Browser Use Tasks API

The Tasks API from Browser Use — 4 operation(s) for tasks.

Operations 6

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /tasks List AI agent tasks · List Tasks #
Ask an LLM
“Which browser agent tasks have I run, and which are still in progress?”
“Can I list only the tasks from one session or within a time window?”
Tell an agent
List the tasks in session {session_id} with status {status}.
Show my agent tasks created after {after} and before {before}.
POST /tasks Start a browser agent task · Create Task #
Ask an LLM
“How do I tell an AI agent to go do something in a browser for me?”
“Can I limit which domains the agent visits and how many steps it takes?”
Tell an agent
Create a task to {task}, starting at {start_url}.
Run {task} in existing session {session_id}.
GET /tasks/{task_id} Get a task's full details, steps and files · Get Task #
Ask an LLM
“How do I see every step the agent took on a task and the files it produced?”
“Where can I get the complete record of a task once it has finished?”
Tell an agent
Show the full details, steps and output files of task {task_id}.
Walk me through what the agent did step by step in task {task_id}.
PATCH /tasks/{task_id} Pause, resume or stop a task · Update Task #
Ask an LLM
“Can I pause an agent task partway through and resume it later?”
“How do I stop a task and also shut down the session it's running in?”
Tell an agent
Pause task {task_id}.
Apply action {action} to task {task_id}.
GET /tasks/{task_id}/status Poll a task's status, output and cost · Get Task Status #
Ask an LLM
“What's the most efficient way to poll whether my agent task is done?”
“How much has a task cost so far, and what did it return?”
Tell an agent
Poll task {task_id} until it finishes and give me its output.
Check only the status and cost of task {task_id}.
GET /tasks/{task_id}/logs Download a task's execution logs · Get Task Logs #
Ask an LLM
“Where can I download the detailed execution logs for a task?”
“How do I debug a failed agent task from its logs?”
Tell an agent
Get the log download link for task {task_id}.
Fetch the step-by-step execution logs of task {task_id} so I can debug it.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/browser-use:browser-use-tasks-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

browser-use-tasks-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Browser Use Public API v2 Tasks API
  summary: Browser Use API for running web agents (v2)
  version: 2.0.0
servers:
- url: https://api.browser-use.com/api/v2
  description: Production server
tags:


# --- truncated at 32 KB (35 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/browser-use/refs/heads/main/openapi/browser-use-tasks-api-openapi.yml