 30 days after task completion
-- Screenshots can be disabled in task settings to reduce storage usage
-
-<Note>
-Screenshots are automatically generated for most tasks unless specifically disabled. The number of screenshots depends on the task complexity and duration.
-</Note>
diff --git a/docs/api-reference/get-task-status.mdx b/docs/api-reference/get-task-status.mdx
deleted file mode 100644
index 04c220174..000000000
--- a/docs/api-reference/get-task-status.mdx
+++ /dev/null
@@ -1,85 +0,0 @@
----
-title: "Get Task Status"
-api: "GET /api/v1/task/{task_id}/status"
-description: "Get the current status of a task"
----
-
-Returns just the current status of a task (created, running, finished, stopped, paused, or failed). This is more lightweight than the full task details endpoint.
-
-## Path Parameters
-
-<ParamField path="task_id" type="string" required>
- ID of the task to check status for
-</ParamField>
-
-## Response
-
-The endpoint returns the status as a simple string value (not wrapped in an object).
-
-<RequestExample>
-```python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-task_id = 'task_1234567890abcdef'
-response = requests.get(f'{BASE_URL}/task/{task_id}/status', headers=HEADERS)
-status = response.json()
-print(f"Task status: {status}")
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/task/{task_id}/status \
- --header 'Authorization: Bearer <token>'
-```
-</RequestExample>
-
-<ResponseExample>
-```json 200
-"finished"
-```
-
-```json 404
-{
- "detail": "Task not found"
-}
-```
-
-```json 422
-{
- "detail": [
- {
- "loc": ["path", "task_id"],
- "msg": "field required",
- "type": "value_error.missing"
- }
- ]
-}
-```
-</ResponseExample>
-
-## Status Values
-
-The status field can have one of the following values:
-
-- `created`: Task is initialized but not yet started
-- `running`: Task is currently executing
-- `finished`: Task has completed successfully
-- `stopped`: Task was manually stopped
-- `paused`: Task execution is temporarily paused
-- `failed`: Task encountered an error and could not complete
-
-## Use Cases
-
-This endpoint is useful for:
-- Polling task status without retrieving full task details
-- Lightweight status checks in monitoring applications
-- Quick status verification before making other API calls
-- Building real-time dashboards with minimal data transfer
-
-<Tip>
-Use this endpoint instead of the full task details endpoint when you only need to check the current status, as it's much faster and uses less bandwidth.
-</Tip>
diff --git a/docs/api-reference/get-task.mdx b/docs/api-reference/get-task.mdx
deleted file mode 100644
index a8d4a8624..000000000
--- a/docs/api-reference/get-task.mdx
+++ /dev/null
@@ -1,187 +0,0 @@
----
-title: "Get Task"
-api: "GET /api/v1/task/{task_id}"
-description: "Get comprehensive information about a task"
----
-
-Returns comprehensive information about a task, including its current status, steps completed, output, and other metadata.
-
-## Path Parameters
-<ParamField path="task_id" type="string" required>
- ID of the task to retrieve
-</ParamField>
-
-
-## Response
-
-<ResponseField name="id" type="string" required>
- The unique identifier for the task
-</ResponseField>
-
-<ResponseField name="task" type="string" required>
- The original task instructions
-</ResponseField>
-
-<ResponseField name="output" type="string | null" required>
- The final output or result from the task (if completed)
-</ResponseField>
-
-<ResponseField name="status" type="enum<string>" required>
- Enumeration of possible task states.
-
- - created: Task is initialized but not yet started
- - running: Task is currently executing
- - finished: Task has completed successfully
- - stopped: Task was manually stopped
- - paused: Task execution is temporarily paused
- - failed: Task encountered an error and could not complete
-
- Available options: `created`, `running`, `finished`, `stopped`, `paused`, `failed`
-</ResponseField>
-
-<ResponseField name="created_at" type="string" required>
- ISO 8601 timestamp of when the task was created
-</ResponseField>
-
-<ResponseField name="steps" type="TaskStepResponse · object[]" required>
- List of task steps with execution details
-
- <Expandable title="Hide child attributes">
- <ResponseField name="id" type="string" required>
- Unique identifier for the step
- </ResponseField>
- <ResponseField name="step" type="integer" required>
- Step number in the execution sequence
- </ResponseField>
- <ResponseField name="evaluation_previous_goal" type="string" required>
- Assessment of the previous goal's completion
- </ResponseField>
- <ResponseField name="next_goal" type="string" required>
- Description of what the next step aims to achieve
- </ResponseField>
- <ResponseField name="url" type="string" required>
- URL of the page where the step was executed
- </ResponseField>
- </Expandable>
-</ResponseField>
-
-<ResponseField name="live_url" type="string | null">
- URL to view live task execution. To preview the url you can directly integrate it in `<iframe>` tag. For example:
- `<iframe src={live_url} width="600" height="450"></iframe>`
- Which will display the task execution and allows you to control the agent live. It is pure VNC implementation.
-</ResponseField>
-
-<ResponseField name="finished_at" type="string | null">
- ISO 8601 timestamp of when the task finished (if completed)
-</ResponseField>
-
-<ResponseField name="browser_data" type="object | null">
- Browser session data (if save_browser_data was enabled)
-
- This field is only available if save_browser_data is set to True in the request.
-
- <Expandable title="Hide child attributes">
- <ResponseField name="browser_data.cookies" type="Cookies · object[]" required>
- List of cookies from the browser session
- </ResponseField>
- </Expandable>
-</ResponseField>
-
-<ResponseField name="user_uploaded_files" type="string[] | null">
- List of files uploaded by the user for this task
-</ResponseField>
-
-<ResponseField name="output_files" type="string[] | null">
- List of files generated during task execution
-</ResponseField>
-
-<ResponseField name="public_share_url" type="string | null">
- Public URL for sharing the task (if public sharing was enabled)
-</ResponseField>
-
-<ResponseField name="metadata" type="object | null">
- Custom metadata key-value pairs associated with the task
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/task/{task_id}"
-
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("GET", url, headers=headers)
-
-print(response.text)
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/task/{task_id} \
- --header 'Authorization: Bearer <token>'
-```
-
-```javascript javascript
-const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
-
-fetch('https://api.browser-use.com/api/v1/task/{task_id}', options)
- .then(response => response.json())
- .then(response => console.log(response))
- .catch(err => console.error(err));
-```
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {
- "id": "<string>",
- "task": "<string>",
- "live_url": "<string>",
- "output": "<string>",
- "status": "created",
- "created_at": "2023-11-07T05:31:56Z",
- "finished_at": "2023-11-07T05:31:56Z",
- "steps": [
- {
- "id": "<string>",
- "step": 123,
- "evaluation_previous_goal": "<string>",
- "next_goal": "<string>",
- "url": "<string>"
- }
- ],
- "browser_data": {
- "cookies": [
- {}
- ]
- },
- "user_uploaded_files": [
- "<string>"
- ],
- "output_files": [
- "<string>"
- ],
- "public_share_url": "<string>",
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
- ```
-
- ```json 422
- {
- "detail": [
- {
- "loc": [
- "<string>"
- ],
- "msg": "<string>",
- "type": "<string>"
- }
- ]
- }
- ```
-</ResponseExample>
diff --git a/docs/api-reference/index.mdx b/docs/api-reference/index.mdx
deleted file mode 100644
index ece0776bf..000000000
--- a/docs/api-reference/index.mdx
+++ /dev/null
@@ -1,120 +0,0 @@
----
-title: "API Reference"
-description: "Complete reference documentation for the Browser Use Cloud API"
-icon: "code"
----
-
-# Browser Use Cloud API
-
-The Browser Use Cloud API allows you to programmatically control browser automation tasks. This API enables you to:
-
-- Create and manage browser automation tasks
-- Schedule recurring tasks
-- Monitor task execution and status
-- Retrieve task outputs and media
-- Manage browser profiles and user data
-- Upload and manage files for task execution
-
-## Base URL
-
-All API requests should be made to the following base URL:
-
-```
-https://api.browser-use.com
-```
-
-## Authentication
-
-All API endpoints (except `/ping`) require authentication using a Bearer token. See the [Authentication](/api-reference/authentication) section for details.
-
-## Rate Limits
-
-The API is subject to rate limiting based on your subscription plan. If you exceed the rate limit, you'll receive a `429 Too Many Requests` response.
-
-## API Endpoints
-
-### Task Management
-
-Core endpoints for creating and managing browser automation tasks:
-
-- [**Run Task**](/api-reference/run-task) - `POST /api/v1/run-task` - Create a new browser automation task
-- [**Get Task**](/api-reference/get-task) - `GET /api/v1/task/{task_id}` - Get comprehensive task information
-- [**Get Task Status**](/api-reference/get-task-status) - `GET /api/v1/task/{task_id}/status` - Get current task status
-- [**List Tasks**](/api-reference/list-tasks) - `GET /api/v1/tasks` - Get paginated list of all tasks
-- [**Stop Task**](/api-reference/stop-task) - `PUT /api/v1/stop-task` - Stop a running task
-- [**Pause Task**](/api-reference/pause-task) - `PUT /api/v1/pause-task` - Pause task execution
-- [**Resume Task**](/api-reference/resume-task) - `PUT /api/v1/resume-task` - Resume a paused task
-
-### Task Media & Files
-
-Endpoints for retrieving task-generated media and files:
-
-- [**Get Task Media**](/api-reference/get-task-media) - `GET /api/v1/task/{task_id}/media` - Get task recordings
-- [**Get Task Screenshots**](/api-reference/get-task-screenshots) - `GET /api/v1/task/{task_id}/screenshots` - Get task screenshots
-- [**Get Task GIF**](/api-reference/get-task-gif) - `GET /api/v1/task/{task_id}/gif` - Get animated task GIF
-- [**Get Task Output File**](/api-reference/files#get-task-output-file) - `GET /api/v1/task/{task_id}/output-file/{file_name}` - Download task output files
-
-### Scheduled Tasks
-
-Endpoints for managing recurring browser automation tasks:
-
-- [**Create Scheduled Task**](/api-reference/scheduled-tasks#create-scheduled-task) - `POST /api/v1/scheduled-task` - Create a new scheduled task
-- [**List Scheduled Tasks**](/api-reference/scheduled-tasks#list-scheduled-tasks) - `GET /api/v1/scheduled-tasks` - Get paginated list of scheduled tasks
-- [**Get Scheduled Task**](/api-reference/scheduled-tasks#get-scheduled-task) - `GET /api/v1/scheduled-task/{task_id}` - Get scheduled task details
-- [**Update Scheduled Task**](/api-reference/scheduled-tasks#update-scheduled-task) - `PUT /api/v1/scheduled-task/{task_id}` - Update scheduled task
-- [**Delete Scheduled Task**](/api-reference/scheduled-tasks#delete-scheduled-task) - `DELETE /api/v1/scheduled-task/{task_id}` - Delete scheduled task
-
-### File Management
-
-Endpoints for uploading and managing files for task execution:
-
-- [**Upload File Presigned URL**](/api-reference/files#upload-file-presigned-url) - `POST /api/v1/uploads/presigned-url` - Get presigned URL for file upload
-
-### Browser Profile Management
-
-Endpoints for managing your browser profiles:
-
-- [**Create Browser Profile**](/api-reference/create-browser-profile) - `POST /api/v1/browser-profiles` - Create a new browser profile
-- [**Get Browser Profile**](/api-reference/get-browser-profile) - `GET /api/v1/browser-profiles/{profile_id}` - Get a browser profile by ID
-- [**List Browser Profiles**](/api-reference/list-browser-profiles) - `GET /api/v1/browser-profiles` - List all browser profiles
-- [**Update Browser Profile**](/api-reference/update-browser-profile) - `PUT /api/v1/browser-profiles/{profile_id}` - Update a browser profile
-- [**Delete Browser Profile**](/api-reference/delete-browser-profile) - `DELETE /api/v1/browser-profiles/{profile_id}` - Delete a browser profile
-
-### User Management
-
-Endpoints for managing your account and checking credits:
-
-- [**Check Balance**](/api-reference/user#check-balance) - `GET /api/v1/balance` - Check API credit balance
-- [**Verify Authentication**](/api-reference/user#verify-authentication) - `GET /api/v1/me` - Verify API key validity
-- [**Delete Browser Profile**](/api-reference/user#delete-browser-profile) - `POST /api/v1/delete-browser-profile-for-user` - Delete browser profile
-
-### Health Check
-
-Endpoints to verify if our Cloud API service is operational:
-
-- [**Ping**](/api-reference/user#ping) - `GET /api/v1/ping` - Health check endpoint
-
-## Response Format
-
-All responses are returned in JSON format. Successful responses will have a 2xx status code, while errors will have a 4xx or 5xx status code.
