FIRE-1 Agent (Beta)

FIRE-1 is an AI agent that enhances Firecrawl’s scraping capabilities. It can controls browser actions and navigates complex website structures to enable comprehensive data extraction beyond traditional scraping methods.

​

What FIRE-1 Can Do:

• Plan and take actions to uncover data
• Interact with buttons, links, inputs, and dynamic elements.
• Get mulitple pages of data that require pagination, multiple steps, etc.

​

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. For /extract it will use the prompt provided in the prompt parameter on the body of the request so you can omit the above agent.prompt field.

​

Example Usage with Scrape Endpoint

Here’s a quick example using FIRE-1 with the scrape endpoint to get the companies on the consumer space from Y Combinator:

from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key="fc-YOUR_API_KEY")

# Scrape a website:
scrape_result = app.scrape_url('firecrawl.dev',
  formats=['markdown', 'html'],
  agent={
    'model': 'FIRE-1',
    'prompt': 'Navigate through the product listings by clicking the \'Next Page\' button until disabled. Scrape each page.'
  }
)

print(scrape_result)

In this scenario, FIRE-1 intelligently clicks the W22 button, the Consumer space button and scrapes the companies.

​

Using FIRE-1 with the Extract Endpoint

Similarly, you can leverage the FIRE-1 agent with the /v1/extract endpoint for complex extraction tasks that require navigation across multiple pages or interaction with elements.

Example:

from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key="fc-YOUR_API_KEY")

# Extract data from a website:
extract_result = app.extract(['firecrawl.dev'],
  prompt="Extract all user comments from this forum thread.",
  schema={
    "type": "object",
    "properties": {
      "comments": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "author": {"type": "string"},
            "comment_text": {"type": "string"}
          },
          "required": ["author", "comment_text"]
        }
      }
    },
    "required": ["comments"]
  },
  agent={
    "model": "FIRE-1"
  }
)

print(extract_result)

FIRE-1 is already live and available under preview.

​

Billing

• Why is FIRE-1 more expensive?
  FIRE-1 leverages advanced browser automation and AI planning to interact with complex web pages, which requires more compute resources than standard extraction.

Note: FIRE-1 is currently in preview. Pricing and limits may change. For the latest details on /extract costs, see our token calculator.

​

Rate limits

• /scrape: 10 requests per minute
• /extract: 10 requests per minute