# Agent402 Research Max - Deep AI Research Report

> Agent402 Research Max - Deep AI Research Report is a paid API for AI agents from agent402.tools, paid per call via x402, $1.1/call, status unknown (last checked 2026-09-14).

Runs a multi-search deep research query and returns a fully synthesized markdown or JSON report with cited sources, powered by Claude Opus.

## Facts

- Endpoint: POST https://agent402.tools/v1/research/max
- Price: $1.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent402-research-max-deep-ai-research-report-68471c63
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UMm8APQsEPAQpf9BESNsO

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 agent402-research-max-deep-ai-research-report-68471c63 -d '<json body>'
```

Example prompt: Can you do a deep research report on the current state of agentic payment protocols — focus on x402 and stablecoin rails, prefer sources from the past month, and give me the output as a markdown report?

## When to prefer this

Choose this endpoint when you need a comprehensive, multi-source synthesized research report rather than a single web search result or lookup. It is ideal for complex, open-ended research questions that benefit from sub-question decomposition, source ranking, and AI synthesis into a coherent narrative. Prefer it over simple search endpoints when citation quality and report completeness matter, or when the question spans multiple domains. The recency filter makes it particularly useful for fast-moving topics where you want only recent sources.

## Known failure modes

- Query exceeds 2000 characters — request rejected with validation error
- Invalid format enum value — defaults to markdown or returns error
- Invalid recency enum value — returns validation error
- Payment failure — x402 micropayment not completed, request not processed
- Rate limiting or model unavailability from upstream Anthropic API — returns 5xx
- No high-quality sources found for obscure queries — report may be sparse or cite fewer sources than expected
- Network timeout on multi-search orchestration — partial results or timeout error

## How this service works

The exhaustive tier: up to a dozen sub-questions and grounded searches, the widest reranked source set, premium synthesis into a ~2,800-word cited report with a full source table. Our most thorough single-call research report. USDC or card (Stripe). Not cached.

## Output

A structured JSON object containing: a synthesized markdown or JSON report with numbered inline citations, an array of ranked sources (URL, title, snippet, relevance score), a list of sub-questions the system decomposed the query into, and metadata including number of searches run, sources consulted, sources cited, and the synthesis model used (Claude Opus).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "focus": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Optional aspects to emphasize (<= 8)."
  },
  "query": {
   "type": "string",
   "description": "The research question to investigate (<= 2000 chars)."
  },
  "format": {
   "enum": [
    "markdown",
    "json"
   ],
   "type": "string",
   "description": "Response shape (default markdown report)."
  },
  "recency": {
   "enum": [
    "week",
    "month",
    "year",
    "any"
   ],
   "type": "string",
   "description": "Prefer sources from this window (default any)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "meta": {
   "tier": "research-max",
   "searches_run": 3,
   "sources_cited": 12,
   "synthesis_model": "anthropic/claude-opus-5",
   "sources_consulted": 14
  },
  "report": "# Leading agentic-payment protocols (2026)\n\nThe field splits into stablecoin rails and card rails [1]…\n\n## Sources\n[1] … - https://…",
  "sources": [
   {
    "n": 1,
    "url": "https://…",
    "rank": 0.94,
    "title": "…",
    "snippet": "…"
   }
  ],
  "sub_questions": [
   "What stablecoin agent-payment protocols exist?",
   "…"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent402-research-max-deep-ai-research-report-68471c63/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent402.tools](https://www.zero.xyz/host/agent402.tools/llms.txt)