-
-## Error Handling
-
-The API uses standard HTTP status codes to indicate the success or failure of a request. In case of an error, the response body will contain additional information about the error. See the [Error Handling](/api-reference/errors) section for details.
-
-## Additional Resources
-
-- [**API Models**](/api-reference/models) - Complete reference for all data models and schemas
-- [**Authentication**](/api-reference/authentication) - Learn how to authenticate API requests
-- [**Rate Limits**](/api-reference/rate-limits) - Understand API rate limiting
-- [**Examples**](/api-reference/examples) - Code examples and common use cases
-- [**SDKs**](/api-reference/sdks) - Available SDKs and client libraries
-
-## Getting Started
-
-1. **Get your API key** from the [Browser Use Cloud dashboard](https://cloud.browser-use.com/settings/api-keys)
-2. **Verify your authentication** using the `/api/v1/me` endpoint
-3. **Create your first task** using the `/api/v1/run-task` endpoint
-4. **Monitor task progress** using the `/api/v1/task/{task_id}` endpoint
-
-For more detailed examples and tutorials, see the [Examples](/api-reference/examples) section.
diff --git a/docs/api-reference/list-browser-profiles.mdx b/docs/api-reference/list-browser-profiles.mdx
deleted file mode 100644
index dbbff2102..000000000
--- a/docs/api-reference/list-browser-profiles.mdx
+++ /dev/null
@@ -1,113 +0,0 @@
----
-title: "List Browser Profiles"
-api: "GET /api/v1/browser-profiles"
-description: "Returns a paginated list of all browser profiles belonging to the user."
----
-
-Returns a paginated list of all browser profiles belonging to the user, ordered by creation date. Each profile includes configuration like ad blocker settings, proxy settings, and viewport dimensions.
-
-<Note>
- Pay-as-you-go users can only have one profile. Subscription users can create
- multiple profiles.
-</Note>
-
-### Query Parameters
-
-<ParamField query="page" type="integer" default="1">
- Page number (minimum: 1)
-</ParamField>
-<ParamField query="limit" type="integer" default="10">
- Number of items per page (minimum: 1)
-</ParamField>
-
-### Response
-
-<ResponseField name="profiles" type="array">
- List of browser profiles
- <ResponseField name="profile_id" type="string">
- Unique identifier for the browser profile
- </ResponseField>
- <ResponseField name="profile_name" type="string">
- Name of the browser profile
- </ResponseField>
- <ResponseField name="description" type="string">
- Description of the profile
- </ResponseField>
- <ResponseField name="persist" type="boolean">
- Save cookies, local storage, and session data between tasks
- </ResponseField>
- <ResponseField name="ad_blocker" type="boolean">
- Block ads and popups during automated tasks
- </ResponseField>
- <ResponseField name="proxy" type="boolean">
- Route traffic through mobile proxies for better stealth
- </ResponseField>
- <ResponseField name="proxy_country_code" type="string">
- Country code for the proxy
- </ResponseField>
- <ResponseField name="browser_viewport_width" type="integer">
- Browser viewport width in pixels
- </ResponseField>
- <ResponseField name="browser_viewport_height" type="integer">
- Browser viewport height in pixels
- </ResponseField>
-</ResponseField>
-<ResponseField name="total_pages" type="integer">
- Total number of pages
-</ResponseField>
-<ResponseField name="page" type="integer">
- Current page number
-</ResponseField>
-<ResponseField name="limit" type="integer">
- Number of items per page
-</ResponseField>
-<ResponseField name="total_count" type="integer">
- Total number of browser profiles
-</ResponseField>
-
-<RequestExample>
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-params = {'page': 1, 'limit': 10}
-response = requests.get(f'{BASE_URL}/browser-profiles', headers=HEADERS, params=params)
-profiles_data = response.json()
-print(profiles_data)
-
-````
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/browser-profiles \
- --header 'Authorization: Bearer <token>'
-````
-
-</RequestExample>
-
-<ResponseExample>
-```json 200
-{
- "profiles": [
- {
- "profile_id": "profile_1234567890abcdef",
- "profile_name": "Default Profile",
- "description": "Main automation profile",
- "persist": true,
- "ad_blocker": true,
- "proxy": true,
- "proxy_country_code": "US",
- "browser_viewport_width": 1280,
- "browser_viewport_height": 960
- }
- ],
- "total_pages": 1,
- "page": 1,
- "limit": 10,
- "total_count": 1
-}
-```
-</ResponseExample>
diff --git a/docs/api-reference/list-scheduled-tasks.mdx b/docs/api-reference/list-scheduled-tasks.mdx
deleted file mode 100644
index d0eec6433..000000000
--- a/docs/api-reference/list-scheduled-tasks.mdx
+++ /dev/null
@@ -1,145 +0,0 @@
----
-title: "List Scheduled Tasks"
-api: "GET /api/v1/scheduled-tasks"
-description: "Returns a paginated list of all scheduled tasks belonging to the user"
----
-
-Returns a paginated list of all scheduled tasks belonging to the user, ordered by creation date. Each task includes basic information like schedule type, next run time, and status.
-
-## Query Parameters
-
-<ParamField query="page" type="integer" default="1">
- Page number (minimum: 1)
-</ParamField>
-<ParamField query="limit" type="integer" default="10">
- Number of items per page (minimum: 1)
-</ParamField>
-
-## Response
-
-<ResponseField name="tasks" type="array">
- List of scheduled tasks
- <ResponseField name="id" type="string">
- The unique identifier for the scheduled task
- </ResponseField>
- <ResponseField name="task" type="string">
- Instructions for what the agent should do
- </ResponseField>
- <ResponseField name="save_browser_data" type="boolean">
- Whether to save browser cookies and data
- </ResponseField>
- <ResponseField name="structured_output_json" type="string">
- JSON schema for structured output
- </ResponseField>
- <ResponseField name="llm_model" type="string">
- LLM model to use
- </ResponseField>
- <ResponseField name="use_adblock" type="boolean">
- Whether to use an adblocker
- </ResponseField>
- <ResponseField name="use_proxy" type="boolean">
- Whether to use a proxy
- </ResponseField>
- <ResponseField name="highlight_elements" type="boolean">
- Whether to highlight elements on the page
- </ResponseField>
- <ResponseField name="schedule_type" type="string">
- Type of schedule: "interval" or "cron"
- </ResponseField>
- <ResponseField name="interval_minutes" type="integer">
- Minutes between runs
- </ResponseField>
- <ResponseField name="cron_expression" type="string">
- Cron expression for scheduling
- </ResponseField>
- <ResponseField name="start_at" type="string">
- When to start the schedule
- </ResponseField>
- <ResponseField name="next_run_at" type="string">
- When the next run is scheduled
- </ResponseField>
- <ResponseField name="end_at" type="string">
- When to end the schedule
- </ResponseField>
- <ResponseField name="is_active" type="boolean">
- Whether the scheduled task is active
- </ResponseField>
- <ResponseField name="created_at" type="string">
- When the scheduled task was created
- </ResponseField>
- <ResponseField name="updated_at" type="string">
- When the scheduled task was last updated
- </ResponseField>
-</ResponseField>
-
-<ResponseField name="total_pages" type="integer">
- Total number of pages
-</ResponseField>
-
-<ResponseField name="page" type="integer">
- Current page number
-</ResponseField>
-
-<ResponseField name="limit" type="integer">
- Number of items per page
-</ResponseField>
-
-<ResponseField name="total_count" type="integer">
- Total number of scheduled tasks
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/scheduled-tasks"
-
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("GET", url, headers=headers)
-
-print(response.text)
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/scheduled-tasks \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "tasks": [
- {
- "id": "scheduled_task_1234567890abcdef",
- "task": "Visit example.com and check if the site is up",
- "save_browser_data": false,
- "structured_output_json": null,
- "llm_model": "gpt-4o",
- "use_adblock": true,
- "use_proxy": true,
- "highlight_elements": true,
- "schedule_type": "interval",
- "interval_minutes": 60,
- "cron_expression": null,
- "start_at": "2023-01-01T00:00:00Z",
- "next_run_at": "2023-01-01T01:00:00Z",
- "end_at": "2023-12-31T23:59:59Z",
- "is_active": true,
- "created_at": "2023-01-01T00:00:00Z",
- "updated_at": "2023-01-01T00:00:00Z"
- }
- ],
- "total_pages": 1,
- "page": 1,
- "limit": 10,
- "total_count": 1
-}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/list-tasks.mdx b/docs/api-reference/list-tasks.mdx
deleted file mode 100644
index 582b196c8..000000000
--- a/docs/api-reference/list-tasks.mdx
+++ /dev/null
@@ -1,133 +0,0 @@
----
-title: "List Tasks"
-api: "GET /api/v1/tasks"
-description: "Get a paginated list of all tasks"
----
-
-Returns a paginated list of all tasks belonging to the user, ordered by creation date. Each task includes basic information like status and creation time. For detailed task info, use the get task endpoint.
-
-<ParamField query="page" type="integer" default="1">
- Page number (minimum: 1)
-</ParamField>
-
-<ParamField query="limit" type="integer" default="10">
- Number of items per page (minimum: 1)
-</ParamField>
-
-<ResponseField name="tasks" type="array">
- List of simplified task objects
- <ResponseField name="id" type="string">
- Unique identifier for the task
- </ResponseField>
- <ResponseField name="task" type="string">
- Original task instructions
- </ResponseField>
- <ResponseField name="output" type="string">
- Final output or result from the task
- </ResponseField>
- <ResponseField name="status" type="string">
- Current status of the task
- </ResponseField>
- <ResponseField name="created_at" type="string">
- ISO 8601 timestamp of task creation
- </ResponseField>
- <ResponseField name="finished_at" type="string">
- ISO 8601 timestamp of task completion
- </ResponseField>
- <ResponseField name="live_url" type="string">
- URL to view live task execution
- </ResponseField>
-</ResponseField>
-
-<ResponseField name="total_pages" type="integer">
- Total number of pages available
-</ResponseField>
-
-<ResponseField name="page" type="integer">
- Current page number
-</ResponseField>
-
-<ResponseField name="limit" type="integer">
- Number of items per page
-</ResponseField>
-
-<ResponseField name="total_count" type="integer">
- Total number of tasks across all pages
-</ResponseField>
-
-<RequestExample>
-```python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-# Get first page with 20 tasks
-params = {'page': 1, 'limit': 20}
-response = requests.get(f'{BASE_URL}/tasks', headers=HEADERS, params=params)
-tasks_data = response.json()
-
-print(f"Found {tasks_data['total_count']} total tasks")
-print(f"Showing page {tasks_data['page']} of {tasks_data['total_pages']}")
-
-for task in tasks_data['tasks']:
- print(f"Task {task['id']}: {task['status']}")
-```
-</RequestExample>
-
-<ResponseExample>
-```json
-{
- "tasks": [
- {
- "id": "task_1234567890abcdef",
- "task": "Visit example.com and take a screenshot",
- "output": "Screenshot taken successfully",
- "status": "finished",
- "created_at": "2023-01-01T12:00:00Z",
- "finished_at": "2023-01-01T12:01:30Z",
- "live_url": "https://live.browser-use.com/task/1234567890abcdef"
- },
- {
- "id": "task_0987654321fedcba",
- "task": "Check product availability on shopping site",
- "output": null,
- "status": "running",
- "created_at": "2023-01-01T11:30:00Z",
- "finished_at": null,
- "live_url": "https://live.browser-use.com/task/0987654321fedcba"
- }
- ],
- "total_pages": 5,
- "page": 1,
- "limit": 10,
- "total_count": 42
-}
-```
-</ResponseExample>
-
-## Pagination
-
-The API uses offset-based pagination:
-
-- **page**: Start from page 1
-- **limit**: Maximum 100 items per page
-- **total_pages**: Use this to implement pagination UI
-- **total_count**: Total number of tasks across all pages
-
-## Ordering
-
-Tasks are ordered by creation date (newest first). This ensures that recently created tasks appear at the top of the list.
-
-## Use Cases
-
-This endpoint is useful for:
-- Building task management dashboards
-- Monitoring task execution status
-- Filtering tasks by status
-- Implementing task history views
-
-<Note>
-This endpoint returns simplified task objects for performance. Use the individual task endpoint to get complete task details including steps and browser data.
