Самый быстрый API браузерного агента из всех, что мы тестировали

ИИ-агент, который работает в вебе за вас

Отправьте задачу и URL. Настоящий браузер Chrome кликает, вводит текст, заполняет формы, входит в аккаунты и возвращает ответ плюс структурированный JSON по вашей схеме.

9.1s
медианная задача, от начала до конца
$0.006
за шаг в быстром режиме, без платы за запуск
JSON
вывод по вашей схеме
5.4×
быстрее ведущего браузерного агента

Один запрос на входе, JSON на выходе

Запрос
curl https://lovelyrouter.com/v1/browser/runs \
  -H "Authorization: Bearer $LOVELY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "goal": "Get the top 3 stories on the front page",
    "start_url": "https://news.ycombinator.com/",
    "output_schema": { "stories": [{ "title": "string", "url": "string", "points": "integer" }] }
  }'
Результат (GET /v1/browser/runs/{id}?wait=30)
{
  "id": "brun_8f3c…",
  "status": "succeeded",
  "steps": 1,
  "answer": "The top 3 stories are …",
  "data": {
    "stories": [
      { "title": "Bitwarden Dual License Model", "url": "https://community.bitwarden.com/…", "points": 95 },
      { "title": "Talorys – A self-hosted personal AI agent…", "url": "https://github.com/rociiu/talorys", "points": 57 },
      { "title": "REA Reverse – Engineer Anything", "url": "https://rea.tools/", "points": 498 }
    ]
  },
  "charge_usd": 0.006
}

Передайте это своему ИИ-агенту

Скопируйте этот промпт в Claude Code, Cursor, Codex или любой кодинг-агент. Он подскажет агенту, где документация и как использовать ваш API-ключ.

Use the Lovely Router browser agent API: a real browser that clicks, types, fills forms and logs in for a task, and returns an answer plus JSON in a schema I choose.

- Docs (read first): https://lovelyrouter.com/docs/browser-agent.md and https://lovelyrouter.com/docs/api/browser.md
- Start a run: POST https://lovelyrouter.com/v1/browser/runs with `{"goal": "...", "start_url": "https://...", "output_schema": {...}}`. Put every value the task needs in the goal. It returns 202 at once; poll the `poll` path (or stream `events`) until the run ends, then read `answer` and `data`.
- Billed per step (fast mode by default). Set `max_steps` to cap a run. For unattended runs send `"human": false`; by default the agent pauses before purchases, sending or deleting (`approve`).
- If you support MCP, you can instead connect the server https://lovelyrouter.com/mcp (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool.
- Auth: read my API key from the LOVELY_API_KEY environment variable and send it as `Authorization: Bearer $LOVELY_API_KEY`. Never print or commit the key. If it is not set, ask me to create one at https://lovelyrouter.com/app/keys.
- Billing is prepaid: every call is charged to my balance, so test with a small request before running anything large.
- Every docs page is plain Markdown; the full index is https://lovelyrouter.com/llms.txt.

My task: <describe the site and what the agent should do or extract>

Создан для настоящих сайтов

Watch it live

Stream each action, every finished step and the browser screen while the agent works, in the console or over the API.

Structured JSON output

Pass an output schema and get validated JSON in data, taken only from the pages the agent visited — including real link URLs.

Logins and 2FA

Write-only vault secrets, typed only on the sites you allow. TOTP seeds become 6-digit codes; save the session so later runs start signed in. The model never sees a value.

Участие человека

The agent can ask you a question, wait for your approval before a purchase, or hand you a Live View for a CAPTCHA.

Загрузка файлов

Upload your files once; the agent picks the right one for each upload field (your CV, not your tax return).

Checks before submitting

Before it clicks submit, the agent compares every field with your task and fixes wrong or pre-filled values.

Самый быстрый API браузерного агента из всех, что мы тестировали

В 5 раз быстрее и намного дешевле. Те же шесть публичных задач 2026-10-10, время замерено от стартового запроса до результата, с настройками по умолчанию. Другой агент — самый популярный браузерный агент с оплатой за шаг в Apify Store.

