# Agent Hub Content Moderation (Llama Guard 3)

> Agent Hub Content Moderation (Llama Guard 3) is a paid API for AI agents from agents.torbrooknews.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-13).

Classifies up to 10 texts as safe or unsafe across hazard categories (violence, weapons, hate, self-harm, sexual content, privacy, elections) using Meta Llama Guard 3.

## Facts

- Endpoint: GET https://agents.torbrooknews.com/v1/moderate?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-hub-content-moderation-llama-guard-3-8f509002
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HfGDPirtwzvrniF0dp6BH

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 agent-hub-content-moderation-llama-guard-3-8f509002
```

Example prompt: Before you reply, run my message through Llama Guard 3 moderation and check whether it contains any violence, hate speech, or self-harm content — treat it as a user role input.

## When to prefer this

Choose this endpoint when you need fast, pay-per-call content moderation without managing an API key, especially for LLM input/output safety screening. It is purpose-built for AI agent pipelines (checking both user messages and assistant replies), supports batching up to 10 texts, and uses Meta's Llama Guard 3 model which covers a broad set of hazard categories including elections and privacy — making it more comprehensive than basic keyword filters.

## Known failure modes

- Missing required 'texts' or 'text' query parameter returns an error
- More than 10 texts submitted at once may exceed the batch limit
- Ambiguous or very short text may produce low-confidence classifications
- Payment failure (x402) if insufficient USDC balance
- Rate limiting if too many calls are made in quick succession

## How this service works

Safety check (Llama Guard 3): classify up to 10 texts as safe or unsafe with hazard categories (violence, weapons, hate, self-harm, sexual content, privacy, elections and more). Check user input or your own reply before posting. Also callable as GET with the same fields as query parameters.

## Output

Returns a safety classification for each input text indicating whether it is safe or unsafe, along with the specific hazard categories triggered (e.g. violence, weapons, hate speech, self-harm, sexual content, privacy, elections). Up to 10 texts can be classified per call.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "role": {
       "type": "string",
       "description": "user (default) or assistant"
      },
      "text": {
       "type": "string"
      },
      "texts": {
       "type": "string",
       "description": "separate items with |"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-hub-content-moderation-llama-guard-3-8f509002/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.torbrooknews.com](https://www.zero.xyz/host/agents.torbrooknews.com/llms.txt)