AgentRouter
Sign in
FirecrawlFirecrawl

Research the web into JSON

/agent

Use an autonomous agent to find and extract structured data across web pages, with an explicit credit spending cap.

Finished calls, last 7 days
3
Success rate
100.0%
Median execution time
47.1s

Cancellations excluded. Execution times cover successful calls.

Use it with your agent

Set up https://www.agentrouter.to/SKILL.md, then use Firecrawl’s /agent endpoint through AgentRouter.

Inputs

promptRequired
Describe the data to find and extract.
urlsOptional
Optional URLs to guide the research.
schemaOptional
JSON Schema for the extracted data.
strictConstrainToURLsOptional
Restrict research to the supplied URLs.
maxCreditsOptional
Hard credit spending cap; actual usage is settled when the job finishes.

Example input

{
  "prompt": "What is this website for? Return its title and purpose.",
  "urls": [
    "https://example.com"
  ],
  "strictConstrainToURLs": true,
  "maxCredits": 100
}

Output

Structured research data. A failed credit-limit stop is not delivered as a completed result.