-</Note>
diff --git a/docs/api-reference/pause-task.mdx b/docs/api-reference/pause-task.mdx
deleted file mode 100644
index 087c26630..000000000
--- a/docs/api-reference/pause-task.mdx
+++ /dev/null
@@ -1,84 +0,0 @@
----
-title: "Pause Task"
-api: "PUT /api/v1/pause-task"
-description: "Pauses execution of a running task"
----
-
-Pauses execution of a running task. The task can be resumed later using the `/resume-task` endpoint. Useful for manual intervention or inspection.
-
-## Parameters
-
-<ParamField query="task_id" type="string" required>
- ID of the task to pause
-</ParamField>
-
-## Response
-
-The endpoint returns an empty response body with a 200 status code on success.
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/pause-task"
-params = {"task_id": "task_1234567890abcdef"}
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("PUT", url, headers=headers, params=params)
-
-print(response.text)
-```
-
-```bash cURL
-curl --request PUT \
- --url 'https://api.browser-use.com/api/v1/pause-task?task_id=task_1234567890abcdef' \
- --header 'Authorization: Bearer <token>'
-```
-
-```javascript javascript
-const options = {method: 'PUT', headers: {Authorization: 'Bearer <token>'}};
-
-fetch('https://api.browser-use.com/api/v1/pause-task?task_id=task_1234567890abcdef', options)
- .then(response => {
- if (response.ok) {
- console.log('Task paused successfully');
- } else {
- return response.json().then(err => { throw err; });
- }
- })
- .catch(err => console.error(err));
-```
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {}
- ```
-
- ```json 422
- {
- "detail": [
- {
- "loc": [
- "query",
- "task_id"
- ],
- "msg": "field required",
- "type": "value_error.missing"
- }
- ]
- }
- ```
-</ResponseExample>
-
-## Usage Notes
-
-- Paused tasks can be resumed using the `/resume-task` endpoint
-- The task status will change to "paused"
-- Browser automation will be temporarily halted
-- Useful for manual intervention or inspection during task execution
-
-<Info>
-Pausing is useful when you need to temporarily halt execution to inspect the current state or make manual adjustments before resuming.
-</Info>
diff --git a/docs/api-reference/ping.mdx b/docs/api-reference/ping.mdx
deleted file mode 100644
index a309710ee..000000000
--- a/docs/api-reference/ping.mdx
+++ /dev/null
@@ -1,38 +0,0 @@
----
-title: "Ping"
-api: "GET /api/v1/ping"
-description: "Check if the server is running and responding"
----
-
-Use this endpoint to check if the server is running and responding. This is the only endpoint that doesn't require authentication.
-
-## Response
-
-A successful response has a 200 status code with an empty JSON object.
-
-<RequestExample>
-
-```python python
-import requests
-
-BASE_URL = 'https://api.browser-use.com/api/v1'
-
-response = requests.get(f'{BASE_URL}/ping')
-if response.status_code == 200:
- print("Server is up and running")
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/ping
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/resume-task.mdx b/docs/api-reference/resume-task.mdx
deleted file mode 100644
index f8772d1f7..000000000
--- a/docs/api-reference/resume-task.mdx
+++ /dev/null
@@ -1,79 +0,0 @@
----
-title: "Resume Task"
-api: "PUT /api/v1/resume-task"
-description: "Resumes execution of a previously paused task"
----
-
-Resumes execution of a previously paused task. The task will continue from where it was paused. You can't resume a stopped task.
-
-## Parameters
-
-<ParamField query="task_id" type="string" required>
- ID of the task to resume
-</ParamField>
-
-## Response
-
-The endpoint returns an empty response body with a 200 status code on success.
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/resume-task"
-params = {"task_id": "task_1234567890abcdef"}
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("PUT", url, headers=headers, params=params)
-
-print(response.text)
-```
-
-```bash cURL
-curl --request PUT \
- --url 'https://api.browser-use.com/api/v1/resume-task?task_id=task_1234567890abcdef' \
- --header 'Authorization: Bearer <token>'
-```
-
-```javascript javascript
-const options = {method: 'PUT', headers: {Authorization: 'Bearer <token>'}};
-
-fetch('https://api.browser-use.com/api/v1/resume-task?task_id=task_1234567890abcdef', options)
- .then(response => response.json())
- .then(response => console.log(response))
- .catch(err => console.error(err));
-```
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {}
- ```
-
- ```json 422
- {
- "detail": [
- {
- "loc": [
- "query",
- "task_id"
- ],
- "msg": "field required",
- "type": "value_error.missing"
- }
- ]
- }
- ```
-</ResponseExample>
-
-## Usage Notes
-
-- Only paused tasks can be resumed
-- The task status will change from "paused" to "running"
-- Browser automation will continue from where it was paused
-- Stopped tasks cannot be resumed - you must create a new task instead
-
-<Warning>
-You cannot resume a task that has been stopped. Only paused tasks can be resumed.
-</Warning>
diff --git a/docs/api-reference/run-task.mdx b/docs/api-reference/run-task.mdx
deleted file mode 100644
index 5f3936ea0..000000000
--- a/docs/api-reference/run-task.mdx
+++ /dev/null
@@ -1,201 +0,0 @@
----
-title: "Run Task"
-api: "POST /api/v1/run-task"
-description: "Requires an active subscription. Returns the task ID that can be used to track progress."
----
-
-Creates a new browser automation task and returns the task ID that can be used to track progress.
-
-## Request Body
-
-<ParamField body="task" type="string" required>
- Instructions for what the agent should do. You can try it out at https://cloud.browser-use.com/
-</ParamField>
-
-<ParamField body="secrets" type="object">
- Dictionary of secrets to be used by the agent. Secrets are safely encrypted before storing in the database.
-</ParamField>
-
-<ParamField body="allowed_domains" type="array">
- List of domains that the agent is allowed to visit (e.g. ["google.com", "amazon.com", "*.skyscanner.com"]). <br/>
- We recommend using a wildcard to allow all subdomains of a domain (e.g. "*.skyscanner.com"). <br/>
- If not set, the agent will be allowed to visit all domains (not recommended if you are using secrets).
-</ParamField>
-
-<ParamField body="browser_profile_id" type="string">
- ID of the browser profile to use. If not set, the default profile will be used.
-</ParamField>
-
-<ParamField body="save_browser_data" type="boolean" default="false">
- If set to True, the browser cookies and other data will be saved. Cookies are safely encrypted before storing in the database.
-</ParamField>
-
-<ParamField body="structured_output_json" type="string">
- If set, the agent will use this JSON schema as the output model (see example here: https://docs.browser-use.com/cloud/implementation#structured-output-example).
-</ParamField>
-
-<ParamField body="llm_model" type="string" default="gpt-4.1">
- LLM model to use.
- Available options:
- - gpt-4.1
- - gpt-4.1-mini
- - o4-mini
- - o3
- - gemini-2.5-flash
- - gemini-2.5-pro
- - claude-sonnet-4-20250514
-</ParamField>
-
-<ParamField body="use_adblock" type="boolean" default="true">
- If set to True, the agent will use an adblocker.
-</ParamField>
-
-<ParamField body="use_proxy" type="boolean" default="true">
- If set to True, the agent will use a (mobile) proxy. Note that proxy is required for captcha solving, so if you disable proxy, you will not be able to solve captchas.
-</ParamField>
-
-<ParamField body="proxy_country_code" type="string" default="us">
- Country code for residential proxy. Must be one of: 'us', 'fr', 'it', 'jp', 'au', 'de', 'fi', 'ca'. Default is 'us'.
-</ParamField>
-
-<ParamField body="highlight_elements" type="boolean" default="true">
- If set to True, the agent will highlight the elements on the page.
-</ParamField>
-
-<ParamField body="included_file_names" type="array">
- File names to include in the task (note: use uploads/presigned-url endpoint to upload the files first!). E.g. ['file1.txt', 'file2.csv']
-</ParamField>
-
-<ParamField body="browser_viewport_width" type="integer" default="1280">
- Width of the browser viewport in pixels. Default is 1280.
-</ParamField>
-
-<ParamField body="browser_viewport_height" type="integer" default="960">
- Height of the browser viewport in pixels. Default is 960.
-</ParamField>
-
-<ParamField body="max_agent_steps" type="integer" default="75">
- Maximum number of agent steps to take. Default is 75. Maximum is 200.
-</ParamField>
-
-<ParamField body="enable_public_share" type="boolean" default="false">
- If set to True, enables public sharing of the task execution. When enabled, a public_share_url will be generated that allows others to view the task results without authentication.
-</ParamField>
-
-<ParamField body="metadata" type="object">
- Optional dictionary of string key-value pairs for custom tagging. Max 10 pairs. Keys: strings (max 100 chars, non-empty). Values: strings (max 1000 chars).
-</ParamField>
-
-## Response
-
-<ResponseField name="id" type="string">
- The unique identifier for the created task.
-</ResponseField>
-
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/run-task"
-
-payload = {
- "task": "<string>",
- "secrets": {},
- "allowed_domains": ["<string>"],
- "save_browser_data": True,
- "structured_output_json": "<string>",
- "llm_model": "gpt-4o",
- "use_adblock": True,
- "use_proxy": True,
- "proxy_country_code": "us",
- "highlight_elements": True,
- "included_file_names": ["<string>"],
- "browser_viewport_width": 123,
- "browser_viewport_height": 123,
- "max_agent_steps": 123,
- "enable_public_share": True,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
-headers = {
- "Authorization": "Bearer <token>",
- "Content-Type": "application/json"
-}
-
-response = requests.request("POST", url, json=payload, headers=headers)
-
-print(response.text)
-```
-
-```bash cURL
-curl --request POST \
- --url https://api.browser-use.com/api/v1/run-task \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{
- "task": "<string>",
- "secrets": {},
- "allowed_domains": [
- "<string>"
- ],
- "save_browser_data": true,
- "structured_output_json": "<string>",
- "llm_model": "gpt-4o",
- "use_adblock": true,
- "use_proxy": true,
- "proxy_country_code": "us",
- "highlight_elements": true,
- "included_file_names": [
- "<string>"
- ],
- "browser_viewport_width": 123,
- "browser_viewport_height": 123,
- "max_agent_steps": 123,
- "enable_public_share": true,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}'
-```
-
-```javascript javascript
-const options = {
- method: 'POST',
- headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
- body: '{"task":"<string>","secrets":{},"allowed_domains":["<string>"],"save_browser_data":true,"structured_output_json":"<string>","llm_model":"gpt-4o","use_adblock":true,"use_proxy":true,"proxy_country_code":"us","highlight_elements":true,"included_file_names":["<string>"],"browser_viewport_width":123,"browser_viewport_height":123,"max_agent_steps":123,"enable_public_share":true,"metadata":{"campaign":"q4-automation","team":"marketing"}}'
-};
-
-fetch('https://api.browser-use.com/api/v1/run-task', options)
- .then(response => response.json())
- .then(response => console.log(response))
- .catch(err => console.error(err));
-
-```
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {
- "id": "task_1234567890abcdef"
- }
- ```
-
- ```json 422
- {
- "detail": [
- {
- "loc": [
- "<string>"
- ],
- "msg": "<string>",
- "type": "<string>"
- }
- ]
- }
- ```
-</ResponseExample>
diff --git a/docs/api-reference/search-url.mdx b/docs/api-reference/search-url.mdx
deleted file mode 100644
index 80d241870..000000000
--- a/docs/api-reference/search-url.mdx
+++ /dev/null
@@ -1,115 +0,0 @@
----
-title: "Search URL"
-api: "POST https://api.browser-use.com/api/v1/search-url"
-description: "Extract specific content from a given URL using AI"
----
-
-## Overview
-
-Extract content from a specific website by navigating it in real-time. Clicks through pages to find exactly what you need.
-
-💡 **Complete working example**: [search_url.py](https://github.com/browser-use/browser-use/blob/main/examples/search/search_url.py)
-
-## Request
-
-<ParamField body="url" type="string" required>
- The URL to extract content from
-</ParamField>
-
-<ParamField body="query" type="string" required>
- What specific content to look for and extract from the URL
-</ParamField>
-
-<ParamField body="depth" type="integer" default="2">
- How deep to navigate within the website (2-5). Higher depth = more thorough exploration through multiple page clicks.
-</ParamField>
-
-## Response
-
-<ResponseField name="url" type="string">
- The URL that was processed
-</ResponseField>
-
-<ResponseField name="content" type="string">
- Extracted content relevant to the search query
-</ResponseField>
-
-<ResponseExample>
-```json Response
-{
- "url": "https://example.com",
- "content": "Relevant content extracted from the website based on your query..."
