agentutility(7)$ man ai-content-detector
/ai-content-detector
PRICE / CALL
$0.03
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
prooflayerCATEGORY
ai
STATUS
● live
NAME
ai-content-detector — detect ai-generated writing with a calibrated probability score
SYNOPSIS
POST https://x402.agentutility.ai/ai-content-detector
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
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.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| text | string | — | required |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| probability_ai_generated | number | Calibrated 0-1 probability that the submitted text was AI-generated. |
| verdict | string | Short label summarizing the call, like "likely_ai", "likely_human", or "uncertain". |
| confidence | number | 0-1 score for how strongly the per-axis signals agree on the verdict. |
| reasoning | array | Ordered list of human-readable reasons backing the verdict, citing which signals fired. |
| suspicious_phrases | array | Verbatim snippets from the input flagged as characteristic AI phrasing. |
| style_signals | object | Per-axis style scores: em-dash overuse, hedge phrases, formulaic transitions, and similar. |
| input_chars | number | Character count of the submitted text after normalization. |
| model | string | Identifier of the classifier model that produced the verdict. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/ai-content-detector \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# Install the MCP package for this endpoint's cluster npx -y @agentutility/mcp-<cluster> # Required: EVM private key with USDC on Base export X402_PRIVATE_KEY=0x... # Then call the ai-content-detector tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- ai-detectioncontentmoderationllmclassify
- env
- VENICE_API_KEY
- methods
- POST
- cluster
- prooflayer
- price
- $0.03 USDC per call
ADJACENT — other endpoints in prooflayer
| endpoint | description | price |
|---|---|---|
| dep-risk-summary | Scores dependency risk for a whole repo from its manifests and lockfiles. | $0.03 |
| github-repo-health | GitHub repo health score / open-source maintainability checker. | $0.03 |
| package-risk-npm | Scores supply-chain risk for an npm package before you install it. | $0.03 |
| prompt-injection-surface | Scans AI app source code for prompt injection risk at LLM call sites. | $0.03 |
| app-store-rejection-explain | Explains App Store and Google Play rejections and turns them into a resubmission plan. | $0.02 |
| db-migration-risk | Audits database migrations for risky SQL before deploy. | $0.02 |
| deploy-config-risk | Audits deploy configuration files for production risks. | $0.02 |
| secrets-exposure-check | Scans project config files for hardcoded secrets before you deploy. | $0.02 |
SEE ALSO