# paid-md Research Brief

> paid-md Research Brief is a paid API for AI agents from paid-md.hihat.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-27).

Crawls up to 8 URLs and synthesizes a cited, multi-source research brief as structured JSON in response to a question or instruction

## Facts

- Endpoint: POST https://paid-md.hihat.workers.dev/research?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-27
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/paid-md-research-brief-5959fa5b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AuEFnQEsYveBYbUO7yUHg

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 paid-md-research-brief-5959fa5b -d '<json body>'
```

Example prompt: Can you research the pricing and features of the top 5 project management tools by crawling their websites — start at https://www.notion.so and follow up to 6 linked pages — and give me a synthesized comparison with cited sources?

## When to prefer this

Choose this endpoint when you need to synthesize information from multiple web pages into a single coherent answer with cited sources — especially when a question spans several documents, pages link to each other, or you want to compare content across a site. It is superior to single-page scrapers when multi-document aggregation is needed, and far more token-efficient than reading raw HTML yourself. Use when you have a seed URL to crawl or an explicit list of up to 8 URLs.

## Known failure modes

- Seed URL is unreachable or returns non-200 response
- Linked pages are behind authentication or paywalls, limiting crawl depth
- Requested depth exceeds maximum of 8 pages
- Malformed or conflicting JSON schema causes structured output to fail
- Pages contain insufficient content to answer the question
- Rate limiting or bot detection on target sites blocks fetching
- Payment of $0.05 USDC not completed, request rejected via x402

## How this service works

Multi-page research brief with cited sources. Crawl one URL and follow its links, or pass a list of URLs, and get a synthesized answer to your question as JSON with a sources array, optionally shaped by your JSON Schema. Use it to compare several pages, gather a list across a site, summarise a topic from multiple sources, or answer a question that spans documents. Up to 8 pages per call, typically 99% fewer tokens than reading the pages yourself.

## Output

A JSON object containing a synthesized, cited answer to the research question or instruction, including a 'sources' array listing the URLs used. The response can be shaped into a custom structure if a JSON Schema is provided. Typically uses 99% fewer tokens than reading the raw pages directly.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Seed url; links on the page are followed."
  },
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Explicit list instead of a seed. No crawl, fetched in parallel."
  },
  "depth": {
   "type": "integer",
   "maximum": 8,
   "minimum": 1,
   "description": "How many pages to use. Defaults to 5 for a seed, 8 for an explicit list."
  },
  "schema": {
   "type": "object"
  },
  "instructions": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/paid-md-research-brief-5959fa5b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from paid-md.hihat.workers.dev](https://www.zero.xyz/host/paid-md.hihat.workers.dev/llms.txt)