Hydrafetch

Hydrafetch is a web data API for LLMs and agents. Send a URL and get back clean Markdown, the page’s own structured data, schema-shaped JSON, links, or a summary. Both panels below are real responses from the live API — the same Wikipedia article, scraped two different ways.

Clean Markdown

The page ships 59,769 tokens of nav, scripts and boilerplate. Your model reads 6,831 tokens of article.

Structured data

Every page also comes back as normalized fields — title, site, type, language, published date — with no LLM involved.

Clean Markdown

The page ships 59,769 tokens of nav, scripts and boilerplate. Your model reads 6,831 tokens of article.

Structured data

Every page also comes back as normalized fields — title, site, type, language, published date — with no LLM involved.

Building with an agent

These docs are written to be read by a model as well as a person. Every page is available as Markdown by appending .md to its URL, and the API describes itself at /mcp/tools and /openapi.json, both without a key. The fastest way to start is to let your agent read that and wire it up:

Prompt

Read https://hydrafetch.com/agents.md and set up Hydrafetch in this project.

Use the HYDRAFETCH_API_KEY environment variable, never a hardcoded key. Then make one scrape call against a URL that is relevant to what this project does, and show me the markdown it returns and what it cost.

Published skills go further: where-to-use-hydrafetch audits a codebase for where we fit, and the full index covers scraping for context, company research, schema extraction and dataset building.

Start here

Scrape

One URL in, clean Markdown and structured data out. The core primitive.

Map

Discover every URL on a site, fast, before you decide what to pull.

Crawl

Walk a whole site and scrape every page as one asynchronous job.

Search

Run a query and get ranked results, each scraped to clean data.

Extract

Pull schema-shaped JSON from pages, with per-field confidence and sources.

Media

Capture a full-page screenshot or collect a page’s images.

Why Hydrafetch

LLM-ready by default

Output is clean Markdown and normalized structured data. No boilerplate, no navigation cruft, no half-rendered pages.

One surface for the whole job

Scrape, crawl, map, search, and extract share the same options and the same clean response shape.

Trustworthy extraction

Structured extraction can return, per field, how confident it is and the exact passage a value came from.

Predictable cost

Every call is billed in credits, charged only on success, and each response tells you what it consumed.

Your first call

Send a URL, get clean Markdown back.

curl -X POST https://api.hydrafetch.com/v1/web/scrape \
  -H "X-API-Key: $HYDRAFETCH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://example.com" }'

const res = await fetch("https://api.hydrafetch.com/v1/web/scrape", {
  method: "POST",
  headers: {
    "X-API-Key": process.env.HYDRAFETCH_API_KEY!,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ url: "https://example.com" }),
});

const { data } = await res.json();
console.log(data.markdown);

import os, requests

res = requests.post(
    "https://api.hydrafetch.com/v1/web/scrape",
    headers={"X-API-Key": os.environ["HYDRAFETCH_API_KEY"]},
    json={"url": "https://example.com"},
)
print(res.json()["data"]["markdown"])

How it works

Get an API key

Every request carries your key in the X-API-Key header. See Authentication.

Call an endpoint

Send a URL, or a query, to the endpoint that fits your job. Most calls return clean data synchronously.

Get clean data back

Responses are LLM-ready: Markdown, structured entities, extracted JSON, links, summaries, or images.

Base URL

All endpoints live under a single versioned base URL:

https://api.hydrafetch.com/v1/web

Ready to make your first call? Head to the Quickstart.

Get started

Core concepts

Web Scraping

Web Extraction

Clean Markdown

Structured data

Clean Markdown

Structured data

Building with an agent

Start here

Scrape

Map

Crawl

Search

Extract

Media

Why Hydrafetch

LLM-ready by default

One surface for the whole job

Trustworthy extraction

Predictable cost

Your first call

How it works

Base URL

Clean Markdown

Structured data

Clean Markdown

Structured data

​Building with an agent

​Start here

Scrape

Map

Crawl

Search

Extract

Media

​Why Hydrafetch

LLM-ready by default

One surface for the whole job

Trustworthy extraction

Predictable cost

​Your first call

​How it works

​Base URL

Building with an agent

Start here

Why Hydrafetch

Your first call

How it works

Base URL