Firecrawl in ChatGPT

Install the official Firecrawl plugin to give ChatGPT and Codex live web data.
Search, scrape, crawl, and interact with pages without leaving the chat.

//
Used by over 1.25M developers
//
Trusted by 150,000+
companies
of all sizes
[ 01 / 04 ]
·
Features

Perfect for

Research without leaving ChatGPT: market maps, company research, and technical questions answered from current sources, with citations
Compare competitor pricing and feature pages in one table
Pull the latest docs into Codex before it writes code
Enrich a lead list from company websites
Get notified in Slack when a pricing page or changelog changes
Query data providers, such as financial news, through Firecrawl Alexandria

Key Features

Search the web and get ranked results with the most relevant excerpts
Scrape any URL into clean markdown, or into JSON fields with a schema
Map every URL on a site, or crawl a section such as a docs site
Parse documents you upload, such as PDFs and DOCX files
Interact with live pages: navigate, click, and fill forms
Run Firecrawl Agent to research a question across many sources
Monitor pages for changes and send alerts to Slack
Pull structured records from 400+ data providers in Firecrawl Alexandria
Search research papers, follow citations, and read full-text passages
Search code repositories and API docs with the Developer Index
Built-in skills for common tasks, with no MCP setup
[ 02 / 04 ]
·
Installation

Install the Firecrawl plugin

One plugin works in both ChatGPT and Codex. Install it, connect your Firecrawl account, and start a new chat. You do not need to configure an MCP server, install skills, or paste an API key.

1

Install the Firecrawl plugin

Click Add to ChatGPT on this page to open the official Firecrawl listing in the ChatGPT plugin directory, where Firecrawl is one of the top three Productivity plugins. You can also open Plugins in ChatGPT or Codex and search for Firecrawl.

2

Connect your Firecrawl account

After you select Install, ChatGPT asks you to sign in to Firecrawl and approve the connection. No account yet? You can create one for free in the same flow.

3

Start a new chat

Start a new chat in ChatGPT or Codex so it loads the plugin, then ask it to use Firecrawl. For example:

Prompt
Find engineering leaders at Stripe and enrich their profiles

How do I get ChatGPT to summarize every page on a website?

To get ChatGPT to summarize every page on a website, install the Firecrawl plugin, ask it to map the site, then crawl the section you want. Firecrawl returns each page as clean Markdown, including pages built with JavaScript, and ChatGPT writes a summary per page plus an overview. A path such as /blog keeps the crawl focused.

1

List the pages with Firecrawl Map

Ask ChatGPT to map the site first. Firecrawl Map returns the site's URLs in one call, so you can see how big each section is before you crawl it. In this example, replace example.com with your site:

Prompt
Use Firecrawl to map https://example.com and group the URLs by section, with a page count for each section.
2

Crawl a section and summarize each page

Ask ChatGPT to crawl one section with a page limit and summarize what comes back. Each crawled page costs 1 Firecrawl credit, and a map costs 1 Firecrawl credit no matter how many URLs it returns. Replace the example URL with the section you want:

Prompt
Use Firecrawl to crawl https://example.com/blog, up to 50 pages. For each page, give the title, the URL and a two-sentence summary. Then write one paragraph on what the section covers.
3

Ask follow-up questions

Narrow the output in the same chat, for example a table of every page that mentions pricing, or crawl the next section. To read a single page instead, give ChatGPT the URL and ask it to scrape that page with Firecrawl.

