Web Scraping

Firecrawl

Web data API for developers searching, scraping and interacting with the web at scale.

Overview

Firecrawl turns web pages and search results into clean content for software projects. It can crawl sites, extract data to a defined shape, parse documents and interact with pages. You can use Firecrawl's hosted infrastructure, official SDKs or CLI. The project is open source, and the free plan offers a lightweight way to get started.

Updated Nov 7, 2026

8 things

What Firecrawl has

For developers

Programmatic access to the product's data and features for developers.
Source code is publicly available for anyone to inspect, modify, or self-host.
A command-line interface that lets you run the tool from a terminal or scripts.
A Model Context Protocol server that lets AI tools connect to and act on your data.
A toolkit that lets developers build on the product using their preferred programming language.

Hosting and storage

A vendor-operated service that runs and maintains software on its own infrastructure.

Support

Faster answers from the support team than customers get as standard.
Real people you can contact when you need help with the tool.

19 features

Key Features

Search results
Send a query and Firecrawl returns relevant results from across the web, each with full-page markdown already included.
Web scraping
Give Firecrawl a URL and it returns clean, structured content — markdown, HTML, screenshots, metadata, or extracted data via a schema.
Page interaction
Scrape a page, then interact with it using AI prompts or code.
Structured data
Yes. Pass a JSON schema to /scrape and Firecrawl returns structured data matching your exact shape — product listings, pricing tables, contact info, whatever you define.
Output formats
Firecrawl returns clean markdown by default, optimized for LLM context windows.
Site crawling
Yes. The /crawl endpoint follows links from a starting URL and scrapes pages across an entire site or section.
Robots.txt rules
It also respects robots.txt rules set for the 'FirecrawlAgent' directive.
Document parsing
Firecrawl can parse and output content from pdfs, docx, and more.
Smart waiting
Firecrawl intelligently waits for content to load, making data extraction faster and more reliable.
Web index
Pull from a growing web index when you want speed, or go live when you need fresh data.
Large-scale extraction
With features like batch scraping, crawling, and scheduled syncs, it's designed to handle large-scale data extraction efficiently, making it ideal for enterprises and large projects.
Web search
Search the web and get full content from results.
Website scraping
Get llm-ready data from websites. Markdown, JSON, screenshot, etc.
Media parsing
Firecrawl can parse and output content from pdfs, docx, and more.
Smart wait
Firecrawl intelligently waits for content to load, making data extraction faster and more reliable.
Live web data
Pull from a growing web index when you want speed, or go live when you need fresh data.
Enhanced coverage
Reaches every corner of the web with comprehensive coverage and high reliability.
Page actions
Click, scroll, write, wait, press and more — interact with any page.
Data formats
Firecrawl returns clean markdown by default, optimized for LLM context windows.

Pros and cons

Pros

The free plan offers a lightweight way to get started.
Official SDKs cover Python, Node.js, Go, Rust, Java and Elixir, with a CLI for terminal work.
The hosted version handles proxies and rendering.
It is open source, with over 180K GitHub stars.

Cons

The Hobby plan is capped at 5000 credits each month.

As of November 2026

Pricing

Freemium. Paid plans start at $19 per month.

Free Plan
$0
Hobby
$19
per month
Standard
$99
per month
Growth
$399
per month
Scale
$749
per month
Enterprise
Custom
on request

Developer features

Web data API
Firecrawl is the web data API to search, scrape, and interact with the web at scale.

You?

Be the first to rate Firecrawl

Your review helps others make better decisions. No account needed. Takes about 10 seconds.

Featured Video

See Firecrawl at work before you try it.

Watch on YouTube

6 questions

FAQs

Is Firecrawl free?

Yes. Firecrawl has a free plan that offers a lightweight way to get started at no cost.

What does Firecrawl do?

It searches, scrapes and interacts with the web through an API. It can return page content, crawl a site and extract data that matches a JSON schema.

Is Firecrawl open source?

Yes. Firecrawl is open source, and its repository has more than 180K GitHub stars.

Who is Firecrawl for?

Firecrawl is for developers working with web data. Its large-scale extraction tools are designed for enterprises and large projects.

Does Firecrawl have integrations?

Yes. Listed integrations include ChatGPT, Claude, Cursor, LangChain, LlamaIndex, Lovable and OpenAI. It also has agent skills for Claude Code and Codex.

Does Firecrawl respect robots.txt rules?

Yes. Firecrawl respects robots.txt rules that are set for the FirecrawlAgent directive.

No reviews yet

Community reviews

Sort:Write a review

No written reviews yet. Be the first to share your experience.

Tried this tool? Share your experience.

Write a review

No reviews yet

Community reviews

Sort:Write a review

No written reviews yet. Be the first to share your experience.

Tried this tool? Share your experience.

Write a review

8 things

What Firecrawl has

For developers

Programmatic access to the product's data and features for developers.
Source code is publicly available for anyone to inspect, modify, or self-host.
A command-line interface that lets you run the tool from a terminal or scripts.
A Model Context Protocol server that lets AI tools connect to and act on your data.
A toolkit that lets developers build on the product using their preferred programming language.

