# AgentRXI Content Moderation (Llama Guard 3)

> AgentRXI Content Moderation (Llama Guard 3) is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.0034/call, status unknown (last checked 2026-10-15).

Classifies up to 10 texts as safe or unsafe using Llama Guard 3, returning hazard categories such as violence, hate speech, self-harm, sexual content, privacy violations, and election-related content.

## Facts

- Endpoint: GET https://agentrxi.com/v1/moderate?utm_source=zero.xyz
- Price: $0.0034/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-content-moderation-llama-guard-3-b62821c0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JxkRkmn1t8bgOlDYKC_zf

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 agentrxi-content-moderation-llama-guard-3-b62821c0
```

Example prompt: Before you post that reply, can you run it through Llama Guard 3 to check if it's safe — flag any hazard categories like violence, hate, or self-harm?

## When to prefer this

Choose this endpoint when you need fast, reliable content moderation powered by Llama Guard 3 for both user inputs and AI-generated replies, especially in agentic pipelines where you want to screen content before it is acted upon or delivered. It supports batch classification of up to 10 texts per call and covers a broad range of hazard categories. Prefer it over general-purpose LLM calls for moderation when you need structured, consistent safety labels with per-category hazard detail at low cost.

## Known failure modes

- Missing required 'text' or 'texts' parameter returns an error
- Exceeding 10 texts in a single request may be rejected
- Malformed pipe-separated 'texts' parameter may cause parse errors
- Payment failure or insufficient USDC balance blocks the request
- Ambiguous or very short texts may yield lower-confidence classifications

## 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. Priced by size: $0.003 + $0.0004 per text + $0.0004 per 1,000 characters. Also callable as GET with the same fields as query parameters.

## Output

Returns a safety classification (safe or unsafe) for each submitted text, along with specific hazard categories triggered (e.g. violence, weapons, hate, self-harm, sexual content, privacy, elections). Each result is tied to the submitted text and role context.

## 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/agentrxi-content-moderation-llama-guard-3-b62821c0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)