Firecrawl is a web-scraping & crawling API built for LLMs: give it a URL and it returns clean markdown (handling JavaScript, proxies and anti-bot for you), or crawl a whole site for RAG. Here's the credit-based pricing, the free allowance, and how to start.
| Piano | Prezzo | Credits (≈ pages) |
|---|---|---|
| Gratuito livello gratuito | $0 | 1,000 credits / mo, recurring |
| Hobby | $19/mo ($16/mo billed yearly) | 5,000 credits / mo |
| Standard | $99/mo ($83/mo billed yearly) | 100,000 credits / mo, higher concurrency |
| Crescita | $399/mo ($333/mo billed yearly) | 500,000 credits / mo |
| Scala | $749/mo ($599/mo billed yearly) | 1,000,000 credits / mo |
| Impresa | costume | custom volume, SLA, support |
Firecrawl's free tier gives 1,000 credits every month, no card required — it renews automatically like the paid plans rather than being a one-time trial pool, so you don't lose it after your first test crawl. That's enough for roughly 1,000 scraped pages/month (fewer if you turn on JS rendering, screenshots or structured extraction, which cost more credits per page). Once you outgrow it, Hobby ($19/mo, 5,000 credits) is the first paid step up. For small recurring jobs, a cheaper raw scraper plus your own markdown conversion can still undercut it.
1. Iscriviti a firecrawl.dev.
2. Open the dashboard — you'll see your free credits.
3. Vai a Chiavi API and copy your key (starts with fc-).
4. Call the scrape endpoint with a Bearer token.
Scrape one page to markdown:
If you only need raw HTML or search results, a generic scraper is cheaper: ScraperAPI E Dati luminosi handle proxies at lower per-request cost, and SerpAPI returns search results as JSON. Firecrawl's edge is the LLM-ready markdown and whole-site crawl — worth it when you're feeding a RAG pipeline and don't want to write HTML cleaning. Pair it with an embeddings store like Pinecone and an LLM like OpenAI O Claudio.
Yes — 1,000 credits every month, no card required. It renews monthly like the paid plans; it isn't a one-time trial pool.
Sign up at firecrawl.dev, open the dashboard, go to API Keys, and copy the key (it starts with fc-). Use it as a Bearer token on the /scrape or /crawl endpoint.
Roughly one credit per page scraped or crawled. Extra features like JavaScript rendering, screenshots or structured extraction can cost more credits per page, so a crawl of 1,000 pages with extraction uses well over 1,000 credits.
Yes — that's its main use case. The crawl endpoint walks a site and returns clean markdown per page, which you can chunk and embed into a vector database for retrieval-augmented generation.
Not affiliated with Firecrawl. Prices are reference estimates — always verify on the official pricing page.