Website to Markdown API
Convert any URL to clean Markdown for LLM ingestion, RAG pipelines and docs migration.
{
"url": "example.com",
"format": "markdown"
}- Output
- Markdown
- Cost
- 1 credit a page
- Best for
- RAG and docs migration
- 500 free credits every month
- No card to start
- Failed requests cost nothing
POST /webscraping
{
"url": "stripe.com",
"format": [
"markdown"
]
}
Raw HTML fights your LLM
- Nav bars, ads and markup waste tokens and pollute context
- Layout changes silently break brittle parsers
- You maintain headless browsers, proxies and CAPTCHA solvers yourself
Clean Markdown
~60% fewer tokens- Headings, lists, links and tables preserved, boilerplate stripped
markdown-llmstrips nav and ads further for token-efficient RAG context- Rendering, proxies and anti-bot handled for you
There is no separate endpoint to learn. Set format: "markdown" — or "markdown-llm" — on the Web Scraping API.
Structure in, structure out.
The conversion keeps what carries meaning and drops what carries layout, so chunks land on real boundaries instead of mid-sentence.
Preserves structure
Headings, lists, links and tables convert to proper Markdown, not flattened text.
# ## - | |LLM-ready variant
markdown-llm additionally strips navigation, ads and cookie banners, leaving the content you meant to embed.
format: "markdown-llm"Handles JS-rendered pages
Headless Chrome renders React, Vue and Angular pages fully before the Markdown conversion runs.
renderJSChunks predictably
Because headings survive, your splitter can cut on sections rather than on an arbitrary character count.
RAG-readySeveral formats at once
Ask for Markdown and HTML in the same request when you need both, and pay the same single credit.
format: ["markdown", "html"]Same key, same pool
Markdown costs no more than raw HTML, and the credits are shared with every other Geekflare API.
1 creditHow teams run Markdown in production.
Split on headings, not on a character count
Fixed-size chunking cuts mid-sentence and strands a table from its caption. Because the conversion keeps H1–H6, your splitter can cut on sections, so each chunk is a coherent idea with a heading you can cite in the answer.
- Heading levels survive so sections are addressable
- Tables stay with the text that introduces them
- Cite the heading back to the user as the source
POST /webscraping
{
"url": "https://docs.example.com/billing",
"format": ["markdown-llm"]
}One request, Markdown back.
# pip install geekflare-api
from geekflare_api.client import GeekflareClient
from geekflare_api.models import WebScrapeDto
with GeekflareClient(api_key="<api-key>") as client:
result = client.web_scrape(
WebScrapeDto(
url="https://example.com",
format=["markdown"]
)
)
print(result)One credit a page, whichever format.
Markdown costs same as HTML scraping, and credits are shared with every other Geekflare API. Failed requests cost nothing.
Growth covers up to ~100,000 pages a month (100K credits), about $0.69 per 1,000 pages. Or $58/mo billed yearly.
- 500 credits / month
- 1 team member
- 7 days log retention
- 1 request per second
- 10K credits / month
- 3 team members
- 30 days log retention
- 5 requests per second
- 100K credits / month
- 5 team members
- 30 days log retention
- 10 requests per second
- 1M credits / month
- 25 team members
- 90 days log retention
- 25 requests per second
Teams that stopped maintaining scrapers.
“Found Geekflare API to get markdown from URL for my AI agents. It is fast and cheaper and works on almost every website.”
Ram DasiArchitect, PA Consulting“After trying many scraping services, I selected Geekflare to scrape public directories. Mainly for two reasons - it is cheaper and fast.”
“Documentation was easy to follow. We were scraping dynamic pages within hours. Very reliable service.”
Markdown, specifically.
General scraping questions are answered on the Web Scraping API page.
Open the Web Scraping API pagemarkdown converts the page's structure faithfully — headings, links, tables, images. markdown-llm additionally strips navigation, ads, cookie banners and other boilerplate that isn't useful context for a model.href as standard [text](url) Markdown, and heading levels H1–H6 are preserved.format: "markdown-llm" exists. Boilerplate-free Markdown chunks more predictably than raw HTML and avoids spending embedding budget on layout noise.Start extracting Markdown today.
Create a free account to test URLs in the playground and grab your API key. 500 credits a month, no card.