Moderate Content

Check if content complies with usage policies.

POST /v1/moderations

cURL

curl https://gateway.bud.studio/v1/moderations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "I want to hurt someone."
  }'

200

{
  "id": "modr-abc123",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": true,
      "categories": {
        "sexual": false,
        "hate": false,
        "harassment": false,
        "self-harm": false,
        "sexual/minors": false,
        "hate/threatening": false,
        "violence/graphic": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "harassment/threatening": true,
        "violence": true
      },
      "category_scores": {
        "sexual": 0.001,
        "hate": 0.003,
        "harassment": 0.156,
        "self-harm": 0.002,
        "sexual/minors": 0.0,
        "hate/threatening": 0.001,
        "violence/graphic": 0.004,
        "self-harm/intent": 0.001,
        "self-harm/instructions": 0.0,
        "harassment/threatening": 0.789,
        "violence": 0.891
      }
    }
  ]
}

cURL

curl https://gateway.bud.studio/v1/moderations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "I want to hurt someone."
  }'

200

{
  "id": "modr-abc123",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": true,
      "categories": {
        "sexual": false,
        "hate": false,
        "harassment": false,
        "self-harm": false,
        "sexual/minors": false,
        "hate/threatening": false,
        "violence/graphic": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "harassment/threatening": true,
        "violence": true
      },
      "category_scores": {
        "sexual": 0.001,
        "hate": 0.003,
        "harassment": 0.156,
        "self-harm": 0.002,
        "sexual/minors": 0.0,
        "hate/threatening": 0.001,
        "violence/graphic": 0.004,
        "self-harm/intent": 0.001,
        "self-harm/instructions": 0.0,
        "harassment/threatening": 0.789,
        "violence": 0.891
      }
    }
  ]
}

Headers

Parameter	Type	Required	Description
Authorization	string	Yes	Bearer authentication header

Body

Parameter	Type	Required	Description
model	string	Yes	Moderation model identifier (e.g., omni-moderation-latest)
input	string or array	Yes	Text content to moderate

Supported Providers

OpenAI

omni-moderation-latest, text-moderation-stable

Azure OpenAI

Enterprise content moderation models