# AgentUtility AI Content Detector

> AgentUtility AI Content Detector is a paid API for AI agents from x402.agentutility.ai, paid per call via x402, $0.03/call, status healthy (last checked 2026-09-15, last successful call 2026-09-14).

Detects AI-generated writing and returns a 0-1 probability score, verdict, suspicious phrases, and per-axis style signals like em-dash overuse, hedge phrases, and formulaic transitions.

## Facts

- Endpoint: POST https://x402.agentutility.ai/ai-content-detector
- Price: $0.03/call
- Payment: x402
- Status: healthy
- Last checked: 2026-09-15
- Last successful call: 2026-09-14
- Success rate: 100% of calls made through Zero
- Rating: 2.0 / 5 from 1 review
- Activations on Zero: 3
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentutility-ai-content-detector-efe3907a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_b6ZVpmryatxVcVF9OE7mU

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 agentutility-ai-content-detector-efe3907a -d '<json body>'
```

Example prompt: Can you check if this article was written by AI? Here's the text: 'In today's rapidly evolving landscape, it is crucial to leverage synergies that drive meaningful outcomes — while ensuring that all stakeholders remain aligned with our core mission.' I want the probability score, a verdict, and any suspicious phrases flagged.

## When to prefer this

Choose this endpoint when you need granular, per-axis style signals alongside the detection score — not just a binary label. It is particularly useful when you need to surface specific suspicious phrases to show users why a verdict was reached, or when downstream logic depends on style breakdown (e.g. em-dash overuse, hedge phrase density). At $0.03 USDC per call with USDC settlement on Base, it suits agentic pipelines that need lightweight, per-document checks at scale without OAuth setup.

## Known failure modes

- Text too short to reliably score — may return low-confidence or error
- Non-English text may yield unreliable signals or unsupported language error
- Heavily edited AI text may receive lower-than-actual probability score
- Payment failure via x402 USDC results in 402 response blocking the call
- Very long texts may time out or require chunking

## How this service works

Detect AI-generated writing with a calibrated probability score. Returns a 0-1 likelihood, a verdict, suspicious phrases, and per-axis style signals (em-dash overuse, hedge phrases, formulaic transitions). Works as an AI content detector, GPT detector, or ChatGPT-text checker.

## Output

Returns a 0-1 probability score indicating likelihood of AI authorship, a binary or categorical verdict (AI-generated vs human-written), a list of suspicious phrases extracted from the text, and per-axis style signals including em-dash overuse, hedge phrase frequency, and formulaic transition patterns.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "verdict": "likely_ai",
  "confidence": 0.9,
  "probability_ai_generated": 0.85
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentutility-ai-content-detector-efe3907a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentutility.ai](https://www.zero.xyz/host/x402.agentutility.ai/llms.txt)