# Firecrawl Web Search with Content Retrieval

> Firecrawl Web Search with Content Retrieval is a paid API for AI agents from gateway.apiosk.com, paid per call via x402, $0.08/call, status unknown (last checked 2026-09-15).

Searches the web for a given query and optionally retrieves scraped, LLM-ready content for each result page.

## Facts

- Endpoint: POST https://gateway.apiosk.com/firecrawl/search
- Price: $0.08/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/firecrawl-web-search-with-content-retrieval-47b28b5e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1iXjFL8XqufiOTgUqF5c8

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-web-search-with-content-retrieval-47b28b5e -d '<json body>'
```

Example prompt: Search the web for 'best practices for LLM prompt engineering in 2024' and retrieve the full markdown content of the top 5 results so I can read them.

## When to prefer this

Choose this endpoint when you need both web search results AND the actual content of those pages in a single call, rather than making a search call followed by separate scrape calls. It is ideal for research agents that need to read and synthesize information from multiple web pages, and when you want LLM-ready markdown output rather than raw HTML. Prefer this over a standalone scrape endpoint when the URLs are not known in advance.

## Known failure modes

- Query returns no results for highly niche or misspelled terms
- Scraping individual result pages fails due to paywalls, bot protection, or dynamic JavaScript rendering
- Rate limits or timeouts on pages that take too long to load
- Payment failure via x402 protocol if wallet has insufficient USDC balance
- Malformed or empty response if the target pages block crawlers

## How this service works

Search the web and optionally retrieve scrape-ready content for each result.

## Output

A list of web search results, each containing the page URL, title, and snippet, with optionally scraped full-page content in markdown or other Firecrawl-supported formats ready for LLM consumption.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/firecrawl-web-search-with-content-retrieval-47b28b5e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gateway.apiosk.com](https://www.zero.xyz/host/gateway.apiosk.com/llms.txt)