Moderations

Detect potentially unsafe content (hate, violence, sexual, self-harm, etc.) so you can filter inputs / outputs before or after calling generation endpoints.

Create a moderation

POST /v1/moderations

Parameters

Parameter	Type	Required	Description
model	string	No	Moderation model, e.g. omni-moderation-latest
input	string | array	Yes	Text to moderate, or an array of texts

Request

curl https://ai.youqi.tech/v1/moderations \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "Some text to be moderated."
  }'

Response

{
  "id": "modr-abc123",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "hate": false,
        "harassment": false,
        "self-harm": false,
        "sexual": false,
        "violence": false
      },
      "category_scores": {
        "hate": 0.00001,
        "harassment": 0.00002,
        "self-harm": 0.0,
        "sexual": 0.00003,
        "violence": 0.00001
      }
    }
  ]
}

Response fields

Field	Type	Description
results[].flagged	boolean	Whether any category was triggered
results[].categories	object	Per-category boolean flags
results[].category_scores	object	Per-category confidence scores (0–1)