# humanverify-create

> humanverify-create is a paid API for AI agents from api.agentstools.dev, paid per call via x402, $0.2/call, status unknown (last checked 2026-09-14).

Submit a subjective or culturally-nuanced question to a human judgement panel and receive a ticket for polling the asynchronous verdict

## Facts

- Endpoint: GET https://api.agentstools.dev/humanverify/create
- Price: $0.2/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/humanverify-create-bf56fef7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HQBLce7bMkmblvUoDIeI9

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 humanverify-create-bf56fef7
```

Example prompt: Can you send this Japanese product name '柔らかな光' to a panel of 5 human raters and ask them 'Does this product name feel natural to a native Japanese speaker?' with the labels 'natural,awkward,wrong' and a $0.05 reward per answer?

## When to prefer this

Choose this endpoint when you need genuine human judgement on subjective, culturally-nuanced, or ambiguous content that an LLM alone cannot reliably assess — such as naturalness of translated text, cultural resonance of brand names, or tone perception. Prefer it over LLM self-evaluation when ground truth requires lived human experience, or when you need a calibrated confidence score based on inter-rater agreement. Not suitable for factual lookups, captchas, or professional advice.

## Known failure modes

- Question flagged as engagement/astroturf task — rejected with 400
- CAPTCHA or PII-related question — rejected outright
- Professional-advice question (legal, medical) — rejected
- Reward value outside 0.02–0.05 range — clamped or error
- Responses count exceeds max of 5 — rejected
- Payment failure via x402 — 402 response before ticket is issued
- Polling ticket before humans have responded — empty or partial result

## How this service works

Get a HUMAN judgement on a subjective/culturally-nuanced question: we post the task to an account-free human rail, collect several answers, and return one typed verdict with an honest confidence (agreement × sample completeness). This create route returns a ticket immediately; poll the free result route for the verdict (human answers arrive asynchronously). Only judgement tasks are accepted — engagement/astroturf, captcha, PII and professional-advice tasks are rejected.

## Output

Returns immediately with a ticket ID. When polled, delivers a typed verdict (categorical majority label or free-text consensus), an honest confidence score computed as agreement rate times sample completeness, and the number of responses collected.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "question"
     ],
     "properties": {
      "labels": {
       "type": "string",
       "description": "Optional CSV of allowed answer labels (e.g. 'natural,awkward,wrong'). If given, the verdict is a categorical majority vote; omit for a free-text consensus."
      },
      "reward": {
       "type": "number",
       "description": "USD paid to each human answer. Default 0.03, clamped 0.02–0.05 (higher = faster fill). Our WURK cost is exactly responses×reward."
      },
      "context": {
       "type": "string",
       "description": "Optional extra context shown to the human worker."
      },
      "question": {
       "type": "string",
       "description": "The judgement question for a human to answer (e.g. 'Is this Japanese product name natural to a native speaker?')."
      },
      "responses": {
       "type": "integer",
       "description": "How many human answers to collect (target N). Default 3, max 5."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/humanverify-create-bf56fef7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentstools.dev](https://www.zero.xyz/host/api.agentstools.dev/llms.txt)