ЗадачаLovely RouterВедущий браузерный агентБыстрее на
Hacker News top story3.7s · $0.00622.5s · $0.0386.1×
Product page two clicks deep7.3s · $0.01863.7s · $0.0958.7×
Book price lookup8.9s · $0.00938.2s · $0.0384.3×
Wikipedia search and read9.9s · $0.01879.5s · $0.1148.0×
Log in, then read the page12.1s · $0.03352.7s · $0.1054.4×
3-step insurance quote form (17 fields)21.3s · $0.126199.6s · $0.9889.4×

Цены

Быстро
$0.006
за шаг браузера
Точный
$0.012
за шаг браузера

Точный режим также смотрит скриншоты, если не уверен, и может запускать код только для чтения, чтобы получать данные.

  • ✓ Без платы за запуск, без подписки
  • ✓ Модели ИИ включены — ключ LLM не нужен
  • ✓ Структурированный вывод JSON включён
  • ✓ Платите только за сделанные шаги
  • Каждый шаг включает 1 минуту; время сверх этого (например, ожидание вашего подтверждения) стоит $0.005/мин
  • Выберите любую нашу модель: её токены по обычной цене × 1,2
Пример задачиШагиБыстроТочный
Read a value from a page1–3$0.006–$0.018$0.012–$0.036
Search a site and read a result2–6$0.012–$0.036$0.024–$0.072
Log in and read account data4–8$0.024–$0.048$0.048–$0.096
Fill and submit a long multi-step form15–25$0.090–$0.150$0.180–$0.300

Справочник API

Те же API-ключи и баланс, что и в остальном Lovely Router. Базовый URL https://lovelyrouter.com

POST /v1/browser/runsStart a run (202). Returns the run with its id.
GET /v1/browser/runs/{id}/eventsLive events (Server-Sent Events): what the agent is doing, each step, the run's state and, with ?screen=1, the browser screen.
GET /v1/browser/runs/{id}?wait=30Status; long-polls up to 50 s until it changes. &trace=1 adds the steps.
POST /v1/browser/runs/{id}/replyAnswer a question, approve or deny, or finish a takeover.
POST /v1/browser/runs/{id}/takeoverTake the browser over in Live View.
POST /v1/browser/runs/{id}/stopStop a run; you pay for the steps taken.
GET /v1/browser/runs/{id}/screenshotThe browser screen now, or the latest one kept.
PUT /v1/browser/vault/{name}Store a write-only secret: {"value", "kind": "password|username|text|totp", "origins"}.
PUT /v1/browser/files/{name}Upload a file (raw body, up to 10 MB) the agent may attach.
GET /v1/browser/profilesSaved sessions (cookies + local storage).

Параметры запуска

goalWhat to do, in plain words, with every value the task needs (required).
start_urlThe first page to open (required).
output_schemaJSON Schema, or shorthand like {"title": "string", "items": [{"name": "string"}]}. The result comes back in data. Without a schema, data is filled only when the goal itself describes a format.
mode"fast" (default, $0.006/step) or "accurate" ($0.012/step): when unsure it also looks at a screenshot of the page, and it can run read-only code to read data. Higher success on hard sites and widgets.
max_stepsStep limit, 1–100 (default 50). You pay only for steps taken.
approvePause for your approval before submitting: "risky" (default: purchases, sending), "submit" (every form) or "none".
human_timeout_minutesHow long the agent waits for you (an answer, an approval, a CAPTCHA), 1–1440 minutes (default 30). The run ends as timed_out if nobody replies.
secretsNames of vault secrets the agent may type (PUT /v1/browser/vault/{name}). The model sees only names.
ephemeral_secretsPer-run secrets that are never stored: {"name": {"value", "kind", "origins"}}.
filesNames of uploaded files the agent may attach to upload fields, or "*".
profile / save_profileStart from saved cookies, or save them when the run ends, so later runs start logged in.
allowed_domainsHostnames the browser may visit, e.g. ["example.com", "*.example.com"].
webhookHTTPS URL notified when the run waits for you or finishes (signed with x-lovely-signature).
stream / screenstream: true returns the run's live events (Server-Sent Events) until it ends, instead of a 202; screen: true adds the browser screen.
model / max_model_usdOptional model from GET /v1/models (e.g. claude-sonnet-5.5) for the agent's thinking, writing and extraction. Its tokens are billed at the model's normal price × 1.2, on top of the step price. max_model_usd caps that spend.

Запуск завершается как succeeded, failed, timed_out или stopped и может быть приостановлен как waiting_for_human. Результат содержит answer (текст), data (JSON или null), steps и charge_usd.

FAQ

Попробуйте на своей задаче

Запустите в консоли, следите за каждым шагом, затем скопируйте вызов API.

Получить ключ