# 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).

Checks text for harmful or policy-violating content using Llama Guard 3, returning OpenAI-compatible moderation results with flagged status, category labels, category scores, and raw Llama Guard codes.

## Facts

- Endpoint: GET https://agentrxi.com/v1/moderations?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-fe5e7b06
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_PzCBDG4YWFdUQHDC5ESlS

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-fe5e7b06
```

Example prompt: Can you check this message for harmful content — 'You should hurt yourself and others' — and tell me if it gets flagged, which categories triggered, and the confidence scores?

## When to prefer this

Choose this endpoint when you need OpenAI-compatible moderation output (drop-in replacement for /v1/moderations) but want Llama Guard 3 as the underlying model, or when you need the raw Llama Guard category codes alongside standard scores. Ideal for pay-per-call usage without an OpenAI account, or when cost transparency per call matters. Prefer over generic LLM prompting for moderation since it returns structured, normalized scores rather than free-text verdicts.

## Known failure modes

- Missing required 'input' parameter returns a 400 validation error
- Input exceeding batch limit of 10 items per POST call may be rejected
- Payment failure or insufficient USDC balance results in 402 Payment Required
- Very long inputs increase cost due to per-1000-character pricing
- Network timeout for extremely large batches

## How this service works

OpenAI-compatible moderation (Llama Guard 3): same response shape as OpenAI /v1/moderations with flagged, categories and category_scores, plus the raw Llama Guard codes. Up to 10 inputs per call. Priced by size: $0.003 + $0.0004 per input + $0.0004 per 1,000 characters. Also callable as GET with the same fields as query parameters.

## Output

Returns an OpenAI-compatible moderation response object containing: a 'flagged' boolean, a 'categories' object mapping harm category names to booleans, a 'category_scores' object mapping category names to confidence scores (0–1), and raw Llama Guard 3 classification codes. Up to 10 inputs can be submitted per call (POST) or one via GET.

## 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",
     "required": [
      "input"
     ],
     "properties": {
      "input": {
       "type": "string",
       "description": "Text to check (POST also accepts an array of up to 10)"
      },
      "model": {
       "type": "string",
       "description": "Ignored"
      }
     }
    }
   },
   "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-fe5e7b06/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)