# Firecrawl Extract

> Firecrawl Extract is a paid API for AI agents from Firecrawl at firecrawl.mpp.tempo.xyz, paid per call via MPP, $0.005/call, status unknown (last checked 2026-10-12).

Extracts structured data from web pages using LLM-powered schema-driven extraction

## Facts

- Endpoint: POST https://firecrawl.mpp.tempo.xyz/v1/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Provider: Firecrawl
- Docs: https://docs.firecrawl.dev
- Website: https://firecrawl.dev
- Tags: scraping, crawling, extraction, llm, web, data
- Canonical page: https://www.zero.xyz/c/firecrawl-extract-38e26fef
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Uo0q1YSrH7FM4eo2a6yd2

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability firecrawl-extract-38e26fef -d '<json body>'
```

Example prompt: Extract the product name, price, availability, and customer rating from https://example.com/product/12345 and return them as structured JSON fields.

## When to prefer this

Use Firecrawl Extract when you need to pull specific structured fields from one or more web pages according to a defined schema, especially when the source is unstructured HTML. Prefer this over the Scrape endpoint when you want machine-readable structured output rather than raw markdown or HTML. Prefer this over Search when you already know the target URL. Best suited for product data, pricing, contact info, article metadata, or any web content where you need typed, schema-conformant JSON output.

## Known failure modes

- URL is inaccessible or returns a non-200 status — extraction fails with a fetch error
- Page content is dynamic/JavaScript-rendered and not fully captured — partial or empty fields returned
- Extraction schema fields don't match available page content — null or missing values in output
- Rate limiting or bot protection on target site blocks access — error response
- Malformed JSON schema input — validation error returned
- LLM extraction confidence is low for ambiguous content — fields may be inaccurate or hallucinated

## How this service works

Extract structured data

## Output

A structured JSON object containing the requested fields extracted from the target webpage, shaped to match the provided schema or prompt, powered by LLM parsing of the page content.

## Example request

```json
{
 "urls": [
  "https://example.com/product/sample"
 ],
 "schema": {
  "type": "object",
  "properties": {
   "name": {
    "type": "string"
   },
   "price": {
    "type": "number"
   },
   "description": {
    "type": "string"
   },
   "availability": {
    "type": "string"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/firecrawl-extract-38e26fef/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from firecrawl.mpp.tempo.xyz](https://www.zero.xyz/host/firecrawl.mpp.tempo.xyz/llms.txt)