Deep research report - MAX (exhaustive)

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. Send POST /v1/research/max with the required field query and pay $1.10 per call over x402 with USDC on an EVM chain. It returns a JSON object with report, sources, sub_questions and meta.

Our most thorough single-call research report. USDC or card (Stripe). Not cached.

Category: LLM gateway · Tags: llm research web-search grounded citations deep-research agent premium

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/v1/research/max \
  -H "Content-Type: application/json" \
  -d '{"query":"What are the leading agentic-payment protocols in 2026 and how do they differ?","recency":"year"}'

Without payment this returns HTTP 402 Payment Required with the exact price for research-max; any x402 v2 or MPP client pays it and retries.

Example response

{
  "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,
      "title": "…",
      "url": "https://…",
      "snippet": "…",
      "rank": 0.94
    }
  ],
  "sub_questions": [
    "What stablecoin agent-payment protocols exist?",
    "…"
  ],
  "meta": {
    "tier": "research-max",
    "searches_run": 3,
    "sources_consulted": 14,
    "sources_cited": 12,
    "synthesis_model": "anthropic/claude-opus-5"
  }
}

From an MCP client

catalog.call {
  "slug": "research-max",
  "params": {
    "query": "What are the leading agentic-payment protocols in 2026 and how do they differ?",
    "recency": "year"
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for research-max; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• query is required. An input the tool rejects returns an HTTP 4xx whose body carries error, tool, expected, required and example, so the caller can correct it.
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails.
• Wallet-only: this tool runs a model, so it has no proof-of-work tier. A prepaid card-credits key (Authorization: Bearer a402_...) also pays it.
• Model-backed: the answer is generated by a model, so the same input can produce different wording.
• Long-running: payment settles after the work finishes, so only EVM exact payments are offered.
• A GET or HEAD to /v1/research/max returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB and a streamed response are not replayed).

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/v1/research/max", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "query": "What are the leading agentic-payment protocols in 2026 and how do they differ?",
    "recency": "year"
  }),
});

Related tools