Web extraction APIs · Lovely Router

Read a web page

Read any public web page as clean Markdown: its title and text, without navigation or ads. For one page you already have the URL of.

$0.0009 / pageDetails →

Browser agent

Any website

Give it a goal and a start page; an AI agent drives a real browser to do it: navigate, fill forms, log in with saved secrets, ask you for codes, hand over for CAPTCHAs, wait for your approval before purchases, and return structured JSON in your schema. For tasks that need interaction; to just read a page, use Read a web page (web-fetch). $0.006 per step in fast mode, $0.012 in accurate mode (looks at screenshots when unsure, can run read-only code to read data). Each step includes 1 minute; time beyond that (e.g. waiting for your approval) costs $0.005/min. Full API: /v1/browser.

$0.006 / stepDetails →

Crawl a website to markdown

Web

Crawl a whole website (or a section of it) and return each page as clean, LLM-ready markdown. Good for RAG and documentation sites.

$0.01 / page + $0.01 / callDetails →

Screenshot a web page

Web

Full-page screenshot (PNG or PDF) of web pages; returns a link to the image.

$0.00275 / screenshotDetails →

Read text from an image (OCR)

Google Lens

Text in an image, read with Google Lens: the full text, or paragraphs, lines and words with positions; optional translation.

$0.0068 / image + $0.003 / callDetails →

Hand it to your AI agent

Copy this prompt into Claude Code, Cursor, Codex or any coding agent. It tells the agent where the docs are and how to use your API key.

Use the Lovely Router Web extraction data tools to get data for me. They return JSON and are billed per result.

- Docs (read first): https://lovelyrouter.com/docs/tools.md and https://lovelyrouter.com/docs/tools/run.md and https://lovelyrouter.com/docs/api/tools.md
- Tools for this:
  - `web-fetch`: Read a web page ($0.0009 / page)
  - `browser-agent`: Browser agent ($0.006 / step)
  - `website-crawl`: Crawl a website to markdown ($0.01 / page + $0.01 / call)
  - `website-screenshot`: Screenshot a web page ($0.00275 / screenshot)
  - `image-ocr`: Read text from an image (OCR) ($0.0068 / image + $0.003 / call)
- Run: POST https://lovelyrouter.com/v1/tools/<id>/run with `{"input": {...}, "max_results": N}`. A 200 has the finished run with `items`; a 202 means it is still running, so poll the `poll` path until `status` is `succeeded`, `failed`, `timed_out` or `stopped`.
- Each tool takes its own input fields: read them with GET https://lovelyrouter.com/v1/tools/<id> (public, no key needed) before the first run.
- 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 data you need and the output format>

Run one from code

How runs, polling and billing work →

curl https://lovelyrouter.com/v1/tools/web-fetch/run \
  -H "Authorization: Bearer $LOVELY_API_KEY" \
  -H "content-type: application/json" \
  -d '{"input":{"url":"https://en.wikipedia.org/wiki/Cloudflare"},"max_results":1}'

Each tool page lists its input fields and an example input. Agents can use every tool over MCP: MCP server

Frequently asked questions

Which tools are in this category?

5 tools: Read a web page, Browser agent, Crawl a website to markdown, Screenshot a web page, Read text from an image (OCR). Each returns JSON and has its own page with its input fields and price.

Is this a web extraction API?

Yes. If you searched for a web extraction API, a website to markdown API or a website screenshot API, this is it: Read any page, crawl a site to Markdown, take screenshots, find contacts, or let the browser agent do the clicking.

How are these tools priced?

Each tool has its own price per result, from $0.0009. You pay only for results delivered, from a prepaid balance with no subscription.

Can AI agents use these tools?

Yes. Connect Claude Code, Cursor or any MCP client to the Lovely Router MCP server and the agent picks the right tool with suggest_tools and runs it with run_tool.

Can I use the data any way I like?

You are responsible for using the data lawfully, including privacy law when results contain personal data. See the Acceptable Use Policy.

Acceptable Use Policy · Use cases · Pricing