-}
-```
-</ResponseExample>
-
-## Example
-
-<RequestExample>
-```python Python
-import aiohttp
-import asyncio
-
-async def search_website():
- payload = {
- "url": "https://www.artificialintelligence-news.com/",
- "query": "Latest AI News",
- "depth": 2
- }
-
- headers = {
- "Authorization": "Bearer YOUR_API_KEY",
- "Content-Type": "application/json"
- }
-
- async with aiohttp.ClientSession() as session:
- async with session.post(
- "https://api.browser-use.com/api/v1/search-url",
- json=payload,
- headers=headers
- ) as response:
- return await response.json()
-
-result = asyncio.run(search_website())
-print(result)
-```
-
-```javascript JavaScript
-const response = await fetch('https://api.browser-use.com/api/v1/search-url', {
- method: 'POST',
- headers: {
- 'Authorization': 'Bearer YOUR_API_KEY',
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- url: 'https://www.artificialintelligence-news.com/',
- query: 'Latest AI News',
- depth: 2
- })
-});
-
-const result = await response.json();
-console.log(result);
-```
-
-```bash cURL
-curl -X POST "https://api.browser-use.com/api/v1/search-url" \
- -H "Authorization: Bearer YOUR_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "url": "https://www.artificialintelligence-news.com/",
- "query": "Latest AI News",
- "depth": 2
- }'
-```
-</RequestExample>
-
-## Pricing
-
-**Cost per request**: `1 cent × depth`
-
-Examples:
-- depth=2 = 2 cents per request (default value)
-- depth=3 = 3 cents per request
-- depth=4 = 4 cents per request
-- depth=5 = 5 cents per request
diff --git a/docs/api-reference/simple-search.mdx b/docs/api-reference/simple-search.mdx
deleted file mode 100644
index 6d3ae0e22..000000000
--- a/docs/api-reference/simple-search.mdx
+++ /dev/null
@@ -1,126 +0,0 @@
----
-title: "Simple Search"
-api: "POST https://api.browser-use.com/api/v1/simple-search"
-description: "Search Google and extract relevant content from multiple top results"
----
-
-## Overview
-
-Search and extract content from multiple websites in real-time. Gets live data by actually visiting sites, not cached results.
-
-💡 **Complete working example**: [simple_search.py](https://github.com/browser-use/browser-use/blob/main/examples/search/simple_search.py)
-
-## Request
-
-<ParamField body="query" type="string" required>
- The search query to process
-</ParamField>
-
-<ParamField body="max_websites" type="integer" default="5">
- Maximum number of websites to process from search results (1-10)
-</ParamField>
-
-<ParamField body="depth" type="integer" default="2">
- How deep to navigate within each website (2-5). Higher depth = more thorough exploration through multiple page clicks.
-</ParamField>
-
-## Response
-
-<ResponseField name="results" type="array">
- Array of results from processed websites
-
- <Expandable title="result object">
- <ResponseField name="url" type="string">
- The URL of the processed website
- </ResponseField>
-
- <ResponseField name="content" type="string">
- Extracted content relevant to the search query
- </ResponseField>
- </Expandable>
-</ResponseField>
-
-<ResponseExample>
-```json Response
-{
- "results": [
- {
- "url": "https://example1.com",
- "content": "Relevant content extracted from the first website..."
- },
- {
- "url": "https://example2.com",
- "content": "Relevant content extracted from the second website..."
- }
- ]
-}
-```
-</ResponseExample>
-
-<RequestExample>
-```python Python
-import aiohttp
-import asyncio
-
-async def search():
- payload = {
- "query": "latest developments in artificial intelligence",
- "max_websites": 5,
- "depth": 2
- }
-
- headers = {
- "Authorization": "Bearer YOUR_API_KEY",
- "Content-Type": "application/json"
- }
-
- async with aiohttp.ClientSession() as session:
- async with session.post(
- "https://api.browser-use.com/api/v1/simple-search",
- json=payload,
- headers=headers
- ) as response:
- return await response.json()
-
-result = asyncio.run(search())
-print(result)
-```
-
-```javascript JavaScript
-const response = await fetch('https://api.browser-use.com/api/v1/simple-search', {
- method: 'POST',
- headers: {
- 'Authorization': 'Bearer YOUR_API_KEY',
- 'Content-Type': 'application/json'
- },
- body: JSON.stringify({
- query: 'latest developments in artificial intelligence',
- max_websites: 5,
- depth: 2
- })
-});
-
-const result = await response.json();
-console.log(result);
-```
-
-```bash cURL
-curl -X POST "https://api.browser-use.com/api/v1/simple-search" \
- -H "Authorization: Bearer YOUR_API_KEY" \
- -H "Content-Type: application/json" \
- -d '{
- "query": "latest developments in artificial intelligence",
- "max_websites": 5,
- "depth": 2
- }'
-```
-</RequestExample>
-
-## Pricing
-
-**Cost per request**: `1 cent × depth × max_websites`
-
-Examples:
-- depth=2, max_websites=5 = 10 cents per request (default values)
-- depth=2, max_websites=3 = 6 cents per request
-- depth=3, max_websites=2 = 6 cents per request
diff --git a/docs/api-reference/stop-task.mdx b/docs/api-reference/stop-task.mdx
deleted file mode 100644
index 24655d408..000000000
--- a/docs/api-reference/stop-task.mdx
+++ /dev/null
@@ -1,79 +0,0 @@
----
-title: "Stop Task"
-api: "PUT /api/v1/stop-task"
-description: "Stops a running browser automation task immediately."
----
-
-Stops a running browser automation task immediately. The task cannot be resumed after being stopped. Use `/pause-task` endpoint instead if you want to temporarily halt execution.
-
-## Parameters
-
-<ParamField query="task_id" type="string" required>
- ID of the task to stop
-</ParamField>
-
-## Response
-
-The endpoint returns an empty response body with a 200 status code on success.
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/stop-task"
-params = {"task_id": "task_1234567890abcdef"}
-headers = {"Authorization": "Bearer <token>"}
-
-response = requests.request("PUT", url, headers=headers, params=params)
-
-print(response.text)
-```
-
-```bash cURL
-curl --request PUT \
- --url 'https://api.browser-use.com/api/v1/stop-task?task_id=task_1234567890abcdef' \
- --header 'Authorization: Bearer <token>'
-```
-
-```javascript javascript
-const options = {method: 'PUT', headers: {Authorization: 'Bearer <token>'}};
-
-fetch('https://api.browser-use.com/api/v1/stop-task?task_id=task_1234567890abcdef', options)
- .then(response => response.json())
- .then(response => console.log(response))
- .catch(err => console.error(err));
-```
-</RequestExample>
-
-<ResponseExample>
- ```json 200
- {}
- ```
-
- ```json 422
- {
- "detail": [
- {
- "loc": [
- "query",
- "task_id"
- ],
- "msg": "field required",
- "type": "value_error.missing"
- }
- ]
- }
- ```
-</ResponseExample>
-
-## Usage Notes
-
-- Once a task is stopped, it cannot be resumed
-- The task status will change to "stopped"
-- Any ongoing browser automation will be immediately terminated
-- Use the pause endpoint if you need to temporarily halt execution with the ability to resume later
-
-<Warning>
-Stopping a task is irreversible. If you need to pause execution temporarily, use the `/pause-task` endpoint instead.
-</Warning>
diff --git a/docs/api-reference/update-browser-profile.mdx b/docs/api-reference/update-browser-profile.mdx
deleted file mode 100644
index aaf9491ce..000000000
--- a/docs/api-reference/update-browser-profile.mdx
+++ /dev/null
@@ -1,111 +0,0 @@
----
-title: "Update Browser Profile"
-api: "PUT /api/v1/browser-profiles/{profile_id}"
-description: "Update a browser profile with partial updates. Only the fields you want to change need to be included."
----
-
-Update a browser profile with partial updates. Only the fields you want to change need to be included.
-
-### Path Parameters
-
-<ParamField path="profile_id" type="string" required>
- ID of the browser profile to update
-</ParamField>
-
-### Request Body
-
-<ParamField body="profile_name" type="string">
- Name of the browser profile
-</ParamField>
-<ParamField body="description" type="string">
- Description of the profile
-</ParamField>
-<ParamField body="persist" type="boolean">
- Save cookies, local storage, and session data between tasks
-</ParamField>
-<ParamField body="ad_blocker" type="boolean">
- Block ads and popups during automated tasks
-</ParamField>
-<ParamField body="proxy" type="boolean">
- Route traffic through mobile proxies for better stealth
-</ParamField>
-<ParamField body="proxy_country_code" type="string">
- Country code for the proxy
-</ParamField>
-<ParamField body="browser_viewport_width" type="integer">
- Browser viewport width in pixels
-</ParamField>
-<ParamField body="browser_viewport_height" type="integer">
- Browser viewport height in pixels
-</ParamField>
-
-### Response
-
-<ResponseField name="profile_id" type="string">
- Unique identifier for the updated browser profile
-</ResponseField>
-<ResponseField name="profile_name" type="string">
- Name of the browser profile
-</ResponseField>
-<ResponseField name="description" type="string">
- Description of the profile
-</ResponseField>
-<ResponseField name="persist" type="boolean">
- Save cookies, local storage, and session data between tasks
-</ResponseField>
-<ResponseField name="ad_blocker" type="boolean">
- Block ads and popups during automated tasks
-</ResponseField>
-<ResponseField name="proxy" type="boolean">
- Route traffic through mobile proxies for better stealth
-</ResponseField>
-<ResponseField name="proxy_country_code" type="string">
- Country code for the proxy
-</ResponseField>
-<ResponseField name="browser_viewport_width" type="integer">
- Browser viewport width in pixels
-</ResponseField>
-<ResponseField name="browser_viewport_height" type="integer">
- Browser viewport height in pixels
-</ResponseField>
-
-<RequestExample>
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-profile_id = 'profile_1234567890abcdef'
-update_data = {"ad_blocker": False}
-response = requests.put(f'{BASE_URL}/browser-profiles/{profile_id}', headers=HEADERS, json=update_data)
-print(response.json())
-
-````
-
-```bash curl
-curl --request PUT \
- --url https://api.browser-use.com/api/v1/browser-profiles/profile_1234567890abcdef \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{"ad_blocker": false}'
-````
-
-</RequestExample>
-
-<ResponseExample>
-```json 200
-{
- "profile_id": "profile_1234567890abcdef",
- "profile_name": "Default Profile",
- "description": "Main automation profile",
- "persist": true,
- "ad_blocker": false,
- "proxy": true,
- "proxy_country_code": "US",
- "browser_viewport_width": 1280,
- "browser_viewport_height": 960
-}
-```
-</ResponseExample>
diff --git a/docs/api-reference/update-scheduled-task.mdx b/docs/api-reference/update-scheduled-task.mdx
deleted file mode 100644
index 725d74638..000000000
--- a/docs/api-reference/update-scheduled-task.mdx
+++ /dev/null
@@ -1,205 +0,0 @@
----
-title: "Update Scheduled Task"
-api: "PUT /api/v1/scheduled-task/{task_id}"
-description: "Updates a scheduled task with partial updates"
----
-
-Updates a scheduled task with partial updates. You can update any combination of the task configuration fields without affecting the others.
-
-## Path Parameters
-
-<ParamField path="task_id" type="string" required>
- ID of the scheduled task to update
-</ParamField>
-
-## Request Body
-
-<ParamField body="task" type="string">
- Instructions for what the agent should do
-</ParamField>
-<ParamField body="schedule_type" type="string">
- Type of schedule: "interval" or "cron"
-</ParamField>
-<ParamField body="interval_minutes" type="integer">
- Minutes between runs (required if schedule_type is "interval")
-</ParamField>
-<ParamField body="cron_expression" type="string">
- Cron expression for scheduling (required if schedule_type is "cron")
-</ParamField>
-<ParamField body="start_at" type="string">
- When to start the schedule (ISO 8601 format)
-</ParamField>
-<ParamField body="end_at" type="string">
- When to end the schedule (ISO 8601 format)
-</ParamField>
-<ParamField body="is_active" type="boolean">
- Whether the scheduled task is active
-</ParamField>
-<ParamField body="use_adblock" type="boolean">
- Whether to use an adblocker
-</ParamField>
-<ParamField body="use_proxy" type="boolean">
- Whether to use a proxy
-</ParamField>
-<ParamField body="highlight_elements" type="boolean">
- Whether to highlight elements on the page
-</ParamField>
-<ParamField body="llm_model" type="string">
- LLM model to use. Available options: gpt-4.1, gpt-4.1-mini, o4-mini, o3, gemini-2.5-flash, gemini-2.5-pro, claude-sonnet-4-20250514
-</ParamField>
-<ParamField body="save_browser_data" type="boolean">
- Whether to save browser cookies and data between runs
-</ParamField>
-<ParamField body="structured_output_json" type="string">
- JSON schema for structured output
-</ParamField>
-
-<ParamField body="metadata" type="object">
- Optional dictionary of string key-value pairs for custom tagging. Max 10 pairs. Keys: strings (max 100 chars, non-empty). Values: strings (max 1000 chars).
