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 multiple pages of data that require pagination, multiple steps, etc.

How to use FIRE-1

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)

Billing

The cost of using FIRE-1 is non-deterministic. See our credit calculator to learn about the base cost of each Extract request.

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.

Rate limits

• /extract: 10 requests per minute