[ 03 / 04 ]
·
What Our Customers Say
//
Community
//

People love
building with Firecrawl

Discover why developers choose Firecrawl every day.
//
FAQ
//

Frequently
asked questions

Everything you need to know about this integration.
General
It is Firecrawl's official plugin in the ChatGPT plugin directory, and one of the top three plugins in its Productivity category. It gives ChatGPT and Codex Firecrawl's tools for searching the web, scraping pages and documents, crawling sites, interacting with dynamic pages, and monitoring changes, plus access to the data providers in Firecrawl Alexandria. ChatGPT picks the right tool when your request needs live web data.
The plugin bundles Firecrawl's tools and skills. The tools cover search, scrape, crawl, interact, monitor, and Firecrawl Alexandria. The skills are ready-made workflows for common tasks, such as searching the web, scraping a page, crawling a site, or running an interaction flow, so you can start them without writing the prompt from scratch. Both come with the install, so you do not need to set up an MCP server or add skills separately.
Technical
Open the Firecrawl listing in the ChatGPT plugin directory, or search for Firecrawl under Plugins. Select Install, sign in to Firecrawl, and approve the connection. Then start a new chat and ask ChatGPT to use Firecrawl.
You need a Firecrawl account, and you can create one for free when you connect. You do not need to copy an API key. You sign in to Firecrawl from ChatGPT and the plugin uses your team's plan.
Integration
Yes. ChatGPT and Codex share the same plugin directory, so one install covers both. In Codex the plugin can also search the Developer Index to answer questions about how a library behaves.
ChatGPT's own page fetch often can't. In Glenn Gabe's GSQI retest on October 19, 2026, ChatGPT returned only navigation and footer text for a page whose main content was built with JavaScript. With the Firecrawl plugin, ChatGPT reads the page through Firecrawl's scrape tool, which renders JavaScript and returns the content a browser shows as Markdown.
Advanced
The Firecrawl plugin can do both. Firecrawl Scrape reads one URL, Firecrawl Map lists the URLs on a site, and Firecrawl Crawl follows links across a site or a section and returns every page's content. Crawled pages count against your team's Firecrawl credits, so give ChatGPT a page limit for large sites.
Start a new chat or restart ChatGPT after installing the plugin. Check that Firecrawl is installed and enabled under Plugins. If sign-in did not finish, open the plugin and reconnect your Firecrawl account.
More Questions 1
Remove the plugin in ChatGPT, or review and revoke connections from MCP settings in your Firecrawl dashboard.
Why Firecrawl?
The world's most comprehensive web data API. Our custom browser stack and semantic index deliver superior data quality across any website, handling more content types and edge cases than any competitor.
JavaScript rendering, dynamic content, and robust request handling built-in.
Process millions of pages with automatic rate limiting, caching, and distributed infrastructure.
Optimized scraping engine with parallel processing and smart caching for instant results.
Comprehensive docs, SDKs for all major languages, and dedicated support to help you succeed.
[ 04 / 04 ]
·
Pricing

Flexible pricing

Start for free, then scale as you grow.Are you an AI agent? See pricing

Free Plan

A lightweight way to get started.
No cost, no card, no hassle.
$0
/month
500 searches or 1,000 pages scraped
2 concurrent requests
Low rate limits

Hobby

Great for side projects and small tools.
Fast, simple, no overkill.
$16
/month
Billed yearly
Save $38
2,500 searches or 5,000 pages scraped
5 concurrent requests
Basic support
$9 per extra 1.5k credits

Standard
Most popular

Perfect for scaling with less effort.
Simple, solid, dependable.
$83
/month
Billed yearly
Save $198
50,000 searches or 100,000 pages scraped
25 concurrent requests
Standard support
$47 per extra 35k credits

Growth

Built for high volume and speed.
Firecrawl at full force.
$333
/month
Billed yearly
Save $798
250,000 searches or 500,000 pages scraped
50 concurrent requests
Priority support
$177 per extra 175k credits

Scale Plans

High-volume plans for teams that need more power and dedicated support. Get access to higher rate limits, more concurrent browsers, and priority support. Scale checks out instantly, no sales call needed.

Need more? Contact us

Also on AWS Marketplace and Google Cloud Marketplace.

Scale

For teams scaling their data pipelines
1,000,000 credits / month
$599/month
Billed yearly
Save $1,798
500,000 searches or 1,000,000 pages scraped
100 concurrent requests
Priority support
$397 per extra 350k credits

Enterprise

Power at your pace with custom solutions
Custom credits
Custom concurrent requests
Dedicated support & SLA
Bulk discounts
Zero-data retention
SSO & advanced security
//
Get started
//
Give ChatGPT live web data
Install the Firecrawl plugin and connect your account in under a minute.
Are you an AI agent? See setup options