# Quartermaster Content Safety Classifier (Llama Guard)

> Quartermaster Content Safety Classifier (Llama Guard) is a paid API for AI agents from quartermaster.surewhynot.app, paid per call via x402, $0.002/call, status healthy (last checked 2026-09-14, last successful call 2026-08-20).

Classifies a text string for content safety using Llama Guard, returning a safe/unsafe verdict and category codes.

## Facts

- Endpoint: GET https://quartermaster.surewhynot.app/v1/moderate
- Price: $0.002/call
- Payment: x402
- Status: healthy
- Last checked: 2026-09-14
- Last successful call: 2026-08-20
- Success rate: 100% of calls made through Zero
- Rating: 5.0 / 5 from 1 review
- Activations on Zero: 6
- Tags: x402
- Canonical page: https://www.zero.xyz/c/quartermaster-content-safety-classifier-llama-guard-1d50311c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1wtzwMrXP_8UHloySycZY

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 quartermaster-content-safety-classifier-llama-guard-1d50311c
```

Example prompt: Check if this message is safe to post: 'You should just hurt yourself if things get that bad' — run it through Llama Guard and tell me whether it's safe or unsafe and what category it flags.

## When to prefer this

Use this endpoint when you need a structured, category-coded content safety verdict powered by Llama Guard specifically — ideal for agents that need machine-readable category codes (not just a binary flag) and are operating within the x402 micropayment ecosystem at low per-call cost.

## Known failure modes

- Text exceeds 12,000 character limit — request rejected
- Empty or missing 'text' query parameter — validation error
- Llama Guard model timeout — upstream inference error
- Payment not included or invalid x402 header — 402 Payment Required

## How this service works

Content-safety classification (Llama Guard): safe/unsafe plus category codes.

## Output

Returns a safe or unsafe verdict along with relevant Llama Guard category codes indicating which safety policy was violated, if any.

## 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": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "maxLength": 12000,
       "description": "Text to classify for safety"
      }
     }
    }
   },
   "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/quartermaster-content-safety-classifier-llama-guard-1d50311c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from quartermaster.surewhynot.app](https://www.zero.xyz/host/quartermaster.surewhynot.app/llms.txt)