Skip to main content

Moderations

POST /v1/moderations

Classifies text/images against safety policies for content moderation, returning category flags and confidence scores.

RequestREQUEST
POSThttps://test.kailin.com.cn/v1/moderations
ResponseRESPONSE
Fill in the request and hit Send — the response shows up here

Request​

curl https://test.kailin.com.cn/v1/moderations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "text to review"
  }'

Request Body​

ParameterTypeRequiredDescription
modelstringNoDefaults to omni-moderation-latest, supports multimodal input
inputstring / arrayYesText to review; for multimodal, pass a content array

Multimodal input (text + image):

{
  "model": "omni-moderation-latest",
  "input": [
    { "type": "moderation_text", "text": "some text" },
    { "type": "moderation_image", "image_url": "https://example.com/img.jpg" }
  ]
}

Response​

{
  "id": "modr-abc123",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "harassment": false,
        "hate": false,
        "sexual": false,
        "violence": false
      },
      "category_scores": {
        "harassment": 0.0001,
        "hate": 0.0001,
        "sexual": 0.0002,
        "violence": 0.0003
      }
    }
  ]
}
FieldDescription
results[].flaggedWhether the content hit a policy
results[].categoriesBoolean results per category (more categories exist, e.g. harassment_threatening, self-harm)
results[].category_scoresConfidence 0–1 per category

Typical Usage​

def check(text: str) -> bool:
    resp = client.moderations.create(model="omni-moderation-latest", input=text)
    return resp.results[0].flagged  # True means the content should be blocked
note

Moderation is free or low-cost (depends on the channel). Call it on both user input and model output for two-way safety.