Use case, URL to markdown

URL to markdown API for your agent. One call per page.

Send a page URL. Read markdown text and page title back. Your agent picks the provider, and you pay per call.

Give this to your agent
set up looot for URL to markdown API - https://looot.ai/use-cases/url-to-markdown-api/skill.md

The short answer

The short answer

URL to markdown API for an agent: it sends a page URL to a catalog endpoint and reads markdown text, page title and description back. Several providers sell the call, so the agent tries the cheapest first. You pay per call, and a failed call costs nothing.

  • Markdown text
  • Page title
  • Description and language
  • Links on the page
  • Screenshot on some providers

The job

What the URL to markdown API gives your agent

Raw HTML is mostly menus, scripts and styling. An agent that reads it spends tokens on noise and can still miss the article. Turning the page into markdown first keeps the headings, lists, links and code, and drops the rest.

The providers differ in how they load the page. Steel opens it in a browser before it reads it, Linkup renders JavaScript when you ask, and Firecrawl can wait and run actions such as a click first. Context.dev turns a YouTube link into the video's transcript, and Jina reports how many tokens the text holds.

You give

a page URL

https://docs.example.com/getting-started

You get

  • Markdown text
  • Page title
  • Description and language
  • Links on the page
  • Screenshot on some providers

Providers, cheapest first

What actually differs between providers

Today the price runs from $0.0002 to $0.0050 across 5 endpoints. The dearest costs about 25 times the cheapest. Price is only one difference. Each entry below says what that endpoint takes or returns that the others do not.

Sample calls

The request and what comes back

Each run is one POST to /v1/runs with an endpoint id and an input. These are illustrative calls with generic values. The run's result holds the provider's own fields.

Request
{"endpointId":"jina-reader","input":{"url":"https://docs.example.com/getting-started"},"wait":30}
ResponseSample output
// POST /v1/runs, then read run.status and run.result
// result: returns the main content as markdown with the title, metadata, external links and the token count

The prompt

Copy one prompt, give it to your agent.

Edit the names and numbers, paste it, and the agent runs the job and shows the cost.

  • One run is one page.
  • 1 step across 5 providers.
  • Runs on demand, whenever you ask.
Prompt: URL to markdown API
Use looot to read https://docs.example.com/getting-started as markdown, keep the headings, lists and code blocks, drop the menus and footer, and give me the page title with the text. 1. Set up https://looot.ai/skill.md. 2. Search the catalog for each step and check its price before you call. 3. Run the cheapest endpoint that fits. 4. Show the results as a table and the total cost.

Give this to your agent
Setup command
set up looot for URL to markdown API - https://looot.ai/use-cases/url-to-markdown-api/skill.md

Before you start

Settle these before the first run

  • Send the full URL with https:// in front. One provider here rejects a link without it.
  • A page built in JavaScript can come back nearly empty from a plain fetch. Use a browser endpoint for it, or Linkup with JavaScript rendering on.
  • Long pages make long markdown. Jina returns the token count of its answer, so your agent can check the size before it passes the text on.
  • Each call reads one URL. To read many pages, your agent loops over the links and you pay per page.

FAQ

Questions people ask

It is an endpoint that takes a link, fetches the page and returns its main content as markdown. Your agent gets the text with its headings and links, without the menus and scripts, ready to read or store.

Send the page URL to one of the endpoints on this page and read the markdown in the run's result. Your agent can then quote it, summarise it or split it into chunks.

Jina Reader is one of the endpoints on this page, billed per call through your looot key. The looot page for Jina at /mcp/jina covers its MCP server and its other tools.

No. Every endpoint here takes a URL and fetches the page itself. If you hold the HTML already, convert it in your own code or publish it at a link the provider can reach.

Yes, with Context.dev or Firecrawl, which fetch the page from a location you set. The other endpoints fetch from wherever the provider runs.

Context.dev returns the video's title, channel, description and transcript for a YouTube link. For transcripts at scale, the YouTube transcript API page compares the providers built for it.

You pay per call, and the price depends on the provider your agent picks. This page reads the cheapest live price from the catalog and shows no number when the catalog is unreachable.

No. A call that fails at the provider costs nothing, and your agent can retry it or send it to another provider.

No. One looot key reaches every provider in the catalog. You top up once, and each call is billed at the price shown before it runs.

Send a POST to /v1/runs with the endpoint id, the input and a new idempotency key, and your looot token in the Authorization header. With wait set to 30, the answer comes back in the response when the run ends within 30 seconds. Otherwise poll GET /v1/runs/<runId>.

That needs scheduled runs, not available yet. Run it by hand whenever you want fresh results.

No. looot bills per call, and nothing runs while your agent is idle.
For agents
use case
URL to markdown API
run
page
schedule
on demand
step
Read the page as markdown: jina context-dev linkup steel firecrawl
setup
https://looot.ai/use-cases/url-to-markdown-api/skill.md
llms.txt
https://looot.ai/llms.txt
updated
2026-10-04
markdown /use-cases/url-to-markdown-api.md

Try URL to markdown with your own agent.

Start your workspace, top up, and paste the prompt into the agent you already use.

Start your workspace See agent recipes