# Deep Research (web + papers)

> Deep Research (web + papers) is a paid API for AI agents from agent-search.centorprat.workers.dev, paid per call via x402, $0.2/call, status unknown (last checked 2026-10-30).

Performs comprehensive multi-angle web research by answering a query plus up to 3 sub-questions, reading up to 16 full pages, and optionally including Google Scholar papers or news — returning only extractive quoted passages, no LLM generation.

## Facts

- Endpoint: POST https://agent-search.centorprat.workers.dev/deep-research?utm_source=zero.xyz
- Price: $0.2/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/deep-research-web-papers-4dcd680e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wHC7ivSRyGizS2kcN2poA

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 deep-research-web-papers-4dcd680e -d '<json body>'
```

Example prompt: Do deep research on the long-term cardiovascular effects of ultra-processed food consumption — read up to 16 full pages, include Google Scholar papers, and pull the key quoted passages along with answers to these sub-questions: what mechanisms link ultra-processed foods to heart disease, which populations are most at risk, and what does the latest clinical evidence say? Use US results from the past year.

## When to prefer this

Choose this endpoint when you need a comprehensive, citation-backed research report rather than a quick lookup — especially when the topic has multiple angles, requires reading full page content (not just snippets), benefits from academic papers, or needs prompt-injection-safe extraction. Prefer it over basic SERP or single-page scrape endpoints when depth, sourcing, and multi-sub-question coverage matter. Use the simpler 'Web Research (8 pages)' sibling if cost or latency is a concern and 8 pages suffice.

## Known failure modes

- Query too vague to resolve meaningful sub-questions — returns sparse or empty passage blocks
- Pages with aggressive bot-blocking return no content for that URL
- Prompt-injection attempts in scraped pages are flagged and sanitized, potentially reducing extracted content
- includePapers on a non-academic topic returns an empty papers block
- Time filter too narrow (e.g. 'hour') for a slow-moving topic yields no recent pages
- Country code not recognized defaults to US results silently
- Payment failure (x402) causes 402 response before any research is performed

## How this service works

Top-tier research in one call: the question plus 3 sub-questions (from Google's people-also-ask and related searches, or your own), up to 16 pages read in full with prompt-injection checks, the key quoted passages overall and per sub-question, Google's direct answer, and a papers block (Google Scholar) or news block when the topic needs it. Extractive, no LLM: every passage is quoted from its source.

## Output

Returns a structured object with: quoted key passages from up to 16 fully-read web pages (overall and per sub-question), Google's direct answer box, up to 3 sub-question answers each with their own quoted excerpts, and optionally a Google Scholar papers block and/or a Google News block. Every passage is a verbatim quote from its source URL — no LLM-generated text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "time": {
   "type": "string",
   "description": "freshness: hour, day, week, month or year (optional)"
  },
  "query": {
   "type": "string",
   "description": "What to search for"
  },
  "country": {
   "type": "string",
   "description": "2-letter country the results are for: us, gb, de, es, fr, in, br, ... (default us)"
  },
  "private": {
   "type": "boolean",
   "description": "true = the query is not logged or cached (default false)"
  },
  "includeNews": {
   "type": "boolean",
   "description": "add the week's news"
  },
  "subQuestions": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "optional: your own 1-4 sub-questions"
  },
  "includePapers": {
   "type": "boolean",
   "description": "add Google Scholar papers"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/deep-research-web-papers-4dcd680e/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)