# Inference402 Content Moderation

> Inference402 Content Moderation is a paid API for AI agents from inference402.worlddata402.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-19).

Checks a text input for harmful or unsafe content using Llama Guard 3 8B, returning a verdict and flagged categories

## Facts

- Endpoint: GET https://inference402.worlddata402.workers.dev/v1/moderate?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/inference402-content-moderation-cbc12e54
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ln7BFn12ykMPxsYif1-rE

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 inference402-content-moderation-cbc12e54
```

Example prompt: Can you check if this user-submitted comment is safe to publish: 'I want to find you and make you pay for what you did'? Run it through content moderation and tell me if it's safe or what categories it violates.

## When to prefer this

Choose this endpoint when you need fast, no-account, pay-per-call content moderation powered by a dedicated safety-tuned model (Llama Guard 3 8B) and you want to pay in USDC on Base without managing API keys or subscriptions. Prefer this over general-purpose LLM-based moderation when you want an explicit safe/unsafe verdict with category labels rather than a free-text judgment, or when your agent stack already uses x402 micropayments for other inference calls on this platform.

## Known failure modes

- Text exceeds 6000 character limit — request rejected or truncated
- Payment not provided or insufficient USDC — 402 Payment Required response
- Network timeout on Cloudflare Worker edge — transient 5xx error
- Empty or missing 'text' parameter — likely returns error or unexpected result
- Edge case: borderline content may be inconsistently classified near decision boundaries

## How this service works

Pay-per-call AI inference for agents: chat (Llama 3.3 70B / 3.1 8B), structured JSON, summarize, translate (incl. Egyptian Arabic), extract, classify, sentiment, keywords, rewrite, embeddings, moderation, vision and speech-to-text. USDC on Base mainnet over x402. No API key, no account.

## Output

Returns a JSON object with the model used ('model': '@cf/meta/llama-guard-3-8b'), a 'verdict' field ('safe' or 'unsafe'), and a 'categories' array listing any violated safety categories (e.g. hate speech, violence, sexual content) if the content is flagged.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 6000
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/meta/llama-guard-3-8b",
  "verdict": "safe",
  "categories": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/inference402-content-moderation-cbc12e54/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from inference402.worlddata402.workers.dev](https://www.zero.xyz/host/inference402.worlddata402.workers.dev/llms.txt)