← Back to directory

Firecrawl

The context API to search, scrape, and interact with the web at scale

Visit Firecrawl

It handles JS rendering, content waiting, and extraction so developers don't have to run their own headless-browser scraping stack.

Vendor's own claim
other/unknown

Core capabilities

Vendor's own claim
  • Scrape - convert a single page into markdown, structured JSON, or a screenshot
  • Crawl - follow links across an entire site and return content for every page
  • Map - return the full list of indexed/discoverable URLs on a site without scraping content
  • Search - query the web and optionally return full page content for results, not just links
  • Extract - pull structured data from pages using natural-language prompts / a schema
  • Interact - drive a live browser session (click, fill forms, navigate) via AI prompts to reach dynamic content
  • Monitor - track a page or site for changes over time
  • Agent (preview) - an autonomous research agent that browses and extracts structured data on its own

API & agent surface

From official docs
Authentication
API key (Bearer token), e.g. Authorization: Bearer fc-xxxxxxxx; no key required for basic/rate-limited use
Base URL
https://api.firecrawl.dev
Notable endpoints
  • POST /scrape - extract a single page as markdown, JSON, or screenshot
  • POST /crawl - asynchronous crawl of an entire site
  • POST /map - return the full list of URLs on a site
  • POST /search - query the web and optionally return full content
  • POST /extract - LLM-based structured extraction from pages
MCP tools exposed
firecrawl_scrapefirecrawl_mapfirecrawl_searchfirecrawl_parsefirecrawl_crawlfirecrawl_check_crawl_statusfirecrawl_extractfirecrawl_agentfirecrawl_agent_statusfirecrawl_interactfirecrawl_interact_stop
Machine-readable spec
No OpenAPI link

Official skills & repos

From official docs

Published by the vendor themselves — not community forks.

Pricing

From official docs
PlanPriceIncludedNotable
Free Plan$0/month1,000 credits/month + 1,000 search creditsScrape up to 1,000 pages, 2 concurrent requests, Low rate limits
Hobby$16/month5,000 credits/month + 1,000 search credits (billed yearly, save $38)Scrape up to 5,000 pages, 5 concurrent requests, Basic support
Standard$83/month100,000 credits/month + 1,000 search credits (billed yearly, save $198)Scrape up to 100,000 pages, 50 concurrent requests, Standard support
Growth$333/month500,000 credits/month + 1,000 search credits (billed yearly, save $798)Scrape up to 500,000 pages, 100 concurrent requests, Priority support
Scale$599/month1,000,000 credits/month + 1,000 search credits (billed yearly, save $1,798)Scrape up to 1,000,000 pages, 150 concurrent requests, Priority support
EnterpriseContact salesCustom creditsUnlimited pages, Custom concurrency, Dedicated support & SLA

Checked 2026-07-30 against their pricing page. Vendors change pricing without notice.

What is Firecrawl

Vendor's own claim

Firecrawl is a developer-focused API product (by the team behind Mendable) that packages web scraping, crawling, and browser automation into a single credit-metered API and official MCP server, aimed at teams building AI agents, RAG pipelines, lead-enrichment tools, and research assistants that need live web data without maintaining their own scraping infrastructure. The vendor claims 1.25M+ developers and 150,000+ companies use it, naming Apple, Canva, Shopify, Zapier, and DoorDash as customers, and the core `firecrawl/firecrawl` GitHub repo has 158K+ stars.

Ideal customer profile

Vendor's own claim

Developers and AI teams building agents, RAG pipelines, lead enrichment, competitive intelligence, content generation, price monitoring, or chatbots that need reliable, LLM-ready web data via API or MCP - from solo builders on the free tier up to enterprises needing zero-data-retention and SSO.

Who should look elsewhere

Our read

Teams without engineering resources to call an API or wire up an MCP client should note that the official material checked on 2026-08-05 emphasized a data-extraction API and open-source app examples rather than a point-and-click GTM application. High-volume scraping teams should also model per-credit cost because credits are consumed by page, search, or browser minute and do not roll over on the retained self-serve plans.

Firecrawl alternatives

Our read

Infrastructure for fetching web pages at scale — proxies, headless browsers, and crawl-to-markdown services that agents can call directly.

Category: Scraping and browser infrastructure. Membership is decided by 3 stated tests, not by category tags — see them and the full comparison.

Firecrawl FAQ

Is there a free tier?

Yes - the Free Plan gives 1,000 credits/month plus 1,000 search credits with no card required, and basic use is even possible without an API key at reduced rate limits.

From official docs
Does Firecrawl publish a machine-readable OpenAPI spec?

The API reference exists as rendered docs, not as a spec we could confirm.

Our read
How is Firecrawl priced?

Credit-based, metered per feature (1 credit/page for scrape, crawl, and map; 2 credits/10 search results; 2 credits/browser-minute for Interact). Self-serve plans run from a free 1,000-credit tier up to $599/month for 1,000,000 credits, billed yearly with a monthly-equivalent price; Enterprise is custom.

From official docs
Who uses Firecrawl?

The vendor claims 1.25M+ developers and 150,000+ companies, naming Apple, Canva, Shopify, Zapier, and DoorDash as customers.

Vendor's own claim
Is Firecrawl open source?

The core engine (firecrawl/firecrawl) is open source on GitHub with 158K+ stars, alongside dozens of official example apps, SDKs, and integrations (n8n node, MCP server, CLI, browser plugins) published under the same GitHub org.

From official docs
What is 'Interact'?

A live browser-session tool that lets an AI agent click, fill forms, and navigate a page via natural-language prompts to reach content that plain scraping can't, billed per browser-minute.

Vendor's own claim
Does Firecrawl offer enterprise security controls?

The Enterprise plan lists zero-data retention, SSO & advanced security, dedicated support, and an SLA on the pricing page.

Vendor's own claim
How much setup does Firecrawl take?

A first call can happen in minutes - no API key is required to start, and the SDKs are a single install command away - though using the full surface (crawl, extract, interact, agent) well takes more reading.

Our read

Verify before you buy

  • Company headcount, funding, or valuation figures
  • A machine-readable OpenAPI specification was not included in the reviewed source set.

Need help setting it up?

This page tells you whether Firecrawl fits. Cheetah builds and runs the system it goes into — enrichment, sequencing, CRM and the joins between them.

Book a call →

The directory stays free. There is nothing gated behind this.