# Ysaere Agent Search + Extract

> Ysaere Agent Search + Extract is a paid API for AI agents from api.ysaere.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-11-20).

Runs a web search, fetches the top 1–5 public pages, and returns clean text excerpts with cited URLs and content hashes — refusing payment if no page can be read

## Facts

- Endpoint: POST https://api.ysaere.com/v1/intel/search-and-extract?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ysaere-agent-search-extract-b35b1b76
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_R8D77chjfPot1SgiYwPt9

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 ysaere-agent-search-extract-b35b1b76 -d '<json body>'
```

Example prompt: Search the web for 'NIST SP 800-171 rev 3 changes' and pull clean text excerpts from the top 3 pages, with URLs and content hashes cited.

## When to prefer this

Choose this endpoint when you need both a live web search AND clean text extraction from the results in a single call — particularly useful for research on regulatory documents, technical specifications, or recent events where you need cited, verifiable excerpts. Prefer it over a plain search API when you need the actual page content (not just titles/snippets), and over a single-URL extractor when you don't yet know which pages to read. The built-in content hashing makes it suitable for compliance or audit workflows where provenance matters.

## Known failure modes

- No readable pages found — call refused before payment is charged
- Search query too short (<2 chars) or too long (>400 chars) — validation error
- limit out of range (must be 1–5) — validation error
- max_chars out of range (must be 200–8000) — validation error
- Target pages behind authentication or paywalls may not be extractable
- Network timeout fetching one or more target pages — partial results or refusal

## How this service works

Ysaere Agent Search + Extract — $0.05 USDC, no account needed. Input: {"query":"NIST SP 800-171 rev 3 changes","limit"?:3,"max_chars"?:2000}. Runs a web search, reads the top 1–5 public pages, and returns clean text excerpts with each URL cited and a v2:sha512: content_hash per page, in this response. If no page can be read, the call is refused before payment. Wallet only. No account price.

## Output

Returns clean text excerpts from 1–5 fetched web pages, each paired with its source URL and a v2:sha512 content hash for integrity verification. If no page can be successfully read before payment is processed, the call is refused entirely.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "number",
   "maximum": 5,
   "minimum": 1,
   "description": "Pages to read (default 3, max 5)"
  },
  "query": {
   "type": "string",
   "maxLength": 400,
   "minLength": 2,
   "description": "Search query (2–400 chars)"
  },
  "stamp": {
   "type": "boolean",
   "description": "Optional. true adds a signed Notary receipt over output_sha512 (+$0.02 USDC). Integrity, not factual truth."
  },
  "max_chars": {
   "type": "number",
   "maximum": 8000,
   "minimum": 200,
   "description": "Excerpt length per page (default 2000)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ysaere-agent-search-extract-b35b1b76/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.ysaere.com](https://www.zero.xyz/host/api.ysaere.com/llms.txt)
