Firecrawl
Popular tool that turns web pages into clean text for AI apps; free to self-host, 1,000 free API pages a month.
Should you use it?
Pick it if
Developers building AI apps or agents that need to read web pages.
Best for: Developers whose AI apps or agents need to read web pages (Automation and agents Top 20)
Skip it if
You only need web search results, not page contents; a search API such as Exa may fit better.
You give up: Self-hosting lacks some cloud features; structured output costs 5 credits a page
The short version
- What this is
- An open-source tool and paid API that crawls websites and turns the pages into clean Markdown or JSON for AI models.
- Why it matters
- Feeding web pages to an AI is a common need; this is the default many builders reach for, and it is free to self-host.
- 190.3k GitHub stars; AGPL-3.0, with MIT SDKs s1.
- API free for 1,000 pages a month; Hobby $19/month s2.
- No independent quality test yet, so no score yet.
Good at
Our take
Firecrawl is a widely used open-source tool for letting an app or agent read the web, with 190.3k GitHub stars s1. It takes a URL and returns clean Markdown or structured JSON s1. The latest server release is v2.11.0 from 19 June s5, but the Python SDK shipped on 8 Oct 2026 s4, so the project is active.
You can run it yourself for free, but the README says the cloud version has extra features s1, and the AGPL-3.0 license has sharing duties if you offer a changed version as a service. The cloud API's free plan covers 1,000 basic pages a month s2. Watch the credit costs: structured JSON extraction adds 4 credits a page s2. We have no independent test of extraction quality to score it yet.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent test of web-extraction quality from the last 90 days is published.
DataResearchAgents
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for data, from our scores, then the ones we'd also look at. The same kind of product comes first.
- Gemini 3.8 FlashTop scoredText model85$19.99 a monthScores 85 in data, first in our ranking; $19.99 a month. Side by side
- LlamaParseDeveloper toolNot reviewed yet$50 a monthFor PDFs and office documents rather than web pages.
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 5
- s1GitHub: firecrawl/firecrawl
- s2Firecrawl pricing
- s3Firecrawl privacy policy
- s4PyPI: firecrawl-py
- s5GitHub: firecrawl releases
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 1 change
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look as a category leader for web data in AI apps. No independent quality test, so not rated yet.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.