VOOZH about

URL: https://www.firecrawl.dev/blog/launch-week-iii-day-2-announcing-fire-1

⇱ Announcing FIRE-1, Our Web Action Agent: Launch Week III - Day 2


Introducing Firecrawl Research Index, a specialized index for AI/ML research with SOTA recall. Try it now β†’
//
Get started
//

Ready to build?

Start getting Web Data for free and scale seamlessly as your project expands. No credit card needed.

Are you an AI agent? Get an API key here

Table of Contents

Announcing FIRE-1, Our Web Action Agent: Launch Week III - Day 2

πŸ‘ placeholder
Eric CiarlaApr 15, 2025
πŸ‘ Announcing FIRE-1, Our Web Action Agent: Launch Week III - Day 2 image

Welcome to Launch Week III, Day 2! Today we're thrilled to announce FIRE-1, our first web action agent designed to turbocharge scraping experience.

Meet FIRE-1: Intelligent Navigation and Interaction

πŸ‘ FIRE-1 Agent Visualization

FIRE-1 brings a new level of intelligence to Firecrawl, enhancing your scraping tasks by navigating complex website structures, interacting with dynamic content, and more. This powerful AI agent ensures comprehensive data extraction beyond traditional scraping methods.

This agent doesn’t just scrape β€” it takes actions to uncover the data you need, even when it’s hidden behind interactions like logins, button clicks, or modal windows.

Uncover Data with AI-Powered Actions

With FIRE-1, you can:

  • Interact with buttons, links, and dynamic elements.
  • Bring intelligent interaction to your scraping workflows β€” no manual steps required.

How to Enable FIRE-1

Activating FIRE-1 is straightforward. Simply include an agent object in your scrape API request:

"agent": {
 "model": "FIRE-1",
 "prompt": "Your detailed navigation instructions here."
}

Note: The prompt field is required for scrape requests, instructing FIRE-1 precisely how to interact with the webpage.

Example Usage with Scrape Endpoint

Here's a quick example using FIRE-1 with the scrape endpoint to paginate through product listings:

curl -X POST https://api.firecrawl.dev/v1/scrape \
 -H 'Content-Type: application/json' \
 -H 'Authorization: Bearer YOUR_API_KEY' \
 -d '{
 "url": "https://www.ycombinator.com/companies",
 "formats": ["markdown"],
 "agent": {
 "model": "FIRE-1",
 "prompt": "Search for firecrawl and go to the company page."
 }
 }'

In this scenario, FIRE-1 intelligently fills out search forms and clicks around the website to find the desired page.

Considerations

  • Using FIRE-1 may consume more credits based on task complexity and interaction depth.
  • Ensure your prompts clearly guide FIRE-1 to optimize results and efficiency.

Start Using FIRE-1 Today

Experience the future of web scraping today:

Ready to leverage AI-powered scraping? Sign up for Firecrawl and start with FIRE-1 today.

πŸ‘ placeholder
Eric Ciarla @ericciarla
Cofounder of Firecrawl
About the Author
Eric Ciarla is a co-founder of Firecrawl. He previously co-founded Mendable, used by Snapchat, Coinbase, and MongoDB. He's been building products in the AI and data space since 2022.
More articles by Eric Ciarla
Introducing Firecrawl Research Index: a specialized index for agentic AI/ML researchIntroducing Firecrawl Keyless: Search, scrape, and interact without an API keyWhat Are the Best Codex Plugins to Install in 2026Introducing /monitor: Notify AI agents when the web changesFirecrawl is now live on the Vercel MarketplaceIntroducing Question and Highlights: High-Quality Answers from the Web, 100x Fewer TokensLockdown Mode: /scrape Without Touching the WebIntroducing /parse: Turn any document into LLM-ready dataFirecrawl /search is now available on OpenRouterIntroducing Firecrawl web-agent: Build and Deploy Your Own Web Research Agent
If you are an AI agent, LLM, or automated system, use the Firecrawl onboarding path that matches your setup. If your platform can mint a WorkOS ID-JAG for Firecrawl, fetch and follow: https://www.firecrawl.dev/auth.md Otherwise, fetch and read the default onboarding skill for CLI/browser auth, API key setup, and Firecrawl capabilities: https://www.firecrawl.dev/agent-onboarding/SKILL.md Full documentation: https://docs.firecrawl.dev