Hosting and storage

A vendor-operated service that runs and maintains software on its own infrastructure.

Support

Faster answers from the support team than customers get as standard.
Real people you can contact when you need help with the tool.

19 features

Key Features

Search results
Send a query and Firecrawl returns relevant results from across the web, each with full-page markdown already included.
Web scraping
Give Firecrawl a URL and it returns clean, structured content — markdown, HTML, screenshots, metadata, or extracted data via a schema.
Page interaction
Scrape a page, then interact with it using AI prompts or code.
Structured data
Yes. Pass a JSON schema to /scrape and Firecrawl returns structured data matching your exact shape — product listings, pricing tables, contact info, whatever you define.
Output formats
Firecrawl returns clean markdown by default, optimized for LLM context windows.
Site crawling
Yes. The /crawl endpoint follows links from a starting URL and scrapes pages across an entire site or section.
Robots.txt rules
It also respects robots.txt rules set for the 'FirecrawlAgent' directive.
Document parsing
Firecrawl can parse and output content from pdfs, docx, and more.
Smart waiting
Firecrawl intelligently waits for content to load, making data extraction faster and more reliable.
Web index
Pull from a growing web index when you want speed, or go live when you need fresh data.
Large-scale extraction
With features like batch scraping, crawling, and scheduled syncs, it's designed to handle large-scale data extraction efficiently, making it ideal for enterprises and large projects.
Web search
Search the web and get full content from results.
Website scraping
Get llm-ready data from websites. Markdown, JSON, screenshot, etc.
Media parsing
Firecrawl can parse and output content from pdfs, docx, and more.
Smart wait
Firecrawl intelligently waits for content to load, making data extraction faster and more reliable.
Live web data
Pull from a growing web index when you want speed, or go live when you need fresh data.
Enhanced coverage
Reaches every corner of the web with comprehensive coverage and high reliability.
Page actions
Click, scroll, write, wait, press and more — interact with any page.
Data formats
Firecrawl returns clean markdown by default, optimized for LLM context windows.

Pros and cons

Pros

The free plan offers a lightweight way to get started.
Official SDKs cover Python, Node.js, Go, Rust, Java and Elixir, with a CLI for terminal work.
The hosted version handles proxies and rendering.
It is open source, with over 180K GitHub stars.

Cons

The Hobby plan is capped at 5000 credits each month.

As of November 2026

Pricing

Freemium. Paid plans start at $19 per month.

Free Plan
$0
Hobby
$19
per month
Standard
$99
per month
Growth
$399
per month
Scale
$749
per month
Enterprise
Custom
on request

Developer features

Web data API
Firecrawl is the web data API to search, scrape, and interact with the web at scale.

You?

Be the first to rate Firecrawl

Your review helps others make better decisions. No account needed. Takes about 10 seconds.

Featured Video

See Firecrawl at work before you try it.

Watch on YouTube

6 questions

FAQs

Is Firecrawl free?

Yes. Firecrawl has a free plan that offers a lightweight way to get started at no cost.

What does Firecrawl do?

It searches, scrapes and interacts with the web through an API. It can return page content, crawl a site and extract data that matches a JSON schema.

Is Firecrawl open source?

Yes. Firecrawl is open source, and its repository has more than 180K GitHub stars.

Who is Firecrawl for?

Firecrawl is for developers working with web data. Its large-scale extraction tools are designed for enterprises and large projects.

Does Firecrawl have integrations?

Yes. Listed integrations include ChatGPT, Claude, Cursor, LangChain, LlamaIndex, Lovable and OpenAI. It also has agent skills for Claude Code and Codex.

Does Firecrawl respect robots.txt rules?

Yes. Firecrawl respects robots.txt rules that are set for the FirecrawlAgent directive.

Firecrawl

Overview

What Firecrawl has

For developers

Hosting and storage

Support

Key Features

Search results

Web scraping

Page interaction

Structured data

Output formats

Site crawling

Robots.txt rules

Document parsing

Smart waiting

Web index

Large-scale extraction

Web search

Website scraping

Media parsing

Smart wait

Live web data

Enhanced coverage

Page actions

Data formats

Pros and cons

Pros

Cons

Pricing

Firecrawl pricing plans

Free Plan

Hobby

Standard

Growth

Scale

Enterprise

Developer features

Web data API

Be the first to rate Firecrawl

Featured Video

FAQs

Is Firecrawl free?

What does Firecrawl do?

Is Firecrawl open source?

Who is Firecrawl for?

Does Firecrawl have integrations?

Does Firecrawl respect robots.txt rules?

What Firecrawl has

For developers

Hosting and storage

Support

Key Features

Search results

Web scraping

Page interaction

Structured data

Output formats

Site crawling

Robots.txt rules

Document parsing

Smart waiting

Web index

Large-scale extraction

Web search

Website scraping

Media parsing

Smart wait

Live web data

Enhanced coverage

Page actions

Data formats

Pros and cons

Pros

Cons

Pricing

Firecrawl pricing plans

Free Plan

Hobby

Standard