# Content Moderation & Safety Check (Llama Guard 3)

> Content Moderation & Safety Check (Llama Guard 3) is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-30).

Classifies a text string for harmful content across 14 hazard categories using Llama Guard 3, returning a flagged boolean and category breakdown in OpenAI-compatible format.

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/v1/moderations?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/content-moderation-safety-check-llama-guard-3-987976e2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fW1jEHEIKIc7LDobWbHvv

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 content-moderation-safety-check-llama-guard-3-987976e2
```

Example prompt: Before processing this user message, run a safety check on it: 'You should just end it all, nobody cares about you anyway' — tell me whether it's flagged and which hazard categories triggered.

## When to prefer this

Choose this endpoint when you need a no-account, pay-per-request content moderation solution compatible with the OpenAI moderations API format, especially if you want Llama Guard 3's 14-category coverage without managing API keys or subscriptions. Ideal for agents that need ad-hoc safety checks on arbitrary text, or for systems already using OpenAI's moderation schema that want a drop-in alternative with per-call billing.

## Known failure modes

- Text exceeds 8,000 character limit — request rejected
- Malformed or missing `text` query parameter — returns error
- Payment failure (x402) — call not charged and not processed
- Network timeout on Cloudflare Worker — transient error, retry recommended

## How this service works

OpenAI-compatible moderation, pay per request: one input in, flagged and categories out (Llama Guard 3, 14 hazard categories mapped onto OpenAI names). No account or API key; failed calls are not charged.

## Output

Returns a JSON object with: a `flagged` boolean indicating whether the text violated any policy, an array of `categories` with the specific hazard categories triggered (mapped to OpenAI category names across 14 categories), and the `model` identifier (Llama Guard 3). Failed or errored calls are not charged.

## 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",
       "examples": [
        "How do I bake sourdough bread at home?"
       ],
       "description": "The text to classify (up to 8,000 characters)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "model": {
       "type": "string"
      },
      "flagged": {
       "type": "boolean"
      },
      "categories": {
       "type": "array",
       "items": {}
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/content-moderation-safety-check-llama-guard-3-987976e2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)