内容安全审核 (Moderations)

POST

https://moyunapi.com/v1/moderations

Moderations

对文本内容进行安全审核，检测是否包含仇恨、暴力、自残、性内容等违规类别，并返回各分类的命中标志与置信分数。input 可为单个字符串或字符串数组（批量）。

请求参数

Authorization

Bearer Token

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json必填

示例

返回响应

🟢200

application/json

成功。

Bodyapplication/json

🟠400

🟠401

🟠429

🔴500

请求示例

Shell

JavaScript

Java

Swift

curl --location 'https://moyunapi.com/v1/moderations' \
--header 'Accept;' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "input": "我希望伤害自己。",
    "model": "omni-moderation-latest"
}'

响应示例

200 - 成功示例

{
    "id": "modr-abc123",
    "model": "omni-moderation-latest",
    "results": [
        {
            "flagged": true,
            "categories": {
                "hate": false,
                "hate/threatening": false,
                "harassment": false,
                "harassment/threatening": false,
                "self-harm": false,
                "self-harm/intent": true,
                "self-harm/instructions": false,
                "sexual": false,
                "sexual/minors": false,
                "violence": false,
                "violence/graphic": false
            },
            "category_scores": {
                "hate": 0.0001,
                "hate/threatening": 0.00003,
                "harassment": 0.0008,
                "harassment/threatening": 0.00005,
                "self-harm": 0.012,
                "self-harm/intent": 0.9234,
                "self-harm/instructions": 0.0002,
                "sexual": 0.0001,
                "sexual/minors": 0.00001,
                "violence": 0.0004,
                "violence/graphic": 0.00002
            }
        }
    ]
}

实时语音对话 (WebSocket)

文档重排序 (Rerank)