Firecrawl CLI gives agents the complete web data toolkit for scraping, searching, and browsing. Try it now →
[ AGENT ]
[ .JSON ]
[ EXTRACT ]
[ DATA ]
In Research Preview - Try for free

Introducing Agent

Describe what data you want to extract
and /agent handles the rest.Read the docs →

[ 01 / 06 ]
·
How It Works
//
How It Works
//

From prompt to data

Whether you need one data point or entire datasets at scale. Firecrawl Agent just works.
Agent searching
LIVE
SOURCE
STATUS
ycombinator.com/companies
extracted
firecrawl.dev/agent
extracted
crunchbase.com/organization/firecrawl
extracted
github.com/firecrawl
extracted
producthunt.com/posts/firecrawl
extracted
Structured output
JSON
RESULT
{
"name": "Firecrawl",
"founders": ["Eric C.", "Nicolas C.", "Caleb P."],
"category": "Developer Tools",
"website": "https://firecrawl.dev"
}
247 records extracted
The evolution of /extract — URLs are now optional
Read docs
[ 02 / 06 ]
·
Use Cases
//
Use Cases
//

Built for any task

From lead generation to dataset curation, Agent finds data in hard to reach places.
Lead Gen

Get all YC W24 companies with founders

E-commerce

Get all Nike Air Jordan listings with prices

Market Data

Get market cap for top 50 tech stocks

Datasets

Build a dataset of all AI papers from arXiv

Real Estate

Get 3BR apartments in SF under $4k

Research

Extract all Michelin star restaurants in NYC

[ 03 / 06 ]
·
Get Started
//
Easy to integrate
//

Start using /agent today

Agent is available in the API, SDKs and MCPs for easy integration.
[ INPUT ]
from firecrawl import FirecrawlApp
from pydantic import BaseModel
from typing import List, Optional

app = FirecrawlApp(api_key ="fc-YOUR-API-KEY")

class Company(BaseModel):
    name: str
    founders: List[str]
    funding: Optional[str] = None
    website: str

class ExtractSchema(BaseModel):
    companies: List[Company]

result = app.agent(
    prompt ="Get all YC W24 companies",
    schema =ExtractSchema
)
[ .JSON ]
{
  "companies": [
    {
      "name": "Firecrawl",
      "founders": ["Eric C.", "Nicolas C.", "Caleb P."],
      "website": "https://firecrawl.dev",
      "category": "Developer Tools"
    },
    {
      "name": "Pylon", 
      "founders": ["Marty Kausas", "Advait Ruia"],
      "website": "https://usepylon.com",
      "category": "Customer Support"
    },
    {
      "name": "Mintlify",
      "founders": ["Han Wang", "Hahnbee Lee"],
      "website": "https://mintlify.com",
      "category": "Developer Tools"
    }
  ]
}
[ 04 / 06 ]
·
Pricing
//
Research Preview
//

Agent Pricing

Dynamic pricing based on query's complexity
5
free runs daily

Explore Agent's capabilities at no cost

Pricing during research preview is dynamic:

  • Simple queries use fewer credits
  • Complex queries use more credits
  • See credit usage in real-time in the agent panel
Try Agent free

Use maxCredits parameter to limit spending.

Model Pricing

Parallel Agents
Spark 1 Fast

Quick lookups available only in Parallel Agents

10credits / cell
Spark 1 Mini

Lightweight model, 60% cheaper

Dynamicbased on tokens
Most Accurate
Spark 1 Pro

High-performance model for complex tasks

Dynamicbased on tokens

Parallel Agents uses an intelligent waterfall: Spark 1 Fast attempts instant retrieval first, then automatically upgrades to Spark 1 Mini when full agent research is needed.

[ 05 / 06 ]
·
FAQ
//
FAQ
//

Frequently asked questions

Everything you need to know about Firecrawl Agent.
Agent
Pricing
Usage
FOOTER
The easiest way to extract
data from the web
Backed by
Y Combinator
LinkedinGithubYouTube
SOC II · Type 2
AICPA
SOC 2
X (Twitter)
Discord