Any URL in.
Clean, LLM-ready Markdown out.

Any URL → clean, LLM-ready Markdown. JS-rendered, with crawl & map built in. JS rendering, site crawls, and semantic chunking included — so your RAG pipeline starts at the interesting part.

the web, as it actually is

<div class="nav-x9" data-tr="…">
  <script>window.__cfg={...}</script>
  <div style="display:none">SALE!</div>
  <h1 class="ttl-x">Pricing</h1>
  <td>Basic</td><td>$29/mo…

what your model gets

# Pricing

| Plan  | Price  |
|-------|--------|
| Basic | $29/mo |

Semantic chunks: 4
Tokens: 182

scrape

One URL → Markdown. Static fetch by default, real browser rendering when the page needs it.

crawl

Point at a site, get the pages that matter — sitemap-aware, budget-capped.

chunk

Semantic, heading-aware chunks sized for embeddings. Free with every plan.

pricing

Pages roll over (capped). Top-ups: 10,000 pages for $5.

Free

free

  • 1,000 pages/mo
  • 1× render concurrency
start free

Indie

$7/mo

  • 8,000 pages/mo
  • 3× render concurrency
get started

Builder

$19/mo

  • 35,000 pages/mo
  • 6× render concurrency
get started

Scale

$49/mo

  • 120,000 pages/mo
  • 12× render concurrency
get started

the full suite

GemScrape is the paid product. The rest of the suite ships around it — as free features and add-ons, not extra subscriptions. Here's what's live and what's next.

gembundle

coming soonfree with GemScrape

Crawl a whole site or repo into one clean, LLM-ready bundle — paste a single file into your model's context instead of wiring up a crawler. Want to know the moment it ships?

gemchunk

live in the pipeline

Semantic, heading-aware Markdown chunking sized for embeddings. Already runs on every scrape — free on all plans, including free.

gemsync

phase 2

Keep sources fresh — re-scrape on a schedule and get a webhook only when the content actually changed.

gemvision

planned · optional add-on

Vision extraction for image-heavy pages — alt-text and figure descriptions in your Markdown, using your own model key (BYOK). Optional; nothing in the core pipeline depends on it.

GemScrape — Any URL in. Clean, LLM-ready Markdown out.