Markdown

HTML in. LLM-ready Markdown out.

Convert any URL into clean Markdown: chunked, embed-ready, deduplicated. The fastest path from "the live web" to a vector store. Built specifically for RAG and LLM training pipelines.

Try in playground Read the docs

credits / call

1.1s

p50 latency

chunk strategies

POST /markdown

POST /markdown
{
  "url":      "https://docs.stripe.com/api/charges",
  "chunk":    "semantic",
  "max_tokens": 800,
  "include":  "main, article, .content"
}

→ 200 OK · 5 credits · 1.1s
{
  "chunks": [
    { "id":"c0", "tokens": 412, "text":"# Charges\n\nA Charge..." },
    { "id":"c1", "tokens": 786, "text":"## Create a Charge\n\nPOST /..." },
    ...
  ],
  "title": "Stripe API · Charges",
  "url":   "https://docs.stripe.com/api/charges"
}

Live playground

See it work, before you sign up.

Drop in a URL, run a real call against the live API, and watch the JSON come back in about a second. No API key required.

Real Markdown

Headings stay headings. Tables stay tables. Code blocks keep their language hints. Links keep their anchors. None of the GPT-flattened slop.

Smart chunking

Pick semantic (header-aware), fixed (token-bounded), sentence, or none. We respect natural document boundaries.

Token-counted

Every chunk comes with tokens pre-counted for the tokenizer of your choice (cl100k, o200k, claude). No surprises at embedding time.

Boilerplate stripped

Nav, footer, ads, "related articles", all gone. Pass include selectors to keep specific zones; pass exclude to drop them.

Embed-ready

Pass embed: "openai" or embed: "voyage" and we return chunks with embedding vectors attached. One round-trip, vector-store-ready.

Drop-in code

Copy. Paste. Ship.

import { Ujeebu } from "ujeebu";
const uj = new Ujeebu(process.env.UJEEBU_KEY);

const { chunks } = await uj.markdown({
  url:        "https://docs.stripe.com/api/charges",
  chunk:      "semantic",
  max_tokens: 800,
});

await pinecone.upsert(chunks.map(c => ({
  id: c.id, values: await embed(c.text)
})));

from ujeebu import Ujeebu
uj = Ujeebu(api_key=os.environ["UJEEBU_KEY"])

result = uj.markdown(
    url="https://docs.stripe.com/api/charges",
    chunk="semantic", max_tokens=800,
    embed="openai",   # vectors included
)

pinecone.upsert([
    (c["id"], c["embedding"], {"text": c["text"]})
    for c in result["chunks"]
])

curl -X POST https://api.ujeebu.com/markdown \
  -H "ApiKey: $UJEEBU_KEY" \
  -d '{
    "url":    "https://docs.stripe.com/api/charges",
    "filter": "fit"
  }'

What people build with it

Real things real teams shipped this quarter.

RAG ingest at scale

A devtools company keeps embeddings of 18k docs sites fresh. Changed URLs re-sent nightly. No HTML stripping. No reprocessing.

LLM training corpora

Build domain-specific Markdown datasets. Filter by token count and language at extraction time, not in post-processing.

Doc-search products

Customer points at their docs URL. 90 seconds later they have a working "ask my docs" widget. Zero-config ingest, real-time freshness.

Ground-truth chunks for evals

Build LLM eval sets from real public content. Same chunks day-over-day means stable eval scores; no "the doc moved" noise.

Pricing

10 credits per Markdown call. Here's what that buys.

One credit pool covers every endpoint. Failed calls cost 0. No per-feature upcharges, no premium-proxy tax. See full pricing →

Start free

Starter per month

$49

30k

Markdown calls / month

300k credits · used flexibly across all endpoints

Markdown calls / month

1M credits · used flexibly across all endpoints

Markdown calls / month

3M credits · used flexibly across all endpoints

Markdown calls / month

15M credits · used flexibly across all endpoints

Choose Business

Pay-as-you-go top-ups PAYG From $0.24 / 1K down to $0.13 / 1K · no subscription · works on the trial too

Buy a credit pack any time. No subscription required. Works on the trial too - great for one-off batches or sizing before you commit. Top-up credits last 60 days under 500K credits, 90 days from 500K and 180 days from 5M. Each Markdown call is 10 credits; counts below convert at that rate.

Pack	Credits	~ Markdown calls	Price	Per 1K credits
Mini	50,000	5k	$12.00	$0.24	Buy
Starter	100,000	10k	$22.00	$0.22	Buy
Standard	500,000	50k	$105.00	$0.21	Buy
Pro	1,000,000	100k	$155.00	$0.16	Buy
Enterprise	5,000,000	500k	$650.00	$0.13	Buy

Sign up free to unlock the top-up flow - the trial's 5,000 credits land instantly, and you can buy any pack right after from the dashboard.

Ship Markdown tonight.

5,000 credits free. No card. Real residential proxies on the free tier.

Get API key Try in playground