Skip to content

Catalogdata

Firecrawl

shipBlueshift — gaining momentum

Turn entire websites into clean, LLM-ready markdown or structured data.

Visit firecrawl.dev →Add to kitOpen in Noemium

ledger entry · observed by @whysanesanders

The go-to tool for scraping site content into markdown for RAG. Handles dynamic sites well and the self-hosted option keeps costs down. Very large sites need rate-limiting and chunking discipline.

Strengths

  • Go-to scrape-to-markdown path for RAG, including many dynamic sites.
  • Self-host option keeps cloud page-volume pricing off the critical path.

Known limitations

  • Large sites require careful rate limiting and caching.
  • Complex JavaScript apps can still break extraction.
  • Cloud pricing climbs with page volume.

Use it when

  • Turning a docs site or blog into LLM-ready markdown.
  • RAG pipelines that need structured extraction, not raw HTML.

Skip it when

  • The target is a huge site you cannot rate-limit and chunk.
  • The app is a brittle JavaScript SPA that still breaks extraction.
  • Cloud crawl volume is the only option and the bill would spike.

Floor guide

Install

Cloud at firecrawl.dev or self-host from mendableai/firecrawl. Start with the cloud free credits.

Requirements

  • A target site you are allowed to crawl
  • A sink (markdown files or a vector store)

Cost

OSS self-host is free. Cloud: 1,000 credits/mo free, then Hobby/Standard/Growth. Page volume is the bill.

Security

Crawling sends the target HTML to Firecrawl Cloud unless you self-host. Do not point it at authenticated app pages you do not own.

Breaks when

  • The site is a brittle SPA and extraction comes back empty.
  • You crawl a huge site with no rate limit and get banned.

Buy-check

  • ·Price — freemium, open source self-host free; cloud 1,000 credits/mo free, then Hobby/Standard/Growth paid as of 2026-08-19. Open the pricing page, not a screenshot.
  • ·Free tier — Free tier exists — burn it first.
  • ·Cancel fallout — What happens to your data/projects on cancel — check the ToS, not the FAQ.
  • ·Seat math — Per-seat pricing multiplies quietly. Count seats before the annual plan.
  • ·Who skips it — Also skipped when: The target is a huge site you cannot rate-limit and chunk.; The app is a brittle JavaScript SPA that still breaks extraction..

Price trail — 1 revisionchangelog →

  • 2026-W34open source self-host free; cloud from $16/moopen source self-host free; cloud 1,000 credits/mo fr…

Facts

pricing
freemium1
price note
open source self-host free; cloud 1,000 credits/mo free, then Hobby/Standard/Growth paid
free tier
yes
open source
yes
api
yes
self-host
yes
category
data
evidence
source-verified

Data: trains on inputs unknown · local processing yes

Sources

  1. 1firecrawl.dev[snapshot]
  2. 2github.com/mendableai/firecrawl[snapshot]

No source, no number.

Edit this page on GitHub

Similar joball alternatives →

toolverdictpriceossself-host
Firecrawlshipfreemiumyesyes
Exashipfreemiumnono
Tavilyshipfreemiumnono
Perplexityshipfreemiumnono

Facts from the catalog files — not scores you can buy. Quality and speed stay in the briefing, not in a fake 1–5 grid.

Exa
dataship

Exa

Neural search engine for finding and ranking web pages by meaning.

APIFREE TIER

freemiumfree $10 credits/mo; usage-based PayGO; Enterprise custom

Blueshift — gaining momentum
Tavily
dataship

Tavily

Search API optimized for LLM agents with structured, sourced answers.

APIFREE TIER

freemiumfree tier (1k calls/mo); paid from $30/mo

Blueshift — gaining momentum
Perplexity
dataship

Perplexity

Answer engine with citations — search rebuilt around LLMs.

APIFREE TIER

freemiumfree tier; Pro $20/mo, Max $200/mo

Blueshift — gaining momentum