Skip to main content

Documentation Index

Fetch the complete documentation index at: https://skyvern.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

A browser session is a persistent browser instance that stays alive between API calls. Use sessions to chain multiple tasks in the same browser without losing cookies, local storage, or login state. For conceptual background, see Browser Sessions.
Python uses snake_case (e.g., create_browser_session); TypeScript uses camelCase (e.g., createBrowserSession). Parameter tables show Python names. TypeScript names are the camelCase equivalents.
Spin up a new cloud browser session. 
session = await client.create_browser_session(timeout=60)
print(session.browser_session_id)  # pbs_abc123

​
Parameters

ParameterTypeRequiredDefaultDescription
timeoutintNo60Session timeout in minutes (5–1440). Timer starts after the session is ready.
proxy_locationProxyLocationNoNoneRoute browser traffic through a geographic proxy.
extensionslist[Extensions]NoNoneBrowser extensions to install. Options: "ad-blocker", "captcha-solver".
browser_typePersistentBrowserTypeNoNoneBrowser type. Options: "chrome", "msedge".
browser_profile_idstrNoNoneLoad a browser profile (cookies, localStorage) into this session. ID starts with bpf_.
request_optionsRequestOptionsNoPer-request configuration (see below).

​
Returns BrowserSessionResponse

FieldTypeDescription
browser_session_idstrUnique ID. Starts with pbs_.
statusstr | NoneCurrent session status.
browser_addressstr | NoneCDP address for connecting to the browser.
app_urlstr | NoneLink to the live browser view in the Cloud UI.
timeoutint | NoneConfigured timeout in minutes.
started_atdatetime | NoneWhen the session became ready.
created_atdatetimeWhen the session was requested.

​
Example: Chain multiple tasks in one session

session = await client.create_browser_session()

# Step 1: Log in
await client.run_task(
    prompt="Log in with username demo@example.com",
    url="https://app.example.com/login",
    browser_session_id=session.browser_session_id,
    wait_for_completion=True,
)

# Step 2: Extract data (same browser, already logged in)
result = await client.run_task(
    prompt="Go to the invoices page and extract all invoice numbers",
    browser_session_id=session.browser_session_id,
    wait_for_completion=True,
)
print(result.output)

# Clean up
await client.close_browser_session(session.browser_session_id)

​
Request options

Override timeout, retries, or headers for this call by passing request_options (Python) or a second options argument (TypeScript). 
from skyvern.client.core import RequestOptions

request_options=RequestOptions(
    timeout_in_seconds=120,
    max_retries=3,
    additional_headers={"x-custom-header": "value"},
)
Option (Python)Option (TypeScript)TypeDescription
timeout_in_secondstimeoutInSecondsint / numberHTTP timeout in seconds.
max_retriesmaxRetriesint / numberRetry count.
additional_headersheadersdict / Record<string, string>Extra headers.
additional_query_parameters-dictExtra query parameters.
additional_body_parameters-dictExtra body parameters.
-abortSignalAbortSignalSignal to cancel the request.
-apiKeystringOverride API key.