-</ParamField>
-
-## Response
-
-Returns the updated scheduled task object with the same format as the Get Scheduled Task response.
-
-<ResponseField name="id" type="string">
- The unique identifier for the scheduled task
-</ResponseField>
-
-<ResponseField name="task" type="string">
- Instructions for what the agent should do
-</ResponseField>
-
-<ResponseField name="save_browser_data" type="boolean">
- Whether to save browser cookies and data
-</ResponseField>
-
-<ResponseField name="structured_output_json" type="string">
- JSON schema for structured output
-</ResponseField>
-
-<ResponseField name="llm_model" type="string">
- LLM model to use
-</ResponseField>
-
-<ResponseField name="use_adblock" type="boolean">
- Whether to use an adblocker
-</ResponseField>
-
-<ResponseField name="use_proxy" type="boolean">
- Whether to use a proxy
-</ResponseField>
-
-<ResponseField name="highlight_elements" type="boolean">
- Whether to highlight elements on the page
-</ResponseField>
-
-<ResponseField name="schedule_type" type="string">
- Type of schedule: "interval" or "cron"
-</ResponseField>
-
-<ResponseField name="interval_minutes" type="integer">
- Minutes between runs
-</ResponseField>
-
-<ResponseField name="cron_expression" type="string">
- Cron expression for scheduling
-</ResponseField>
-
-<ResponseField name="start_at" type="string">
- When to start the schedule
-</ResponseField>
-
-<ResponseField name="next_run_at" type="string">
- When the next run is scheduled
-</ResponseField>
-
-<ResponseField name="end_at" type="string">
- When to end the schedule
-</ResponseField>
-
-<ResponseField name="is_active" type="boolean">
- Whether the scheduled task is active
-</ResponseField>
-
-<ResponseField name="created_at" type="string">
- When the scheduled task was created
-</ResponseField>
-
-<ResponseField name="updated_at" type="string">
- When the scheduled task was last updated
-</ResponseField>
-
-<ResponseField name="metadata" type="object | null">
- Custom metadata key-value pairs associated with the scheduled task
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-url = "https://api.browser-use.com/api/v1/scheduled-task/{task_id}"
-
-headers = {"Authorization": "Bearer <token>"}
-
-payload = {
- "task": "Updated task description",
- "is_active": False,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
-
-response = requests.request("PUT", url, headers=headers, json=payload)
-
-print(response.text)
-```
-
-```bash curl
-curl --request PUT \
- --url https://api.browser-use.com/api/v1/scheduled-task/{task_id} \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{
- "task": "Updated task description",
- "is_active": false,
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
- }'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "id": "scheduled_task_1234567890abcdef",
- "task": "Updated task description",
- "save_browser_data": false,
- "structured_output_json": null,
- "llm_model": "gpt-4o",
- "use_adblock": true,
- "use_proxy": true,
- "highlight_elements": true,
- "schedule_type": "interval",
- "interval_minutes": 60,
- "cron_expression": null,
- "start_at": "2023-01-01T00:00:00Z",
- "next_run_at": "2023-01-01T01:00:00Z",
- "end_at": "2023-12-31T23:59:59Z",
- "is_active": false,
- "created_at": "2023-01-01T00:00:00Z",
- "updated_at": "2023-01-01T00:30:00Z",
- "metadata": {
- "campaign": "q4-automation",
- "team": "marketing"
- }
-}
-```
-
-</ResponseExample>
diff --git a/docs/api-reference/upload-file-presigned-url.mdx b/docs/api-reference/upload-file-presigned-url.mdx
deleted file mode 100644
index 842d45056..000000000
--- a/docs/api-reference/upload-file-presigned-url.mdx
+++ /dev/null
@@ -1,115 +0,0 @@
----
-title: "Upload File Presigned URL"
-api: "POST /api/v1/uploads/presigned-url"
-description: "Returns a presigned URL for uploading a file to the user's files bucket"
----
-
-Returns a presigned URL for uploading a file to the user's files bucket. After uploading a file, you can include it in tasks using the `included_file_names` field in the `RunTaskRequest`.
-
-## Request Body
-
-<ParamField body="file_name" type="string" required>
- Name of the file to upload (e.g., 'data.csv', 'image.png')
-</ParamField>
-<ParamField body="content_type" type="string" required>
- Content type of the file (e.g., 'text/csv', 'image/png', 'application/pdf'). Only images and documents are supported.
-</ParamField>
-
-## Response
-
-<ResponseField name="upload_url" type="string">
- A presigned URL to upload the file to.
-</ResponseField>
-
-<RequestExample>
-
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-# Step 1: Get a presigned URL
-file_data = {
- "file_name": "data.csv",
- "content_type": "text/csv"
-}
-
-response = requests.post(f'{BASE_URL}/uploads/presigned-url', headers=HEADERS, json=file_data)
-upload_url = response.json()['upload_url']
-
-# Step 2: Upload the file to the presigned URL
-with open('local_data.csv', 'rb') as file:
- file_content = file.read()
-
-upload_response = requests.put(upload_url, data=file_content, headers={
- 'Content-Type': 'text/csv'
-})
-
-if upload_response.status_code == 200:
- print("File uploaded successfully")
-
-# Step 3: Use the file in a task
-task_data = {
- "task": "Process the data in the CSV file and extract the top 5 rows",
- "included_file_names": ["data.csv"]
-}
-
-task_response = requests.post(f'{BASE_URL}/run-task', headers=HEADERS, json=task_data)
-task_id = task_response.json()['id']
-print(f"Task created with ID: {task_id}")
-```
-
-```bash curl
-curl --request POST \
- --url https://api.browser-use.com/api/v1/uploads/presigned-url \
- --header 'Authorization: Bearer <token>' \
- --header 'Content-Type: application/json' \
- --data '{
- "file_name": "data.csv",
- "content_type": "text/csv"
- }'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-{
- "upload_url": "https://storage.browser-use.com/uploads/user_123/data.csv?signature=..."
-}
-```
-
-</ResponseExample>
-
-## File Usage in Tasks
-
-To use uploaded files in your tasks, include their names in the `included_file_names` array when creating a task:
-
-```json
-{
- "task": "Process the data in the CSV file and extract the top 5 rows",
- "included_file_names": ["data.csv", "config.json"]
-}
-```
-
-The agent will have access to these files during task execution and can read their contents.
-
-## Supported File Types
-
-The following file types are supported for upload:
-
-- Text files: `.txt`, `.csv`, `.json`, `.xml`, `.html`, `.md`
-- Images: `.jpg`, `.jpeg`, `.png`, `.gif`, `.webp`
-- Documents: `.pdf`, `.doc`, `.docx`, `.xls`, `.xlsx`, `.ppt`, `.pptx`
-
-## File Size Limits
-
-- Maximum file size: 10 MB per file
-- Maximum total size of all files for a task: 50 MB
-
-<Note>
-Files are automatically deleted after 30 days unless they are used in a scheduled task.
-</Note>
diff --git a/docs/api-reference/user.mdx b/docs/api-reference/user.mdx
deleted file mode 100644
index 26ab137c4..000000000
--- a/docs/api-reference/user.mdx
+++ /dev/null
@@ -1,61 +0,0 @@
----
-title: "Me"
-api: "GET /api/v1/me"
-description: "Returns a boolean value indicating if the API key is valid and the user is authenticated"
----
-
-Returns a boolean value indicating if the API key is valid and the user is authenticated.
-
-## Response
-
-The endpoint returns a boolean value directly (not wrapped in an object):
-- `true` if the API key is valid and the user is authenticated
-- `false` if the API key is invalid or the user is not authenticated
-
-<RequestExample>
-
-```python python
-import requests
-
-API_KEY = 'your_api_key_here'
-BASE_URL = 'https://api.browser-use.com/api/v1'
-HEADERS = {'Authorization': f'Bearer {API_KEY}'}
-
-response = requests.get(f'{BASE_URL}/me', headers=HEADERS)
-is_authenticated = response.json()
-if is_authenticated:
- print("API key is valid")
-else:
- print("API key is invalid")
-```
-
-```bash curl
-curl --request GET \
- --url https://api.browser-use.com/api/v1/me \
- --header 'Authorization: Bearer <token>'
-```
-
-</RequestExample>
-
-<ResponseExample>
-
-```json 200
-true
-```
-
-```json 401
-false
-```
-
-</ResponseExample>
-
-## Usage Notes
-
-- This endpoint is useful for validating API keys before making other API calls
-- Unlike other endpoints, this returns a simple boolean value rather than an object
-- A `true` response confirms both authentication and authorization
-- This endpoint can be used for health checks of your API integration
-
-<Tip>
-Use this endpoint to verify your API key is working correctly before making other API calls, especially in automated systems.
-</Tip>
diff --git a/docs/cloud/authentication.mdx b/docs/cloud/v1/authentication.mdx
similarity index 97%
rename from docs/cloud/authentication.mdx
rename to docs/cloud/v1/authentication.mdx
index 278b02a48..cadd7ef14 100644
--- a/docs/cloud/authentication.mdx
+++ b/docs/cloud/v1/authentication.mdx
@@ -33,7 +33,7 @@ print(response.json())
## Verifying Authentication
-You can verify that your API key is valid by making a request to the `/api/v1/me` endpoint. See the [Me endpoint documentation](../api-reference/user) for more details.
+You can verify that your API key is valid by making a request to the `/api/v1/me` endpoint. See the [Me endpoint documentation](/api-reference/api-v1/me) for more details.
## API Key Security
diff --git a/docs/cloud/custom-sdk.mdx b/docs/cloud/v1/custom-sdk.mdx
similarity index 100%
rename from docs/cloud/custom-sdk.mdx
rename to docs/cloud/v1/custom-sdk.mdx
diff --git a/docs/cloud/implementation.mdx b/docs/cloud/v1/implementation.mdx
similarity index 98%
rename from docs/cloud/implementation.mdx
rename to docs/cloud/v1/implementation.mdx
index c7b400e33..2d80250f1 100644
--- a/docs/cloud/implementation.mdx
+++ b/docs/cloud/v1/implementation.mdx
@@ -1,5 +1,5 @@
---
-title: "Implementing the API"
+title: "V1 Implementation"
description: "Learn how to implement the Browser Use API in Python"
icon: "code"
---
@@ -8,7 +8,7 @@ This guide shows how to implement common API patterns using Python. We'll create
## Basic Implementation
-For all settings see [Run Task](cloud/api-v10/run-task).
+For all settings see [Run Task](/api-reference/api-v1/run-task).
Here's a simple implementation using Python's `requests` library to stream the task steps:
diff --git a/docs/cloud/n8n-browser-use-integration.mdx b/docs/cloud/v1/n8n-browser-use-integration.mdx
similarity index 81%
rename from docs/cloud/n8n-browser-use-integration.mdx
rename to docs/cloud/v1/n8n-browser-use-integration.mdx
index fd852588b..b18641a8b 100644
--- a/docs/cloud/n8n-browser-use-integration.mdx
+++ b/docs/cloud/v1/n8n-browser-use-integration.mdx
@@ -11,7 +11,7 @@ icon: "plug"
> 3. Waits for the task to finish via a **webhook**
> 4. Formats the output and drops a rich message into Slack
-You can grab the workflow JSON below – copy it and import it into n8n, plug in your API keys and hit *Execute* 🚀.
+You can grab the workflow JSON below – copy it and import it into n8n, plug in your API keys and hit _Execute_ 🚀.
---
@@ -19,7 +19,7 @@ You can grab the workflow JSON below – copy it and import it into n8n, plug in
• **Autonomous browsing** – Browser Use opens pages like a real user (using Playwright + Chromium), follows links, clicks buttons and reads DOM content.
-• **Structured output** – You tell the agent *exactly* which fields you need. No brittle regex or XPaths.
+• **Structured output** – You tell the agent _exactly_ which fields you need. No brittle regex or XPaths.
• **Scales effortlessly** – Kick off hundreds of tasks and monitor them through the Cloud API.
@@ -47,16 +47,18 @@ SLACK_WEBHOOK_URL="https://hooks.slack.com/services/…"
1. Copy the [workflow JSON](#workflow-json) below to your clipboard.
2. In n8n click **Import** → **From Clipboard** and paste the JSON.
3. Hit **Import**
-4. Replace the *Browser-Use API Key* credential and *Slack webhook URL* credential with yours.
