# NetIntel Content Moderation API

> NetIntel Content Moderation API is a paid API for AI agents from netintel.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Analyzes text content for harmful categories (harassment, hate, violence, spam, sexual, self-harm) and returns a moderation grade, score, and block/allow recommendation

## Facts

- Endpoint: POST https://netintel.dev/content-moderate
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/netintel-content-moderation-api-3320a631
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Oz8uAbOXagrx3iWw0r4Rz

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 netintel-content-moderation-api-3320a631 -d '<json body>'
```

Example prompt: Can you check this message for harmful content and tell me whether to block it: 'I know where you live and I will make you regret this' — I need a grade, a safety score, and which categories like harassment or violence are flagged?

## When to prefer this

Use this endpoint when you need detailed, categorized content moderation with per-category severity levels and a human-readable reasoning explanation, not just a binary pass/fail. Ideal for platforms screening user-generated text for harassment, violence, hate speech, spam, or self-harm before publishing. The graded score and block/allow recommendation make it suitable for automated enforcement pipelines. Preferred over basic keyword filters when nuanced threat detection and explainability are required.

## Known failure modes

- Empty or missing text body returns a 400 error
- Payment not included or insufficient USDC triggers 402 Payment Required
- Overly long input may be truncated or rejected
- Non-English text may reduce moderation accuracy
- Rate limits or server errors return 429 or 500 responses

## How this service works

Moderate text content using Claude Haiku — flags categories like harassment, hate, sexual content, violence, self-harm, and spam with per-category severity and an overall allow/flag/block recommendation, so agents can screen user-generated content before publishing or storing it.

## Output

Returns a JSON object with a letter grade (e.g. 'F'), a numeric safety score (0-100), an overall recommendation ('block' or 'allow'), a list of findings with category and severity, a human-readable reasoning string, and a per-category breakdown (hate, spam, sexual, violence, self_harm, harassment) each with a flagged boolean and severity level.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "properties": {
      "text": {
       "type": "string",
       "description": "The text to moderate — a comment, message, post, review, or any user-generated content. Max 10000 words or 50KB."
      }
     },
     "required": [
      "text"
     ]
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "categories": {
       "type": "object",
       "description": "Per-category verdicts (harassment, hate, sexual, violence, self_harm, spam), each with flagged (boolean) and severity (none/low/medium/high)"
      },
      "flagged_categories": {
       "type": "array",
       "items": {
        "type": "string"
       },
       "description": "Category names where flagged=true"
      },
      "overall": {
       "type": "string",
       "description": "Overall recommendation: allow, flag, or block"
      },
      "reasoning": {
       "type": "string",
       "description": "One-sentence rationale for the verdict"
      },
      "score": {
       "type": "number",
       "description": "Content cleanliness score 0-100 (allow=100, flag=70, block=20)"
      },
      "grade": {
       "type": "string",
       "description": "Letter grade A-F derived from the score"
      },
      "findings": {
       "type": "array",
       "items": {
        "type": "object"
       },
       "description": "One entry per flagged category with its severity"
      }
     }
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "grade": "F",
  "score": 20,
  "overall": "block",
  "findings": [
   {
    "category": "harassment",
    "severity": "high"
   },
   {
    "category": "violence",
    "severity": "medium"
   }
  ],
  "reasoning": "Contains a direct threat of physical harm targeting the recipient.",
  "categories": {
   "hate": {
    "flagged": false,
    "severity": "none"
   },
   "spam": {
    "flagged": false,
    "severity": "none"
   },
   "sexual": {
    "flagged": false,
    "severity": "none"
   },
   "violence": {
    "flagged": true,
    "severity": "medium"
   },
   "self_harm": {
    "flagged": false,
    "severity": "none"
   },
   "harassment": {
    "flagged": true,
    "severity": "high"
   }
  },
  "flagged_categories": [
   "harassment",
   "violence"
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/netintel-content-moderation-api-3320a631/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from netintel.dev](https://www.zero.xyz/host/netintel.dev/llms.txt)