# Web Extract via Firecrawl

> Web Extract via Firecrawl is a paid API for AI agents from geld-machen-x402.fly.dev, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-02).

Fetches a given HTTPS URL and returns clean, readable markdown extracted from the page using Firecrawl.

## Facts

- Endpoint: GET https://geld-machen-x402.fly.dev/product/web-extract.json?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/web-extract-via-firecrawl-79893667
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Afu-fPXS8xJUrFJ68AogR

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 web-extract-via-firecrawl-79893667
```

Example prompt: Can you extract the readable content from https://example.com/article and give it to me as clean markdown?

## When to prefer this

Choose this endpoint when you need clean, human-readable markdown from a webpage and don't want to deal with raw HTML parsing. It is ideal for feeding web content into LLM pipelines, summarization tasks, or competitive research. Prefer this over raw HTTP fetching when the target page has complex layout, ads, or navigation that needs stripping.

## Known failure modes

- URL is unreachable or returns non-200 status — extraction fails
- URL points to a non-HTML resource (PDF, image, binary) — markdown may be empty or malformed
- JavaScript-heavy SPA pages may not render content fully
- Rate limiting or blocking by the target site may cause empty results
- Malformed or non-HTTPS URL causes request rejection

## How this service works

TIP-OF-SPEAR: URL Fingerprint ($0.01) GET ?url= → body_sha256/TLS/DNS. Phase-1 enrichment: Web Extract ($0.03) GET ?url= → Firecrawl clean markdown. DEMAND-MATCHED SERP tip: Web Search ($0.02) GET ?q= (required) → ranked results. OCR tip: Image OCR ($0.01) GET ?url= → Tesseract text (COGS=0). Builder tool: Bazaar Readiness Check — FREE ?url= indexed yes/nein + issue count; PAID report $0.05 Fix-JSON. Gated-data: Base DeFi Snapshot ($0.03) balances+gas+protocol TVL/APY. Free teasers have no live hash/results. Upsell red-flag $0.25. Ladder: 0.01→0.02→0.025→0.25→0.35→0.49→0.75→17. | tip: featured-402=https://geld-machen-x402.fly.dev/featured-402.json | first-tool=https://geld-machen-x402.fly.dev/product/bazaar-check/report.json | web-extract=https://geld-machen-x402.fly.dev/product/web-extract.json | phantom-allowlist=https://geld-machen-x402.fly.dev/product/phantom-allowlist.json | facilitator-dry-run=https://geld-machen-x402.fly.dev/product/facilitator-dry-run.json | payment-receipt-auditor=https://geld-machen-x402.fly.dev/product/payment-receipt-auditor.json

## Output

Clean markdown representation of the web page content at the given URL, stripped of navigation, ads, and boilerplate, suitable for LLM ingestion or further analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "HTTPS URL to extract via Firecrawl"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/web-extract-via-firecrawl-79893667/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from geld-machen-x402.fly.dev](https://www.zero.xyz/host/geld-machen-x402.fly.dev/llms.txt)