+4. Replace the _Browser-Use API Key_ credential and _Slack webhook URL_ credential with yours.
---
## How the workflow works
### 1. `Form Trigger` – collect the competitor’s name
+
A public n8n form with a single required field. When a user submits, the workflow fires instantly.
### 2. `HTTP Request – Browser Use Run Task`
+
We POST to `/api/v1/run-task` with the following body:
```json title="run-task payload"
@@ -64,35 +66,47 @@ We POST to `/api/v1/run-task` with the following body:
"task": "Do exhaustive research on {{ $json[\"Competitor Name\"] }} and extract all pricing information, job postings, new features and announcements",
"save_browser_data": true,
"structured_output_json": {
- "pricing": {"plans": ["string"], "prices": ["string"], "features": ["string"]},
- "jobs": {"titles": ["string"], "departments": ["string"], "locations": ["string"]},
- "new_features": {"titles": ["string"], "description": ["string"]},
- "announcements": {"titles": ["string"], "description": ["string"]}
+ "pricing": {
+ "plans": ["string"],
+ "prices": ["string"],
+ "features": ["string"]
+ },
+ "jobs": {
+ "titles": ["string"],
+ "departments": ["string"],
+ "locations": ["string"]
+ },
+ "new_features": { "titles": ["string"], "description": ["string"] },
+ "announcements": { "titles": ["string"], "description": ["string"] }
},
- "metadata": {"source": "n8n-competitor-demo"}
+ "metadata": { "source": "n8n-competitor-demo" }
}
```
Important bits:
• `structured_output_json` tells the agent which keys to return – no post-processing required.
-• We tag the task with `metadata.source` so the webhook can filter only *our* jobs.
+• We tag the task with `metadata.source` so the webhook can filter only _our_ jobs.
### 3. `Webhook` + `IF` – wait for task completion
-Browser Use sends a webhook when anything happens to a task (see our [Webhooks guide](/cloud/webhooks) for setup details). We expose an n8n Webhook node at `/get-research-data` and let the agent call it.
+
+Browser Use sends a webhook when anything happens to a task (see our [Webhooks guide](/cloud/v1/webhooks) for setup details). We expose an n8n Webhook node at `/get-research-data` and let the agent call it.
We only proceed when **both** conditions are true:
-* `payload.status == "finished"`
-* `payload.metadata.source == "n8n-competitor-demo"`
+- `payload.status == "finished"`
+- `payload.metadata.source == "n8n-competitor-demo"`
### 4. `Get Task Details`
+
The webhook body includes the `session_id`. We fetch the full task record so we get the `output` field containing the structured JSON from step 2.
### 5. `Code – Generate Slack message`
+
A short JS snippet turns the JSON into a nicely-formatted Slack block with emojis and bullet points. Feel free to tweak the formatting.
### 6. `HTTP Request – Send to Slack`
+
Finally we POST the message to your incoming webhook and celebrate 🎉.
---
@@ -101,15 +115,15 @@ Finally we POST the message to your incoming webhook and celebrate 🎉.
This workflow is just the starting point – Browser Use + n8n gives you endless possibilities. Here are some ideas:
-| Want to... | How to do it |
-| ---- | ------ |
-| **Extract different data** | Edit `structured_output_json` to specify exactly what fields you need (pricing, reviews, contact info, etc.) and adjust the JS formatter. |
-| **Send to Teams/Email/Notion** | Swap the last Slack node for Teams, Gmail, or any of n8n's 400+ connectors. |
-| **Run automatically** | Replace the Form trigger with a Cron trigger for daily/weekly competitor monitoring. |
-| **Monitor multiple competitors** | Use a Google Sheets trigger with a list of companies and loop through them. |
-| **Add AI analysis** | Pipe the extracted data through OpenAI/Claude to generate insights and summaries. |
-| **Create alerts** | Set up conditional logic to only notify when competitors announce new features or price changes. |
-| **Build a dashboard** | Send data to Airtable, Notion, or Google Sheets to build a real-time competitor intelligence dashboard. |
+| Want to... | How to do it |
+| -------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
+| **Extract different data** | Edit `structured_output_json` to specify exactly what fields you need (pricing, reviews, contact info, etc.) and adjust the JS formatter. |
+| **Send to Teams/Email/Notion** | Swap the last Slack node for Teams, Gmail, or any of n8n's 400+ connectors. |
+| **Run automatically** | Replace the Form trigger with a Cron trigger for daily/weekly competitor monitoring. |
+| **Monitor multiple competitors** | Use a Google Sheets trigger with a list of companies and loop through them. |
+| **Add AI analysis** | Pipe the extracted data through OpenAI/Claude to generate insights and summaries. |
+| **Create alerts** | Set up conditional logic to only notify when competitors announce new features or price changes. |
+| **Build a dashboard** | Send data to Airtable, Notion, or Google Sheets to build a real-time competitor intelligence dashboard. |
The beauty of Browser Use is that it handles the complex web browsing while you focus on building the perfect workflow for your needs.
@@ -374,5 +388,6 @@ The beauty of Browser Use is that it handles the complex web browsing while you
Copy everything between the braces, import into n8n and you're good to go.
<Note>
-Having trouble? Ping us in the #integrations channel on [Discord](https://discord.gg/fT6Re4KN) – we’re happy to help.
+ Having trouble? Ping us in the #integrations channel on
+ [Discord](https://discord.gg/fT6Re4KN) – we’re happy to help.
</Note>
diff --git a/docs/cloud/pricing.mdx b/docs/cloud/v1/pricing.mdx
similarity index 87%
rename from docs/cloud/pricing.mdx
rename to docs/cloud/v1/pricing.mdx
index afbb56481..85eff0116 100644
--- a/docs/cloud/pricing.mdx
+++ b/docs/cloud/v1/pricing.mdx
@@ -35,11 +35,5 @@ The following table shows the total cost per step for each available LLM model:
For example, using GPT-4.1 for a 10 step task:
- Task initialization: $0.01
-- 10 steps × $0.03 per step = $0.30
+- 10 steps x \$0.03 per step = \$0.30
- **Total cost: $0.31**
-
-<Note>
- You need an active subscription and an API key from
- [cloud.browser-use.com/billing](https://cloud.browser-use.com/billing) to get
- started.
-</Note>
diff --git a/docs/cloud/quickstart.mdx b/docs/cloud/v1/quickstart.mdx
similarity index 88%
rename from docs/cloud/quickstart.mdx
rename to docs/cloud/v1/quickstart.mdx
index e1cf89506..0027968a6 100644
--- a/docs/cloud/quickstart.mdx
+++ b/docs/cloud/v1/quickstart.mdx
@@ -18,12 +18,12 @@ icon: "cloud"
<Note>
You need an active subscription and an API key from
[cloud.browser-use.com/billing](https://cloud.browser-use.com/billing). For
- detailed pricing information, see our [pricing page](/cloud/pricing).
+ detailed pricing information, see our [pricing page](/cloud/v1/pricing).
</Note>
## Creating Your First Agent
-To understand how the API works visit the [Run Task](/api-reference/run-task?playground=open) page.
+To understand how the API works visit the [Run Task](/api-reference/api-v1/run-task?playground=open) page.
```bash
curl -X POST https://api.browser-use.com/api/v1/run-task \
@@ -41,4 +41,4 @@ curl -X POST https://api.browser-use.com/api/v1/run-task \
Playground](https://cloud.browser-use.com/playground).
</Note>
-For the full implementation guide see the [Implementation](/cloud/implementation) page.
+For the full implementation guide see the [Implementation](/cloud/v1/implementation) page.
diff --git a/docs/cloud/search.mdx b/docs/cloud/v1/search.mdx
similarity index 90%
rename from docs/cloud/search.mdx
rename to docs/cloud/v1/search.mdx
index 6f733d801..297861480 100644
--- a/docs/cloud/search.mdx
+++ b/docs/cloud/v1/search.mdx
@@ -1,11 +1,12 @@
---
-title: "Search API Quickstart"
+title: "Search API"
description: "Get started with Browser Use's search endpoints to extract content from websites"
icon: "magnifying-glass"
---
<Warning>
-**🧪 BETA - This API is in beta - it may change and might not be available at all times.**
+ **🧪 BETA - This API is in beta - it may change and might not be available at
+ all times.**
</Warning>
## Why Browser Use Over Traditional Search?
@@ -14,7 +15,7 @@ icon: "magnifying-glass"
- 🔍 **Deep navigation**: Clicks through menus, forms, and multiple pages to find buried content
- 🚀 **Always current**: Live prices, breaking news, real-time analytics - not cached results
-- 🎯 **No stale data**: See exactly what's on the page right now
+- 🎯 **No stale data**: See exactly what's on the page right now
- 🌐 **Dynamic content**: Handles JavaScript, forms, and interactive elements
- 🏠 **No surface limitations**: Gets data from pages that require navigation or interaction
@@ -27,6 +28,7 @@ The Search API allows you to quickly extract relevant content from websites usin
💡 **Complete working examples** are available in the [examples/search](https://github.com/browser-use/browser-use/tree/main/examples/search) folder.
### Simple Search
+
Search Google and extract content from multiple top results:
```python
@@ -39,12 +41,12 @@ async def simple_search():
"max_websites": 5,
"depth": 2
}
-
+
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
-
+
async with aiohttp.ClientSession() as session:
async with session.post(
"https://api.browser-use.com/api/v1/simple-search",
@@ -58,21 +60,22 @@ asyncio.run(simple_search())
```
### Search URL
+
Extract content from a specific URL:
```python
async def search_url():
payload = {
"url": "https://browser-use.com/#pricing",
- "query": "Find pricing information for Browser Use",
+ "query": "Find pricing information for Browser Use",
"depth": 2
}
-
+
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
-
+
async with aiohttp.ClientSession() as session:
async with session.post(
"https://api.browser-use.com/api/v1/search-url",
@@ -90,7 +93,7 @@ asyncio.run(search_url())
- **query**: Search query or content to extract
- **depth**: How deep to navigate within each website (2-5, default: 2)
- `depth=2`: Checks main page + 1 click deeper
- - `depth=3`: Checks main page + 2 clicks deeper
+ - `depth=3`: Checks main page + 2 clicks deeper
- `depth=5`: Thoroughly explores multiple navigation levels
- **max_websites**: Number of websites to process (simple-search only, default: 5)
- **url**: Target URL to extract from (search-url only)
@@ -98,11 +101,13 @@ asyncio.run(search_url())
## Pricing
### Simple Search
+
**Cost per request**: `1 cent × depth × max_websites`
Example: depth=2, max_websites=3 = 6 cents per request
-### Search URL
+### Search URL
+
**Cost per request**: `1 cent × depth`
-Example: depth=2 = 2 cents per request
+Example: depth=2 = 2 cents per request
diff --git a/docs/cloud/webhooks.mdx b/docs/cloud/v1/webhooks.mdx
similarity index 100%
rename from docs/cloud/webhooks.mdx
rename to docs/cloud/v1/webhooks.mdx
diff --git a/docs/cloud/v2/node-quickstart.mdx b/docs/cloud/v2/node-quickstart.mdx
new file mode 100644
index 000000000..7d67e3aa1
--- /dev/null
+++ b/docs/cloud/v2/node-quickstart.mdx
@@ -0,0 +1,142 @@
+---
+title: "Node.js"
+description: "Get started with Browser Use Cloud API using Node.js"
+icon: "node-js"
+---
+
+<img src="/images/cloud-banner-js.png" alt="Browser Use Node.js" width="full" />
+
+> The repository is available on [GitHub](https://github.com/browser-use/browser-use-node)
+
+<CodeGroup>
+
+```sh npm
+npm install browser-use-sdk
+```
+
+```sh pnpm
+pnpm add browser-use-sdk
+```
+
+```sh yarn
+yarn add browser-use-sdk
+```
+
+```sh bun
+bun add browser-use-sdk
+```
+
+</CodeGroup>
+
+☝️ Get your API Key at [Browser Use Cloud](https://cloud.browser-use.com/billing)
+
+```ts
+import BrowserUse from "browser-use-sdk";
+
+const client = new BrowserUse({
+ apiKey: "bu_...",
+});
+
+const result = await client.tasks.run({
+ task: "Search for the top 10 Hacker News posts and return the title and url.",
+});
+
+console.log(result.doneOutput);
+```
+
+> The full API of this library can be found in [api.md](https://github.com/browser-use/browser-use-node/blob/main/api.md).
