# Exa-Compatible Page Contents

> Exa-Compatible Page Contents is a paid API for AI agents from agent-search.centorprat.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-30).

Fetches full text and highlights from up to 10 URLs in Exa /contents-compatible format, returning clean markdown with prompt-injection detection

## Facts

- Endpoint: POST https://agent-search.centorprat.workers.dev/exa/contents?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/exa-compatible-page-contents-729bea99
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_S28_tfmkSDt7WCyTIRyfU

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 exa-compatible-page-contents-729bea99 -d '<json body>'
```

Example prompt: Fetch the full text and highlighted excerpts from these 3 URLs — https://example.com/article1, https://example.com/article2, https://example.com/article3 — and return the content as clean markdown, flagging any prompt-injection attempts.

## When to prefer this

Choose this endpoint when you need to fetch and read page contents from multiple URLs at once using Exa-compatible request/response format, especially if you're already integrated with Exa's /contents API and want a drop-in alternative at lower cost ($0.004 for up to 10 URLs). Prefer it when you also need prompt-injection safety verdicts on retrieved content, or when you need clean markdown output rather than raw HTML. If you only need a single URL scraped in Firecrawl format, use the sibling Firecrawl-compatible scrape endpoint instead.

## Known failure modes

- URL unreachable or returns non-200 status — per-URL error status returned
- More than 10 URLs submitted — request rejected
- Paywalled or bot-blocked page — partial or empty text returned
- URL returns non-HTML content (PDF, binary) — may return empty or degraded text
- Prompt-injection detected in page content — flagged in verdict but content still returned

## How this service works

Drop-in Exa-compatible contents: send urls (or ids) and text / highlights options exactly as for Exa /contents and get results with id, url, title, author, publishedDate, text and highlights plus per-URL statuses, as clean markdown with a prompt-injection verdict. Up to 10 URLs for $0.004. Not affiliated with Exa.

## Output

Returns a list of results per URL, each containing: id, url, title, author, publishedDate, full page text as clean markdown, extracted highlights, and a prompt-injection verdict. Also includes per-URL status codes indicating success or failure for each requested page.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": [
    "boolean",
    "object"
   ],
   "description": "true or {maxCharacters}"
  },
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "1-10 URLs (or ids)"
  },
  "highlights": {
   "type": [
    "boolean",
    "object"
   ],
   "description": "true or {query}"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/exa-compatible-page-contents-729bea99/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-search.centorprat.workers.dev](https://www.zero.xyz/host/agent-search.centorprat.workers.dev/llms.txt)