Browserbase

Fetch a URL and return its content, status code, and headers without starting a browser session. Returns markdown for LLM-friendly reading, or structured JSON against a schema you provide.

Search the web and return structured results with titles and URLs. Pass a result URL to fetch_page to read the page itself.

Start an autonomous browser agent on a plain-English task, such as finding a pricing page and returning the cheapest plan. Returns a run ID immediately; poll get_agent_run for the result.

Get an agent run by ID: its status, result summary, steps taken, and the failure cause if it did not complete.

List agent runs, newest first. Filter by status, agent, or a creation-time window.

Get the step-by-step message stream for an agent run: what the agent saw, decided, and did. Use to debug a run that failed or returned an unexpected result.

Stop a running agent before it finishes, ending its browser session. Use to cut off a run that is looping or heading somewhere unintended.

Create a reusable agent: a name plus a standing system prompt and result schema that every run started with it inherits. Use when the same browsing job runs repeatedly and should return the same shape each time.

Get a reusable agent by ID, including its system prompt and result schema.

List reusable agents. Call this to find an agent to pass to run_agent.

Update a reusable agent’s name, system prompt, or result schema. Only the fields provided change.

Delete a reusable agent permanently. Runs already started with it are unaffected.

Start a cloud browser session and return the connection URL an external automation drives. Sessions consume browser minutes until they end, so release them when finished.

List browser sessions, filtered by status or by the metadata set when the session was created. Use the running status to find sessions still consuming browser minutes.

Get one browser session by ID: its status, region, timestamps, and proxy bytes used.

Get the browser’s command and event log for a session, to debug what an automation or agent run actually did. Available once the session has ended.

Get live view and debugger URLs for a running session, so a person can watch or take over the browser. This is how to clear a login or CAPTCHA an automation cannot.

Release a running browser session so it stops consuming browser minutes and frees a concurrency slot.

Create a context that persists cookies and local storage across browser sessions, so a later session resumes an existing login instead of signing in again.

Get a browser context by ID, including which project owns it and when it was created.

Delete a browser context permanently, discarding the cookies and local storage it held.

List the Browserbase projects your API key can reach, with each project’s concurrency limit and default session timeout.

Get one Browserbase project by ID, including its concurrency limit and default session timeout.

Get the browser minutes and proxy bytes a project has consumed this billing period. Use before starting sessions or agent runs to check remaining allowance.

Validate the Browserbase API key with a lightweight call. Returns success plus a short message.