Firecrawl
Turns websites into LLM-ready Markdown and data for AI agents
Overview
Firecrawl is a web data API for AI: scrape, crawl, map and search endpoints that return clean Markdown, JSON and screenshots, an Agent endpoint for multi-site research, plus Interact, Monitor and the Alexandria index; open source under AGPL-3.0. Free 1,000 credits a month; Hobby $19 a month.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 1 Oct 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
- 1,000 credits a month
- 2 concurrent browsers
- Low rate limits
- 5,000 credits
- 5 concurrent browsers
- Basic support
- 100,000 credits
- 25 concurrent browsers
- Standard support, DPA
- 500,000 credits
- 50 concurrent browsers
- Priority and Slack support
- 1,000,000 credits
- 100 concurrent browsers
- One-month credit rollover
- SSO and SCIM
- Zero data retention
- SLA and bulk discounts
Use cases
What you can produce with Firecrawl
- Scrape, crawl and map endpoints returning Markdown and JSON
- Search with page content
- Agent endpoint for multi-site research
- Interact and Monitor for page actions and change tracking
- Alexandria licensed and proprietary data indexes
- SDKs, CLI and MCP server
Firecrawl is one of the most popular ways to feed live web content into AI agents and retrieval pipelines: reliable scraping of difficult pages, whole-site crawls, search with content, and now multi-site research and licensed data through Alexandria, backed by fresh funding. Credits go quickly at scale and some developers find it expensive, while the open-source version is AGPL-licensed, which matters for commercial self-hosting. Start on the free 1,000 credits; budget carefully for heavy crawling.
What we found
Firecrawl is an API that turns websites into clean Markdown, structured JSON and screenshots for AI applications. Its scrape endpoint handles single pages, including JavaScript-heavy ones, through stealth browsers and proxies; crawl and map discover and fetch whole sites; search returns web results with their content; and the Agent endpoint, the successor to Extract, gathers and structures information across sites from a prompt. Newer products include Interact, for clicking and typing on pages, Monitor, for tracking changes, and Alexandria, launched with its September 2026 funding, which combines licensed data from providers such as Wikimedia Enterprise with Firecrawl's own research, developer and government indexes. There are SDKs, a command-line tool and an MCP server, and the core is open source under the AGPL-3.0 licence. Its benchmarks, such as 96% coverage on its own 1,000-URL test, are its own.
SideGuide Technologies, Inc., trading as Firecrawl, is based in San Francisco with a hub in Toronto. It began in Y Combinator's summer 2022 batch, building Mendable before Firecrawl, and was founded by Caleb Peffer, its chief executive, Eric Ciarla and Nicolas Silberstein Camara. It raised a $14.5 million Series A in August 2025 and a $75 million Series B led by Smash Capital on 22 September 2026, and says it has more than 1.5 million users, including teams at Apple, Canva and Lovable.
Pricing changed on 4 September 2026. The free plan gives 1,000 credits a month, about 1,000 pages, with two concurrent browsers and no card. Hobby costs $19 a month, or $16 billed annually, for 5,000 credits; Standard $99, or $83, for 100,000; Growth $399, or $333, for 500,000; and Scale $749, or $599, for a million credits with rollover. Extra credits come in $5 steps, and JSON extraction costs four extra credits a page. It holds SOC 2 Type II certification.
G2 shows a single review, and some developers on Hacker News have called it expensive. It suits developers feeding web content into AI agents and retrieval pipelines.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
About this listing
This entry was compiled from publicly available data including Firecrawl's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Firecrawl unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to Firecrawl directly →
Spotted something out of date? Suggest an update →
From our guides
Guide · 13 min read
Firecrawl vs Crawl4AI vs Jina Reader vs Browser Use — Getting Web Data Into Your LLM (2026...
Four open-source ways to feed web data to an LLM compared: licenses, self-host p...
Guide · 16 min read
Self-Host Firecrawl with Docker: Scrape the Web into LLM-Ready Markdown (2026)
We cloned Firecrawl v2.11.0, built its seven-service Docker stack, and scraped o...
More in Code & Dev Tools