+
+### Structured Output with Zod
+
+```ts
+import z from "zod";
+
+const TaskOutput = z.object({
+ posts: z.array(
+ z.object({
+ title: z.string(),
+ url: z.string(),
+ })
+ ),
+});
+
+const result = await client.tasks.run({
+ task: "Search for the top 10 Hacker News posts and return the title and url.",
+});
+
+for (const post of result.parsedOutput.posts) {
+ console.log(`${post.title} - ${post.url}`);
+}
+```
+
+### Streaming Agent Updates
+
+```ts
+const task = await browseruse.tasks.create({
+ task: "Search for the top 10 Hacker News posts and return the title and url.",
+ schema: TaskOutput,
+});
+
+const stream = browseruse.tasks.stream({
+ taskId: task.id,
+ schema: TaskOutput,
+});
+
+for await (const msg of stream) {
+ switch (msg.status) {
+ case "started":
+ case "paused":
+ case "stopped":
+ console.log(`running: ${msg}`);
+ break;
+
+ case "finished":
+ console.log(`done:`);
+
+ for (const post of msg.parsedOutput.posts) {
+ console.log(`${post.title} - ${post.url}`);
+ }
+ break;
+ }
+}
+```
+
+## Webhook Verification
+
+> We encourage you to use the SDK functions that verify and parse webhook events.
+
+```ts
+import {
+ verifyWebhookEventSignature,
+ type WebhookAgentTaskStatusUpdatePayload,
+} from "browser-use-sdk/lib/webhooks";
+
+export async function POST(req: Request) {
+ const signature = req.headers["x-browser-use-signature"] as string;
+ const timestamp = req.headers["x-browser-use-timestamp"] as string;
+
+ const event = await verifyWebhookEventSignature(
+ {
+ body,
+ signature,
+ timestamp,
+ },
+ {
+ secret: SECRET_KEY,
+ }
+ );
+
+ if (!event.ok) {
+ return;
+ }
+
+ switch (event.event.type) {
+ case "agent.task.status_update":
+ break;
+ case "test":
+ break;
+ default:
+ break;
+ }
+}
+```
diff --git a/docs/cloud/v2/python-quickstart.mdx b/docs/cloud/v2/python-quickstart.mdx
new file mode 100644
index 000000000..a23636235
--- /dev/null
+++ b/docs/cloud/v2/python-quickstart.mdx
@@ -0,0 +1,130 @@
+---
+title: "Python"
+description: "Get started with Browser Use Cloud API using Python"
+icon: "python"
+---
+
+<img
+ src="/images/cloud-banner-python.png"
+ alt="Browser Use Python"
+ width="full"
+/>
+
+> The repository is available on [GitHub](https://github.com/browser-use/browser-use-python).
+
+```sh
+pip install browser-use-sdk
+```
+
+☝️ Get your API Key at [Browser Use Cloud](https://cloud.browser-use.com/billing)
+
+```python
+from browser_use_sdk import BrowserUse
+
+client = BrowserUse(api_key="bu_...")
+
+result = client.tasks.run(
+ task="Search for the top 10 Hacker News posts and return the title and url."
+)
+
+result.done_output
+```
+
+> The full API reference can be found in [api.md](https://github.com/browser-use/browser-use-python/blob/main/api.md).
+
+## Async usage
+
+Simply import `AsyncBrowserUse` instead of `BrowserUse` and use `await` with each API call:
+
+```python
+import os
+import asyncio
+from browser_use_sdk import AsyncBrowserUse
+
+client = AsyncBrowserUse(
+ api_key=os.environ.get("BROWSER_USE_API_KEY"), # This is the default and can be omitted
+)
+
+
+async def main() -> None:
+ task = await client.tasks.run(
+ task="Search for the top 10 Hacker News posts and return the title and url.",
+ )
+ print(task.done_output)
+
+
+asyncio.run(main())
+```
+
+Functionality between the synchronous and asynchronous clients is otherwise identical.
+
+## Structured Output with Pydantic
+
+Browser Use Python SDK provides first class support for Pydantic models.
+
+```py
+class HackerNewsPost(BaseModel):
+ title: str
+ url: str
+
+class SearchResult(BaseModel):
+ posts: List[HackerNewsPost]
+
+async def main() -> None:
+ structured_result = await client.tasks.run(
+ task="""
+ Find top 10 Hacker News articles and return the title and url.
+ """,
+ structured_output_json=SearchResult,
+ )
+
+ if structured_result.parsed_output is not None:
+ print("Top HackerNews Posts:")
+ for post in structured_result.parsed_output.posts:
+ print(f" - {post.title} - {post.url}")
+
+asyncio.run(main())
+```
+
+## Streaming Updates with Async Iterators
+
+```py
+class HackerNewsPost(BaseModel):
+ title: str
+ url: str
+
+class SearchResult(BaseModel):
+ posts: List[HackerNewsPost]
+
+
+async def main() -> None:
+ structured_task = await client.tasks.create(
+ task="""
+ Find top 10 Hacker News articles and return the title and url.
+ """,
+ structured_output_json=SearchResult,
+ )
+
+ async for update in client.tasks.stream(structured_task.id, structured_output_json=SearchResult):
+ if len(update.steps) > 0:
+ last_step = update.steps[-1]
+ print(f"{update.status}: {last_step.url} ({last_step.next_goal})")
+ else:
+ print(f"{update.status}")
+
+ if update.status == "finished":
+ if update.parsed_output is None:
+ print("No output...")
+ else:
+ print("Top HackerNews Posts:")
+ for post in update.parsed_output.posts:
+ print(f" - {post.title} - {post.url}")
+
+ break
+
+asyncio.run(main())
+```
+
+## Advanced
+
+For more advanced usage of the SDK and contributions to the SDK, see [Github repository](https://github.com/browser-use/browser-use-python).
diff --git a/docs/cloud/v2/quickstart.mdx b/docs/cloud/v2/quickstart.mdx
new file mode 100644
index 000000000..74a990ff2
--- /dev/null
+++ b/docs/cloud/v2/quickstart.mdx
@@ -0,0 +1,48 @@
+---
+title: "Quickstart"
+description: "Skip the setup with Browser Use Cloud"
+icon: "cloud"
+---
+
+<img
+ className="block dark:hidden rounded-2xl"
+ src="/images/cloud-banner.png"
+ alt="Browser Use Cloud Banner"
+/>
+<img
+ className="hidden dark:block rounded-2xl"
+ src="/images/cloud-banner-dark.png"
+ alt="Browser Use Cloud Banner"
+/>
+
+## Get Started
+
+☝️ Get your API Key at [Browser Use Cloud](https://cloud.browser-use.com) then choose your language.
+
+<CardGroup cols={2}>
+ <Card
+ title="Python SDK"
+ icon="python"
+ href="/cloud/v2/python-quickstart"
+
+>
+
+ Browser Use NPC Mode SDK 🤖
+
+ </Card>
+ <Card
+ title="Node.js SDK"
+ icon="node-js"
+ href="/cloud/v2/node-quickstart"
+
+>
+
+ Browser Use Wizard Mode SDK 🧙‍♂️
+
+ </Card>
+
+</CardGroup>
+
+{/* <br /> */}
+
+> To play around with the API, you can use the [Browser Use Cloud Playground](https://cloud.browser-use.com/playground).
diff --git a/docs/customize/browser-settings.mdx b/docs/customize/browser-settings.mdx
index d09bed33f..dbec43905 100644
--- a/docs/customize/browser-settings.mdx
+++ b/docs/customize/browser-settings.mdx
@@ -22,10 +22,13 @@ agent = Agent('fill out the form on this page', browser_session=browser_session)
```
<Note>
- The new `BrowserSession` & `BrowserProfile` accept all the same arguments that Playwright's [`launch_persistent_context(...)`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context) takes, giving you full control over browser settings at launch. (see below for the full list)
+ The new `BrowserSession` & `BrowserProfile` accept all the same arguments that
+ Playwright's
+ [`launch_persistent_context(...)`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context)
+ takes, giving you full control over browser settings at launch. (see below for
+ the full list)
</Note>
-
---
## `BrowserSession`
@@ -65,8 +68,9 @@ PID of a running chromium-based browser process to connect to on localhost. See
<Note>
For web scraping tasks on sites that restrict automated access, we recommend
- using [our cloud](https://browser-use.com) or an external browser provider for better reliability.
- See the [Connect to your Browser](real-browser) guide for detailed connection instructions.
+ using [our cloud](https://browser-use.com) or an external browser provider for
+ better reliability. See the [Connect to your Browser](/customize/real-browser)
+ guide for detailed connection instructions.
</Note>
### Session-Specific Parameters
@@ -79,13 +83,10 @@ browser_profile: BrowserProfile = BrowserProfile()
Optional `BrowserProfile` template containing default config to use for the `BrowserSession`. (see below for more info)
-
-
-
#### `**kwargs`
-`BrowserSession` can also accept *all* of the parameters [below](#browserprofile).
-(the parameters *above* this point are specific to `BrowserSession` and cannot be stored in a `BrowserProfile` template)
+`BrowserSession` can also accept _all_ of the parameters [below](#browserprofile).
+(the parameters _above_ this point are specific to `BrowserSession` and cannot be stored in a `BrowserProfile` template)
Extra `**kwargs` passed to `BrowserSession(...)` act as session-specific overrides to the `BrowserProfile(...)` template.
@@ -111,7 +112,6 @@ await asyncio.gather(agent1.run(), agent2.run())
---
-
## `BrowserProfile`
A `BrowserProfile` is a 📋 config template for a 🎭 `BrowserSession(...)`.
@@ -124,7 +124,9 @@ When you find yourself storing or re-using many browser configs, you can upgrade
- config = {key: val, key: val, ...}
- BrowserSession(**config)
```
+
To this instead:
+
```diff
+ config = BrowserProfile(key=val, key=val, ...)
+ BrowserSession(browser_profile=config)
@@ -145,12 +147,12 @@ session = BrowserSession(headless=True, storage_state='auth.json', viewport={...
<Tip>
`BrowserProfiles`s are designed to easily be given 🆔 `uuid`s and put in a database + made editable by users.
-`BrowserSession`s get their own 🆔 `uuid`s and be linked by 🖇 foreign key to whatever `BrowserProfiles` they use.
+`BrowserSession`s get their own 🆔 `uuid`s and be linked by 🖇 foreign key to whatever `BrowserProfiles` they use.
This cleanly separates the per-connection rows from the bulky re-usable config and avoids wasting space in your db.
This is useful because a user may only have 2 or 3 profiles, but they could have 100k+ sessions within a few months.
-</Tip>
+</Tip>
`BrowserProfile` and `BrowserSession` can both take any of the:
@@ -195,6 +197,7 @@ If `True` it wont close the browser after the first `agent.run()` ends. Useful f
```python
stealth: bool = False
```
+
Set to `True` to use [`patchright`](https://github.com/Kaliiiiiiiiii-Vinyzu/patchright) to avoid bot-blocking. (Might cause issues with some sites, requires manual testing.)
<a name="restrict-urls"></a>
@@ -207,13 +210,14 @@ allowed_domains: list[str] | None = None
List of allowed domains for navigation. If None, all domains are allowed.
Example: `['google.com', '*.wikipedia.org']` - Here the agent will only be able to access `google.com` exactly and `wikipedia.org` + `*.wikipedia.org`.
-
+
Glob patterns are supported:
+
- `['example.com']` ✅ will match only `https://example.com/*` exactly, subdomains will not be allowed.
It's always the most secure to list all the domains you want to give the access to explicitly w/ schemes e.g.
`['https://google.com', 'http*://www.google.com', 'https://myaccount.google.com', 'https://mail.google.com', 'https://docs.google.com']`
-- `['*.example.com']` ⚠️ **CAUTION** this will match `https://example.com` and *all* its subdomains.
- Make sure *all* the subdomains are safe for the agent! `abc.example.com`, `def.example.com`, ..., `useruploads.example.com`, `admin.example.com`
+- `['*.example.com']` ⚠️ **CAUTION** this will match `https://example.com` and _all_ its subdomains.
+ Make sure _all_ the subdomains are safe for the agent! `abc.example.com`, `def.example.com`, ..., `useruploads.example.com`, `admin.example.com`
#### `disable_security`
@@ -222,8 +226,8 @@ disable_security: bool = False
```
<Warning>
-⚠️ Setting this to `True` is NOT RECOMMENDED.
-It completely disables all basic browser security features.
+ ⚠️ Setting this to `True` is NOT RECOMMENDED. It completely disables all basic
+ browser security features.
</Warning>
This option is for debugging and interacting across cross-origin iFrames when there are no cookies or sensitive data in use.
@@ -236,12 +240,11 @@ deterministic_rendering: bool = False
```
<Warning>
-⚠️ Setting this to `True` is NOT RECOMMENDED.
