Typed judgment

$0.001 per call · USDC via x402 · POST /v1/judge

Ask a typed question about any content and get an answer your code can branch on, not prose to parse. Send POST /v1/judge with the required fields state and questions and pay $0.001 per call over x402 or MPP (there is no free tier). It returns the result.

Send state (the content, a string or object) and questions (your own ids mapped to question objects); get back answers keyed by those ids. Three question types: choice (pick one of your named options: returns choice, probabilities per option and confidence), score (a position on levels you describe, lowest first: returns score as a fractional level index, probabilities per level index, confidence and a legend naming each level), and noul (a yes/no: returns noul, the probability of yes from 0 to 1). Up to 8 questions per call, answered in parallel over one piece of state. Use it for routing, triage, classification and gating decisions. Served by jev-latest with gpt-6-luna as fallback (name either first with model); the answer names the model that served, and fallbackFrom when the first was unavailable. Model-backed, not deterministic.

Category: AI & compute · Tags: ai classify judgment routing extraction

TRY IN PLAYGROUND →

Parameters

NameTypeRequiredDescription
statestring | object | arrayyesThe content to judge. Up to 8000 characters.
modelstring (one of: gpt-6-luna, jev-latest, jev-preview)noWhich model answers first; the other is the fallback. Defaults to jev-latest.
questionsobjectyesYour own ids mapped to question objects. Each has type (choice/score/noul), instructions, and criteria for choice/score.

Example request

curl -i -X POST https://agent402.tools/v1/judge \
  -H "Content-Type: application/json" \
  -d '{"state":"The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.","questions":{"severity":{"type":"score","instructions":"How severe is the reported issue?","criteria":["Cosmetic; no impact to functionality","Broken or degraded feature, but a workaround exists","Blocking issue; no workaround exists"]},"is_reproducible":{"type":"noul","instructions":"Does this report describe steps that would let an engineer reproduce the problem?"}}}'

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

Example response

{}

From an MCP client

catalog.call {
  "slug": "judge",
  "params": {
    "state": "The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.",
    "questions": {
      "severity": {
        "type": "score",
        "instructions": "How severe is the reported issue?",
        "criteria": [
          "Cosmetic; no impact to functionality",
          "Broken or degraded feature, but a workaround exists",
          "Blocking issue; no workaround exists"
        ]
      },
      "is_reproducible": {
        "type": "noul",
        "instructions": "Does this report describe steps that would let an engineer reproduce the problem?"
      }
    }
  }
}

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

Errors and behavior

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/judge", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "state": "The export button crashes the settings page in Safari. It works in Chrome, but a few of our customers only use Safari.",
    "questions": {
      "severity": {
        "type": "score",
        "instructions": "How severe is the reported issue?",
        "criteria": [
          "Cosmetic; no impact to functionality",
          "Broken or degraded feature, but a workaround exists",
          "Blocking issue; no workaround exists"
        ]
      },
      "is_reproducible": {
        "type": "noul",
        "instructions": "Does this report describe steps that would let an engineer reproduce the problem?"
      }
    }
  }),
});

Related tools

Decisions (OpenAI wire)

$0.001 · POST /v1/decisions

OpenAI's Decisions API on its own wire: point an OpenAI SDK's base URL here and client.decisions.create works unchanged,…

Image generation

$0.030 · POST /api/image-gen

Generate an image from a text prompt using GPT Image 2 (low quality, 1024x1024). No API key needed; pay per call via x40…

Image generation (HD)

$0.100 · POST /api/image-gen-hd

Generate a higher-quality image from a text prompt using GPT Image 2 (medium quality, 1024x1024). No API key needed; pay…

Image generation (Premium)

$0.150 · POST /api/image-gen-premium

Generate a larger image from a text prompt using GPT Image 2 (medium quality): 1536x1024 landscape by default, 1024x1536…

LLM inference

$0.010 · POST /api/llm

LLM inference proxy - send an OpenAI-format chat/completions request and get a response from GPT-4o-mini. Supports visio…

LLM inference (Premium)

$0.500 · POST /api/llm-premium

LLM inference proxy (Premium tier) - o3 or o3-mini reasoning models. Supports vision (up to 2 image URLs) and structured…