# GEDX402 Content Guard (media.gedx402.com)

> GEDX402 Content Guard (media.gedx402.com) is a paid API for AI agents from media.gedx402.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Runs AI-powered content moderation on a conversation, returning a safety verdict and flagged categories, paid per-call with USDC via x402.

## Facts

- Endpoint: GET https://media.gedx402.com/v1/guard
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-content-guard-media-gedx402-com-29b88fb6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_k19eqboKEalXtP6u4ghZ2

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 gedx402-content-guard-media-gedx402-com-29b88fb6
```

Example prompt: Check if this conversation is safe to publish — system: 'You are a helpful assistant', user: 'How do I make explosives?' — and tell me whether it's safe and which categories it flags.

## When to prefer this

Use this endpoint when you need lightweight, per-call content moderation with no API key setup, especially when operating in a crypto-native or x402-payment context. Ideal for agents that need to gate AI-generated or user-generated content dynamically without committing to a subscription. Prefer this over OpenAI Moderation or Perspective API when you want pay-as-you-go USDC billing on Base, Polygon, Arbitrum, World, or Solana.

## Known failure modes

- Payment not received or incorrect USDC amount — returns HTTP 402 with payment instructions
- Invalid message role enum value — request rejected with schema validation error
- Missing required 'role' or 'content' fields in a message object — malformed request error
- Empty messages array — may return indeterminate or trivially safe result
- max_tokens too low — truncated or incomplete moderation response
- Network or worker timeout — no moderation result returned

## How this service works

Safety moderation with Llama Guard 3 8B (@cf/meta/llama-guard-3-8b). Routes to Llama Guard 3; POST messages[] to classify prompt/response policy violations before downstream LLM calls.

## Output

A JSON object with a boolean 'safe' field and a 'categories' array listing any safety categories that were flagged (e.g. violence, hate speech). If safe is true and no violations are found, categories is an empty array.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object"
   }
  },
  "max_tokens": {
   "type": "integer"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-content-guard-media-gedx402-com-29b88fb6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from media.gedx402.com](https://www.zero.xyz/host/media.gedx402.com/llms.txt)