# Verdict L402 - Content Moderation

> Verdict L402 - Content Moderation is a paid API for AI agents from verdict.kechlab.com, paid per call via x402, $0.0092/call, status unknown (last checked 2026-10-21).

Performs semantic content moderation across categories including profanity, harassment, hate speech, sexual content, threats, self-harm, and scams, returning per-category scores and an allow/review/block decision.

## Facts

- Endpoint: POST https://verdict.kechlab.com/v1/moderate?utm_source=zero.xyz
- Price: $0.0092/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verdict-l402-content-moderation-ff8fce77
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4P17YtkaZdLyI1aFWjUet

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 verdict-l402-content-moderation-ff8fce77 -d '<json body>'
```

Example prompt: Check this user comment for hate speech, harassment, scams, and sexual content — tell me if it should be allowed, flagged for review, or blocked, and give me a score for each category: 'You're a worthless idiot, click here to claim your prize money'

## When to prefer this

Prefer this endpoint when you need semantic, context-aware moderation rather than simple keyword matching — especially for disguised, obfuscated, or multilingual offensive content. It is ideal when you need fine-grained per-category scores and a three-tier decision (allow/review/block) rather than a binary pass/fail. Choose it when you need to tolerate certain categories (e.g. mild profanity on an adult platform) via the ignore list.

## Known failure modes

- Empty or missing text field returns a validation error
- Unrecognized category names in the ignore list may be silently ignored or return an error
- Very short or ambiguous text may produce low-confidence scores across all categories
- Non-text content (binary, structured data) is not supported
- Rate limits or payment failures may block the request with an HTTP 402 or 429 response

## How this service works

Semantic content moderation, not a word list: profanity (even disguised, any language), harassment, hate, sexual content, threats, self-harm, scams. Per-category scores, allow/review/block, configurable ignore list.

## Output

Returns per-category risk scores (profanity, harassment, hate, sexual, violence, self_harm, spam_scam) and an overall moderation decision of allow, review, or block. Semantic detection catches disguised or obfuscated language across multiple languages without relying on word lists.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "the text to moderate"
  },
  "ignore": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "(optional) categories to tolerate: profanity, harassment, hate, sexual, violence, self_harm, spam_scam"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verdict-l402-content-moderation-ff8fce77/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verdict.kechlab.com](https://www.zero.xyz/host/verdict.kechlab.com/llms.txt)