Market Data · x402 · early usage

Estimate whether text (or a web page's text) is AI-written using a trained classifier:…

Estimate whether text (or a web page's text) is AI-written using a trained classifier: about 78% accurate on a held-out benchmark (not a guarantee). Uncertain results suggest a rerun on a longer section (300+ words); tell phrases are only a secondary 'possibl…

by grokzilla.shop · discovered, not yet claimed by its owner · updated 2026-10-13

30d calls9

30d payers4

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

Tags: ai-detection · ai-text · stylometry · content-check · text · bazaar

Call contract

Method: POST
Input: json
Output: json
Last paid call: 2026-10-13

Input example from Bazaar metadata

{
  "text": "So I finally fixed the porch light on Saturday. It's worth noting that I'd tried twice before and gave up (the wiring is ancient). Honestly the whole thing was a testament to stubbornness. My brother Sam held the ladder and complained the entire time, which didn't help one bit. In conclusion, the bulb works, the switch clicks, and I only shocked myself once! Next up is the doorbell, if I can find the manual. I can't, probably. It's in a box somewhere in the garage behind 3 bikes and a broken lawnmower."
}

Output example

{
  "ai_likelihood": 0.7822,
  "band": [
    0.5334,
    1
  ],
  "caveats": [
    "Detection is probabilistic and should not be used as the only evidence that a text was or was not written by a person.",
    "ai_likelihood is a stylometric score from 0 to 1, not a calibrated probability. The band widens when there is less text and is not a statistical confidence interval.",
    "A low score means these surface patterns are weak. It does not prove a person wrote the text.",
    "Weights were chosen on a small set of public-domain prose, poems, and synthetic assistant-style paragraphs. Fixture accuracy is not a field accuracy."
  ],
  "classifier": {
    "model_kind": "logistic_regression",
    "model_version": "2026-10-13",
    "probability_ai": 0.362,
    "threshold_ai": 0.585,
    "threshold_human": 0.3233,
    "verdict": "uncertain"
  },
  "content_type": "opinion",
  "method": "stylometry",
  "possible_ai_influence": true,
  "rubric_score": 0.4,
  "sections": [
    {
      "evidence": [
        "8 sentences, sentence-length CV 0.35 (AI <= 0.34, human >= 0.55)",
        "rhythm is in the overlap range where human and prompted-AI text both sit"
      ],
      "result": "no_signal",
      "section": "rhythm",
      "section_weight": 0.1
    },
    {
      "evidence": [
        "tell-phrase weight 2.4 (2.64 per 100 words, 138-entry list)",
        "tells: it's worth noting, a testament to, in conclusion",
        "lexical diversity MTLD 105 (informational, not scored)",
        "surprisal mean 3.21, variance 2.15, spike 0.40; rare-word share 0.033; MATTR 0.834; Zipf slope deviation 0.63",
        "tell phrases are dense; possible AI influence (secondary signal)"
      ],
      "result": "ai_sign",
      "section": "vocabulary",
      "section_weight": 0.4
    },
    {
      "evidence": [
        "ai cues: hedging (2 hedges)",
        "human cues: none",
        "first person, names, dialogue and sensory detail are not counted either way"
      ],
      "result": "no_signal",
      "section": "voice_structure",
      "section_weight": 0.3
    },
    {
      "evidence": [
        "rhythm vs vocabulary: no_overlap (no_signal / ai_sign)",
        "vocabulary vs voice_structure: no_overlap (ai_sign / no_signal)",
        "voice_structure vs rhythm: no_overlap (no_signal / no_signal)",
        "tell phrases present but not confirmed by two sections; secondary signal only"
      ],
      "result": "no_signal",
      "section": "resolution",
      "section_weight": 0.2
    }
  ],
  "signals": {
    "average_word_length": 4.3846,
    "burstiness": 0.3542,
    "contraction_rate": 3.2967,
    "hapax_ratio": 0.8841,
    "lexical_features_used": true,
    "line_count": 1,
    "line_length_uniformity": null,
    "punctuation_diversity": 4,
    "repeated_ngram_rate": 0,
    "sentence_count": 8,
    "sentence_length_mean": 11.375,
    "sentence_length_variance": 16.2344,
    "stock_phrase_hits": 3,
    "stock_phrase_per_100": 3.2967,
    "stock_phrases_found": [
      "it's worth noting",
      "a testament to",
      "in conclusion"
    ],
    "type_token_ratio": 0.7582,
    "verse_like": false
  },
  "skill": "ai_detector",
  "tell_phrases": [
    {
      "count": 1,
      "phrase": "it's worth noting",
      "tell_weight": 0.9
    },
    {
      "count": 1,
      "phrase": "a testament to",
      "tell_weight": 0.9
    },
    {
      "count": 1,
      "phrase": "in conclusion",
      "tell_weight": 0.6
    }
  ],
  "verdict": "possible_ai_influence",
  "word_count": 91
}

