AI Inference · x402 · early usage

Jev-powered research: routed search, cited answer, claims verified against sources

by x402.agentindex.world · discovered, not yet claimed by its owner · updated 2026-10-08

30d calls3

30d payers3

MethodPOST

Outputjson

Mirrored from Coinbase's public x402 Bazaar. The description is the provider's own text and has not been reviewed here; the payment requirements are copied as published.

What it does

Jev-powered research: routed search, cited answer, claims verified against sources. Ask a question, get a 5-8 sentence answer, each claim tagged to a numbered source, built from real page content - no invented facts. A fast paid LLM writes it, under 4.5s guaranteed; on a rare miss, a no-LLM extractive fallback (top sentences from the sources, picked by Jev) takes over instead, marked "synthesis":"extractive". Try GET /research/sample.

Tags: research report with sources · cited answer · web research · bazaar

Call contract

Method: POST
Input: json
Output: json
Last paid call: 2026-10-08

Input example from Bazaar metadata

{
  "query": "What are the main features of the Rust programming language?"
}

Output example

{
  "answer": "The main features of the Rust programming language include an emphasis on performance, type safety, concurrency, and memory safety [1]. Rust supports multiple programming paradigms [1]. The language's syntax is heavily influenced by C++ and functional programming languages such as OCaml [2]. Rust has a focus on static typing and a borrow system, similar to other systems programming languages [5]. However, sources [3] and [4] do not provide information about Rust, instead discussing other programming languages, Zig and V, respectively. Overall, the sources suggest that Rust is a systems programming language with a strong focus on safety and performance [1][2][5].",
  "claims_verified": true,
  "claims_verified_reason": null,
  "query": "What are the main features of the Rust programming language?",
  "sources": [
    {
      "published_at": null,
      "source": "wikipedia",
      "title": "Rust (programming language)",
      "url": "https://en.wikipedia.org/wiki/Rust_(programming_language)"
    },
    {
      "published_at": null,
      "source": "wikipedia",
      "title": "Rust syntax",
      "url": "https://en.wikipedia.org/wiki/Rust_syntax"
    },
    {
      "published_at": null,
      "source": "wikipedia",
      "title": "Zig (programming language)",
      "url": "https://en.wikipedia.org/wiki/Zig_(programming_language)"
    },
    {
      "published_at": null,
      "source": "wikipedia",
      "title": "V (programming language)",
      "url": "https://en.wikipedia.org/wiki/V_(programming_language)"
    },
    {
      "published_at": null,
      "source": "wikipedia",
      "title": "Mojo (programming language)",
      "url": "https://en.wikipedia.org/wiki/Mojo_(programming_language)"
    }
  ],
  "synthesis": "llm",
  "timing_ms": {
    "search": 1230,
    "synthesis": 644,
    "total": 2160,
    "verify": 287
  }
}

Use with an agent

Discover. Agents find this listing with GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP tool search_resources, or /discovery/resources.
Inspect. Fetch /resources/33819.json for the price and payment options.
Pay. Call GET https://x402.agentindex.world/research. The provider answers 402 with its payment requirements. An x402 client signs one of the options below and retries with PAYMENT-SIGNATURE.
Execute. The provider returns 200 with the data. Agent Bazaar is not in the request path and never sees your payment.

For humans

You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.

Pricing & payment

Price: $0.005 / request
Protocol: x402 v2
Auth: No account or API key. Pay per request.
Networks: Base
Demand: 3 calls · 3 unique payers in 30d (public x402 Bazaar data)

x402 payment requirements

Scheme	Network	Asset	Amount	Pay to	Timeout
exact	Base eip155:8453	USDC	$0.005	0xb3F32bdfe8D07825BC0D7387295aB1D7559BA69d	300s

accepts[] (raw JSON)

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xb3F32bdfe8D07825BC0D7387295aB1D7559BA69d",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "5000",
    "amountUsd": 0.005,
    "maxTimeoutSeconds": 300
  }
]

Schemas

Output schema (JSON Schema)

{
  "properties": {
    "example": {
      "properties": {
        "answer": {
          "description": "5-8 sentences, each claim cited inline as [n] referring to the sources array (1-indexed).",
          "type": "string"
        },
        "claims_verified": {
          "description": "True only if a Jev check confirmed the answer's citations are supported. False if unsupported OR if verification was skipped/timed out - see claims_verified_reason.",
          "type": "boolean"
        },
        "claims_verified_reason": {
          "description": "Why claims_verified is false: 'jev_found_unsupported_claim', 'verification_timed_out_or_failed', 'insufficient_time_budget_remaining', or null when verified true.",
          "type": [
            "string",
            "null"
          ]
        },
        "query": {
          "type": "string"
        },
        "sources": {
          "items": {
            "properties": {
              "published_at": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "source": {
                "type": "string"
              },
              "title": {
                "type": "string"
              },
              "url": {
                "type": "string"
              }
            },
            "type": "object"
          },
          "type": "array"
        },
        "synthesis": {
          "description": "'llm' when a paid fast model wrote the answer (the common case). 'extractive' when that model missed its own tight time cap and the answer is instead the most relevant sentences already present in the sources, verbatim, picked by Jev - never a second LLM call.",
          "enum": [
            "llm",
            "extractive"
          ],
          "type": "string"
        },
        "timing_ms": {
          "description": "search, synthesis, verify, total, in milliseconds.",
          "type": "object"
        },
        "x402_receipt": {
          "description": "Billing and provenance receipt for this call.",
          "type": "object"
        }
      },
      "required": [
        "query",
        "answer",
        "synthesis",
        "sources",
        "claims_verified",
        "timing_ms"
      ],
      "type": "object"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "type": "object"
}

Example shape — generated from the schema, not a captured live response

{
  "example": {
    "answer": "string",
    "claims_verified": true,
    "claims_verified_reason": "string",
    "query": "string",
    "sources": [
      {
        "published_at": "string",
        "source": "string",
        "title": "string",
        "url": "string"
      }
    ],
    "synthesis": "llm",
    "timing_ms": {},
    "x402_receipt": {}
  },
  "type": "string"
}

Examples

curl

curl "https://x402.agentindex.world/research"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

JavaScript

const res = await fetch("https://x402.agentindex.world/research");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

Python

import httpx
res = httpx.get("https://x402.agentindex.world/research")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Details

Provider: x402.agentindex.world
Endpoint: https://x402.agentindex.world/research
Machine-readable: /resources/33819.json