Moderation API：omni-moderation-latest（已下线）

export LAOZHANG_API_KEY="替换为你的老张API密钥"

curl --fail-with-body --max-time 60 \
  "https://api.laozhang.ai/v1/chat/completions" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "response_format": {"type": "json_object"},
    "messages": [
      {"role": "system", "content": "你是内容审核器。判断用户文本是否违规，只输出 JSON：{\"flagged\": true|false, \"categories\": [命中的类别，可选 sexual、harassment、hate、illicit、self-harm、violence]}"},
      {"role": "user", "content": "今天天气不错，我们去公园散步吧。"}
    ]
  }'

{"flagged": false, "categories": []}

{
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "sexual": false,
        "sexual/minors": false,
        "harassment": false,
        "harassment/threatening": false,
        "hate": false,
        "hate/threatening": false,
        "illicit": false,
        "illicit/violent": false,
        "self-harm": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "violence": false,
        "violence/graphic": false
      }
    }
  ]
}