-It can be glitchy & slow, and it increases chances of getting blocked by anti-bot systems. It's mostly useful for QA applications.
+ ⚠️ Setting this to `True` is NOT RECOMMENDED. It can be glitchy & slow, and it
+ increases chances of getting blocked by anti-bot systems. It's mostly useful
+ for QA applications.
</Warning>
-
-
It's a shortcut for adding these launch args:
- `--deterministic-mode`
@@ -251,7 +254,7 @@ It's a shortcut for adding these launch args:
- `--force-device-scale-factor=2`
- `--enable-webgl`
-With these options fonts will look slightly worse than macOS and slightly than Windows, but rendering will be more consistent between OSs and runs. The cost is performance and stability. Software rendering is slower, easier to fingerprint as a bot, and sometimes glitchy. You likely *don't need this option* unless you're trying to do screenshot diffing.
+With these options fonts will look slightly worse than macOS and slightly than Windows, but rendering will be more consistent between OSs and runs. The cost is performance and stability. Software rendering is slower, easier to fingerprint as a bot, and sometimes glitchy. You likely _don't need this option_ unless you're trying to do screenshot diffing.
#### `highlight_elements`
@@ -268,6 +271,7 @@ viewport_expansion: int = 500
```
Viewport expansion in pixels. With this you can control how much of the page is included in the context of the LLM:
+
- `-1`: All elements from the entire page will be included, regardless of visibility (highest token usage but most complete).
- `0`: Only elements which are currently visible in the viewport will be included.
- `500` (default): Elements in the viewport plus an additional 500 pixels in each direction will be included, providing a balance between context and token usage.
@@ -330,8 +334,8 @@ The library will automatically save a new `storage_state.json` next to any `cook
`storage_state.json`: `{"cookies": [{cookie}, {cookie}, {cookie}], "origins": {... optional localstorage state ...}}`
Or run `playwright open https://example.com/ --save-storage=storage_state.json` and log into any sites you need to generate a fresh storage state file.
-</Warning>
+</Warning>
#### `profile_directory`
@@ -366,14 +370,13 @@ trace_path: str | None = None
Directory path for saving Agent trace files. Files are automatically named as `{trace_path}/{context_id}.zip`.
-
---
-<a name="playwright-parameters"></a><a name="playwright"></a>
+<a name="playwright-parameters"></a>
+<a name="playwright"></a>
### Playwright Launch Options
-
All the parameters below are standard playwright parameters and can be passed to both `BrowserSession` and `BrowserProfile`.
They are defined in `browser_use/browser/profile.py`. See here for the [official Playwright documentation](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context) for all of these options.
@@ -383,7 +386,7 @@ They are defined in `browser_use/browser/profile.py`. See here for the [official
headless: bool | None = None
```
-Runs the browser without a visible UI. If None, auto-detects based on display availability. If you set `headless=False` on a server with no monitor attached, the browser will fail to launch (use `xvfb` + vnc to give a headless server a virtual display you can remote control).
+Runs the browser without a visible UI. If None, auto-detects based on display availability. If you set `headless=False` on a server with no monitor attached, the browser will fail to launch (use `xvfb` + vnc to give a headless server a virtual display you can remote control).
`headless=False` is recommended for maximum stealth and is required for human-in-the-loop workflows.
@@ -424,9 +427,8 @@ If you see errors like `Failed to parse Extensions` or similar and failures when
```python
args: list[str] = []
```
-Additional command-line arguments to pass to the browser. See here for the [full list of available chrome launch options](https://peter.sh/experiments/chromium-command-line-switches/).
-
+Additional command-line arguments to pass to the browser. See here for the [full list of available chrome launch options](https://peter.sh/experiments/chromium-command-line-switches/).
#### `ignore_default_args`
@@ -434,7 +436,7 @@ Additional command-line arguments to pass to the browser. See here for the [full
ignore_default_args: list[str] | bool = ['--enable-automation', '--disable-extensions']
```
-List of default CLI args to stop playwright from including when launching chrome. Set it to `True` to disable *all* default options (not recommended).
+List of default CLI args to stop playwright from including when launching chrome. Set it to `True` to disable _all_ default options (not recommended).
#### `env`
@@ -540,7 +542,6 @@ default_navigation_timeout: float | None = None
Default timeout for page navigation in milliseconds (e.g. `30000` if you want 30s).
-
### Playwright Viewport Options
Configure browser window size, viewport, and display properties:
@@ -617,8 +618,8 @@ no_viewport: bool | None = not headless
Disable fixed viewport. Content will resize with window.
-*Tip:* don't use this parameter, it's a playwright standard parameter but it's redundant and only serves to override the `viewport` setting above.
-A viewport is *always* used in headless mode regardless of this setting, and is *never* used in headful mode unless you pass `viewport={width, height}` explicitly.
+_Tip:_ don't use this parameter, it's a playwright standard parameter but it's redundant and only serves to override the `viewport` setting above.
+A viewport is _always_ used in headless mode regardless of this setting, and is _never_ used in headful mode unless you pass `viewport={width, height}` explicitly.
#### `device_scale_factor`
@@ -724,7 +725,8 @@ bypass_csp: bool = False
```
<Warning>
-Enabling this can increase security risk and makes the bot very easy to fingerprint. (Cloudflare, Datadome, etc. will block you)
+ Enabling this can increase security risk and makes the bot very easy to
+ fingerprint. (Cloudflare, Datadome, etc. will block you)
</Warning>
Toggles bypassing Content-Security-Policy. Enabling reduces some CSP-related errors that can arise from automation scripts injected into pages with strict policies that forbid inline scripts.
@@ -736,7 +738,7 @@ java_script_enabled: bool = True
```
<Warning>
-Not recommended, untested with Browser Use and likely breaks things.
+ Not recommended, untested with Browser Use and likely breaks things.
</Warning>
Whether or not to enable JavaScript in the context.
@@ -773,7 +775,6 @@ client_certificates: list[ClientCertificate] = []
Client certificates to be used with requests.
-
### Playwright Recording Options
Note: Browser Use also provides some of our own recording-related options not listed below (see above).
@@ -790,7 +791,9 @@ record_video_dir: str | Path | None = None
Directory to save `.webm` video recordings. [Playwright Docs: `record_video_dir`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context-option-record-video-dir)
<Note>
-This parameter also has an alias `save_recording_path` for backwards compatibility with past versions, but we recommend using the standard Playwright name `record_video_dir` going forward.
+ This parameter also has an alias `save_recording_path` for backwards
+ compatibility with past versions, but we recommend using the standard
+ Playwright name `record_video_dir` going forward.
</Note>
#### `record_video_size`
@@ -814,7 +817,9 @@ record_har_path: str | Path | None = None
Path to save `.har` network trace files. [Playwright Docs: `record_har_path`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context-option-record-har-path)
<Note>
-This parameter also has an alias `save_har_path` for backwards compatibility with past versions, but we recommend using the standard Playwright name `record_har_path` going forward.
+ This parameter also has an alias `save_har_path` for backwards compatibility
+ with past versions, but we recommend using the standard Playwright name
+ `record_har_path` going forward.
</Note>
#### `record_har_content`
@@ -871,7 +876,9 @@ traces_dir: str | Path | None = None
Directory to save all-in-one trace files. Files are automatically named as `{traces_dir}/{context_id}.zip`. [Playwright Docs: `traces_dir`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-persistent-context-option-traces-dir)
<Note>
-This parameter also has an alias `trace_path` for backwards compatibility with past versions, but we recommend using the standard Playwright name `traces_dir` going forward.
+ This parameter also has an alias `trace_path` for backwards compatibility with
+ past versions, but we recommend using the standard Playwright name
+ `traces_dir` going forward.
</Note>
#### `handle_sighup`
diff --git a/docs/docs.json b/docs/docs.json
index fd3dae402..606d27560 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -58,78 +58,61 @@
]
},
{
- "tab": "Cloud API",
- "groups": [
- {
- "group": "Get Started",
- "pages": ["cloud/quickstart", "cloud/search", "cloud/pricing"]
- },
- {
- "group": "Guides",
- "pages": [
- "cloud/implementation",
- "cloud/custom-sdk",
- "cloud/webhooks",
- "cloud/authentication",
- "cloud/n8n-browser-use-integration"
- ]
- },
- {
- "group": "Search API",
- "pages": ["api-reference/simple-search", "api-reference/search-url"]
- },
- {
- "group": "Tasks API",
- "pages": [
- "api-reference/run-task",
- "api-reference/stop-task",
- "api-reference/pause-task",
- "api-reference/resume-task",
- "api-reference/get-task",
- "api-reference/get-task-status",
- "api-reference/list-tasks",
- "api-reference/get-task-media",
- "api-reference/get-task-screenshots",
- "api-reference/get-task-output-file"
- ]
- },
+ "tab": "Cloud",
+ "versions": [
{
- "group": "Scheduled Tasks API",
- "pages": [
- "api-reference/list-scheduled-tasks",
- "api-reference/create-scheduled-task",
- "api-reference/get-scheduled-task",
- "api-reference/update-scheduled-task",
- "api-reference/delete-scheduled-task"
+ "version": "v2",
+ "groups": [
+ {
+ "group": "Get Started",
+ "pages": [
+ "cloud/v2/quickstart",
+ "cloud/v2/python-quickstart",
+ "cloud/v2/node-quickstart"
+ ]
+ },
+ {
+ "group": "Platform",
+ "pages": [
+ "cloud/v1/pricing",
+ "cloud/v1/n8n-browser-use-integration",
+ "cloud/v1/search"
+ ]
+ },
+ {
+ "group": "REST API reference",
+ "openapi": "https://app.stainless.com/api/spec/documented/browser-use/openapi.documented.yml"
+ }
]
},
{
- "group": "Browser Profiles API",
- "pages": [
- "api-reference/list-browser-profiles",
- "api-reference/create-browser-profile",
- "api-reference/get-browser-profile",
- "api-reference/update-browser-profile",
- "api-reference/delete-browser-profile"
+ "version": "v1",
+ "groups": [
+ {
+ "group": "Get Started",
+ "pages": [
+ "cloud/v1/quickstart",
+ "cloud/v1/search",
+ "cloud/v1/pricing"
+ ]
+ },
+ {
+ "group": "Guides",
+ "pages": [
+ "cloud/v1/implementation",
+ "cloud/v1/custom-sdk",
+ "cloud/v1/webhooks",
+ "cloud/v1/authentication",
+ "cloud/v1/n8n-browser-use-integration"
+ ]
+ },
+ {
+ "group": "REST API reference",
+ "openapi": "https://api.browser-use.com/api/v1/openapi.json"
+ }
]
- },
- {
- "group": "Files API",
- "pages": ["api-reference/upload-file-presigned-url"]
- },
- {
- "group": "User API",
- "pages": ["api-reference/check-balance", "api-reference/user"]
- },
- {
- "group": "Health Check API",
- "pages": ["api-reference/ping"]
}
]
- },
- {
- "tab": "Cloud API v2",
- "openapi": "https://app.stainless.com/api/spec/documented/browser-use/openapi.documented.yml"
}
]
},
diff --git a/docs/images/cloud-banner-js.png b/docs/images/cloud-banner-js.png
new file mode 100644
index 000000000..7d5f68d4d
Binary files /dev/null and b/docs/images/cloud-banner-js.png differ
diff --git a/docs/images/cloud-banner-python.png b/docs/images/cloud-banner-python.png
new file mode 100644
index 000000000..953a6b26c
Binary files /dev/null and b/docs/images/cloud-banner-python.png differ
diff --git a/docs/introduction.mdx b/docs/introduction.mdx
index 597f6d21b..806068cc3 100644
--- a/docs/introduction.mdx
+++ b/docs/introduction.mdx
@@ -22,10 +22,9 @@ icon: "book-open"
<Card
title="Cloud API"
icon="cloud"
- href="/cloud/quickstart"
+ href="/cloud/v2/quickstart"
color="#FE750E"
>
Skip the setup and start automating with Browser Use Cloud
</Card>
-
</CardGroup>
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index 5ce019c7f..a9a692f62 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -5,7 +5,7 @@ icon: "rocket"
---
<Info>
- You can skip this steps by using [Browser Use Cloud](/cloud/quickstart)
+ You can skip this steps by using [Browser Use Cloud](/cloud/v2/quickstart)
</Info>
## Prepare the environment
@@ -32,7 +32,7 @@ Install the dependencies:
uv pip install browser-use
```
-Then install playwright (or manually install the chromium browser):
+Then install Chromium from [source](https://www.chromium.org/getting-involved/download-chromium/) or run the command below (this does not install Playwright only Chromium and dependencies).
```bash
uvx playwright install chromium --with-deps