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/35087.json for the price and payment options.
Pay. Call GET https://grokzilla.shop/api/skills/ai-detector. 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: $0.01 / request
Protocol: x402 v2
Auth: No account or API key. Pay per request.
Networks: Base
Demand: 9 calls · 4 unique payers in 30d (public x402 Bazaar data)

x402 payment requirements

Scheme	Network	Asset	Amount	Pay to	Timeout
exact	Base eip155:8453	USDC	$0.01	0xc22f9CAEBAc37fE72D5142f35f21f6696Ea9Ef69	300s

accepts[] (raw JSON)

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xc22f9CAEBAc37fE72D5142f35f21f6696Ea9Ef69",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "10000",
    "amountUsd": 0.01,
    "maxTimeoutSeconds": 300
  }
]

Schemas

Output schema (JSON Schema)

{
  "properties": {
    "example": {
      "properties": {
        "ai_likelihood": {
          "type": "number"
        },
        "band": {
          "items": {
            "type": "number"
          },
          "type": "array"
        },
        "caveats": {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "classifier": {
          "properties": {
            "model_kind": {
              "type": "string"
            },
            "model_version": {
              "type": "string"
            },
            "probability_ai": {
              "type": "number"
            },
            "threshold_ai": {
              "type": "number"
            },
            "threshold_human": {
              "type": "number"
            },
            "verdict": {
              "type": "string"
            }
          },
          "type": "object"
        },
        "content_type": {
          "type": "string"
        },
        "method": {
          "type": "string"
        },
        "possible_ai_influence": {
          "type": "boolean"
        },
        "rubric_score": {
          "type": "number"
        },
        "sections": {
          "items": {
            "properties": {
              "evidence": {
                "type": "array"
              },
              "result": {
                "type": "string"
              },
              "section": {
                "type": "string"
              },
              "section_weight": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "type": "array"
        },
        "signals": {
          "properties": {
            "average_word_length": {
              "type": "number"
            },
            "burstiness": {
              "type": "number"
            },
            "contraction_rate": {
              "type": "number"
            },
            "hapax_ratio": {
              "type": "number"
            },
            "lexical_features_used": {
              "type": "boolean"
            },
            "line_count": {
              "type": "integer"
            },
            "line_length_uniformity": {
              "type": "null"
            },
            "punctuation_diversity": {
              "type": "integer"
            },
            "repeated_ngram_rate": {
              "type": "number"
            },
            "sentence_count": {
              "type": "integer"
            },
            "sentence_length_mean": {
              "type": "number"
            },
            "sentence_length_variance": {
              "type": "number"
            },
            "stock_phrase_hits": {
              "type": "integer"
            },
            "stock_phrase_per_100": {
              "type": "number"
            },
            "stock_phrases_found": {
              "items": {
                "type": "string"
              },
              "type": "array"
            },
            "type_token_ratio": {
              "type": "number"
            },
            "verse_like": {
              "type": "boolean"
            }
          },
          "type": "object"
        },
        "skill": {
          "type": "string"
        },
        "tell_phrases": {
          "items": {
            "properties": {
              "count": {
                "type": "integer"
              },
              "phrase": {
                "type": "string"
              },
              "tell_weight": {
                "type": "number"
              }
            },
            "type": "object"
          },
          "type": "array"
        },
        "verdict": {
          "type": "string"
        },
        "word_count": {
          "type": "integer"
        }
      },
      "required": [
        "skill"
      ],
      "type": "object"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "type": "object"
}

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

{
  "example": {
    "ai_likelihood": 0,
    "band": [
      0
    ],
    "caveats": [
      "string"
    ],
    "classifier": {
      "model_kind": "string",
      "model_version": "string",
      "probability_ai": 0,
      "threshold_ai": 0,
      "threshold_human": 0,
      "verdict": "string"
    },
    "content_type": "string",
    "method": "string",
    "possible_ai_influence": true,
    "rubric_score": 0,
    "sections": [
      {
        "evidence": [
          "value"
        ],
        "result": "string",
        "section": "string",
        "section_weight": 0
      }
    ],
    "signals": {
      "average_word_length": 0,
      "burstiness": 0,
      "contraction_rate": 0,
      "hapax_ratio": 0,
      "lexical_features_used": true,
      "line_count": 0,
      "line_length_uniformity": null,
      "punctuation_diversity": 0,
      "repeated_ngram_rate": 0,
      "sentence_count": 0,
      "sentence_length_mean": 0,
      "sentence_length_variance": 0,
      "stock_phrase_hits": 0,
      "stock_phrase_per_100": 0,
      "stock_phrases_found": [
        "string"
      ],
      "type_token_ratio": 0,
      "verse_like": true
    },
    "skill": "string",
    "tell_phrases": [
      {
        "count": 0,
        "phrase": "string",
        "tell_weight": 0
      }
    ],
    "verdict": "string",
    "word_count": 0
  },
  "type": "string"
}

Examples

curl

curl "https://grokzilla.shop/api/skills/ai-detector"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

JavaScript

const res = await fetch("https://grokzilla.shop/api/skills/ai-detector");
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://grokzilla.shop/api/skills/ai-detector")
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: grokzilla.shop
Endpoint: https://grokzilla.shop/api/skills/ai-detector
Machine-readable: /resources/35087.json