POST /v1/moderations

审查（Moderations）

内容安全审核接口，兼容 OpenAI Moderations 格式

接口说明

审查接口用于检测文本内容是否包含敏感或违规信息，返回各类别的检测结果和置信度分数。

认证

使用 Bearer Token 认证，格式：Authorization: Bearer sk-xxxxxx

请求体参数

参数 类型 必需 说明
input string | array 是 要审查的文本内容，可以是单个字符串或字符串数组
model string 否 模型名称，如 omni-moderation-latest，默认 text-moderation-latest

请求示例

cURL
curl -X POST "https://your-base-url/v1/moderations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -d '{
    "input": "这是一段需要审查的文本内容",
    "model": "omni-moderation-latest"
  }'

响应示例

200 OK
{
  "id": "modr-abc123",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "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": false,
        "violence": false
      },
      "category_scores": {
        "sexual": 0.00012,
        "hate": 0.00003,
        "harassment": 0.00089,
        "self-harm": 0.00001,
        "sexual/minors": 0.00001,
        "hate/threatening": 0.00001,
        "violence/graphic": 0.00002,
        "self-harm/intent": 0.00001,
        "self-harm/instructions": 0.00001,
        "harassment/threatening": 0.00005,
        "violence": 0.00015
      }
    }
  ]
}
在线测试 直接在此页面测试 API
Authorization
Body