Firecrawl

What is Firecrawl?

Firecrawl is a web data API for AI agents and LLM applications. Its endpoints scrape a single page, crawl a whole site by following links, map a site's URLs, search the web, run an interactive browser sandbox and launch an autonomous research agent. Pages come back as clean markdown, HTML or structured JSON, with options for PDF parsing, LLM extraction, PII redaction and zero data retention. Usage is metered in credits: a scrape or crawled page costs 1 credit, a map call 1 credit, and search 2 credits per 10 results. The project is open source under AGPL-3.0 and also sold as a hosted service. Plans run from a free tier with 1,000 credits a month to Hobby at $19/month, Standard at $99/month, Growth at $399/month and Scale at $749/month, plus custom Enterprise terms and pay-as-you-go credit top-ups.

Use cases

• Scrape pages into markdown for LLMs
• Crawl a whole website
• Give AI agents live web search
• Feed RAG pipelines with site content
• Extract structured JSON from pages
• Map every URL on a site
• Run a browser session through an API

Who it's for

• AI application developers
• Data engineers
• Agent builders
• Enterprise IT teams

Why use Firecrawl

• Replaces custom crawler code with one API that handles scraping, crawling, mapping and search.
• Returns content shaped for models, which keeps downstream RAG and agent prompts simple.
• Gives a free tier of 1,000 monthly credits with no credit card required to test it.
• Lets you run the open-source code yourself or use the hosted service, depending on your compliance needs.
• Prices usage in credits, so cost follows the pages and options you use.

Firecrawl features

• Scrape endpoint for markdown, HTML or structured data
• Crawl endpoint that follows links across a site
• Map endpoint that lists a site's URLs
• Search endpoint with optional result scraping
• Interact browser sandbox billed per browser minute
• Autonomous web research agent
• LLM-based JSON extraction and question formats
• PDF parsing and audio or video transcription
• PII redaction and zero data retention options
• Signed webhooks and SOC 2 Type II compliance
• Pay-as-you-go credits on paid plans

Firecrawl integrations

• MCP

How to get started with Firecrawl

1. Sign up for a free API key, or call the keyless endpoints for limited free use of search, scrape and parse.
2. Choose an endpoint: scrape a URL, crawl a site, map its links, search the web or open an interactive session.
3. Add options such as JSON extraction, PDF parsing or PII redaction, which add credits per page.
4. Pass the returned markdown or structured data into your LLM, agent or data pipeline.
5. Upgrade the plan or enable pay-as-you-go credits when the monthly allotment runs out.

Firecrawl limitations

• The Free plan has 1,000 credits a month, 2 concurrent requests and low rate limits
• Scrape options such as JSON extraction add credits per page
• Zero data retention, SSO and SCIM require Enterprise
• AGPL-3.0 licensing carries obligations if you modify and host the code

Firecrawl pricing

Yes, Firecrawl has a free plan. Paid plans start at $19 per month, according to the official pricing page on 24 Oct 2026.

Firecrawl plans

• Free

  $0

  No credit card required

  • 1,000 credits per month
  • 2 concurrent requests
  • Low rate limits
  • Community support

• Hobby

  $19/month

  or $16/month billed annually ($190/year)

  • 5,000 credits per month
  • 5 concurrent requests
  • Basic support
  • Pay-as-you-go credits

• Standard

  $99/month

  or $83/month billed annually ($990/year)

  • 100,000 credits per month
  • 25 concurrent requests
  • Standard support
  • Pay-as-you-go credits

• Growth

  $399/month

  or $333/month billed annually ($3,990/year)

  • 500,000 credits per month
  • 50 concurrent requests
  • Priority support
  • Slack support

• Scale

  $749/month

  or $599/month billed annually ($7,190/year)

  • 1,000,000 credits per month
  • 100 concurrent requests
  • Priority support
  • One-month credit rollover
  • Invoiced billing

• Enterprise

  Custom

  • Custom credits and concurrency
  • Dedicated support and SLA
  • Zero-data retention
  • SSO and SCIM
  • Bulk discounts

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

Firecrawl alternatives

The main Firecrawl alternatives listed on Debuly are Crawl4AI, Exa, Browserbase, Hyperbrowser, Spider and Tavily. The table compares pricing and platforms; order is A–Z.

1. 

   Browserbase

   Cloud platform of headless browsers, search and fetch APIs and agent runtime for building AI agents that browse and act on the web.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Browserbase (official site)
2. 

   Crawl4AI

   Open-source web crawler and scraper that turns pages into clean Markdown for LLMs and RAG, with an optional hosted cloud API.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Crawl4AI (official site)
3. 

   Exa

   Web search API for AI agents and apps that returns relevant passages with citations, billed pay-as-you-go from a free monthly credit.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Exa (official site)
4. 

   Hyperbrowser

   Cloud infrastructure that gives AI agents hosted Chrome sessions, isolated sandboxes, and web fetch, crawl and search APIs.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Hyperbrowser (official site)
5. 

   Spider

   Web crawling and scraping API with cloud browsers and residential proxies, billed per request, for AI agents and data pipelines.

   Developer platformsAutomation and agentsResearch and search
   PaidVisit Spider (official site)
6. 

   Tavily

   Web search, extraction and crawling API built for AI agents and RAG, with a free tier of 1,000 credits a month.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Tavily (official site)

Firecrawl FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from firecrawl.dev · fetched 23 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.