建立審核 - CometAPI Documentation

POST

moderations

curl https://api.cometapi.com/v1/moderations \
  -X POST \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
  "model": "omni-moderation-latest",
  "input": "I want to bake cookies for my family."
}'

{
  "id": "modr-1594",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "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,
        "sexual": false,
        "sexual/minors": false,
        "violence": false,
        "violence/graphic": false
      },
      "category_scores": {
        "harassment": 0.0001,
        "harassment/threatening": 0.0001,
        "hate": 0.0001,
        "hate/threatening": 0.0001,
        "illicit": 0.0001,
        "illicit/violent": 0.0001,
        "self-harm": 0.0001,
        "self-harm/intent": 0.0001,
        "self-harm/instructions": 0.0001,
        "sexual": 0.0001,
        "sexual/minors": 0.0001,
        "violence": 0.0001,
        "violence/graphic": 0.0001
      },
      "category_applied_input_types": {
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm": [
          "text"
        ],
        "self-harm/intent": [
          "text"
        ],
        "self-harm/instructions": [
          "text"
        ],
        "sexual": [
          "text"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text"
        ],
        "violence/graphic": [
          "text"
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 0,
    "total_tokens": 12,
    "input_tokens": 12,
    "output_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    },
    "input_tokens_details": null,
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  }
}

使用此端點可在你將使用者產生的內容送到模型端點之前先進行檢查。傳送一個與 OpenAI 相容的審核請求，並包含 model 與 input 值。

在 bearer header 中使用 CometAPI API key：Authorization: Bearer $COMETAPI_KEY。

請求主體

欄位	類型	必填	說明
`input`	string 或 array	是	要檢查的內容。單一文字輸入請使用字串，批次文字檢查請使用字串陣列，或使用 OpenAI 風格的多模態部分，例如文字加上 `image_url`。
`model`	string	是	審核模型的 model ID。除非你有特定的審核模型需求，否則請使用 `omni-moderation-latest` 進行文字與圖片審核。

對於多模態審核，請使用 OpenAI 風格的多模態輸入，並搭配支援該格式的模型，例如 omni-moderation-latest。公開圖片 URL 必須可供 CometAPI 伺服器下載。若要進行可直接複製使用的圖片測試，請使用 base64 data URL。

請求範例

當你只需要分類單一文字輸入時，請傳送單一文字字串：

curl https://api.cometapi.com/v1/moderations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "omni-moderation-latest",
    "input": "I want to bake cookies for my family."
  }'

當你想在一次請求中檢查多個文字輸入時，請傳送字串陣列：

curl https://api.cometapi.com/v1/moderations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "omni-moderation-latest",
    "input": [
      "I want to bake cookies.",
      "I want to kill someone."
    ]
  }'

當你的審核輸入包含 CometAPI 可下載的圖片時，請傳送文字加上圖片 URL：

curl https://api.cometapi.com/v1/moderations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "omni-moderation-latest",
    "input": [
      { "type": "text", "text": "...text to classify goes here..." },
      {
        "type": "image_url",
        "image_url": {
          "url": "https://www.gstatic.com/webp/gallery/1.png"
        }
      }
    ]
  }'

當你需要自包含的圖片請求時，請使用 base64 data URL：

curl https://api.cometapi.com/v1/moderations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
    "model": "omni-moderation-latest",
    "input": [
      { "type": "text", "text": "...text to classify goes here..." },
      {
        "type": "image_url",
        "image_url": {
          "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAAAAAA6fptVAAAADElEQVR4nGP4//8/AAX+Av4N70a4AAAAAElFTkSuQmCC"
        }
      }
    ]
  }'

回應結構

回應包含 id、model、results 與 usage。results 中的每個項目都會回報對應輸入是否被標記、分類布林值、分類分數，以及套用到各分類的輸入類型。對於批次文字請求，results 會為每個輸入字串一一包含對應項目。請使用 usage 取得計費與監控欄位。

授權

Authorization

string

header

必填

CometAPI API key used for model requests. Send it as Authorization: Bearer $COMETAPI_KEY.

主體

application/json

model

string

必填

Required moderation model ID. Use omni-moderation-latest for text and image moderation unless you have a specific moderation model requirement.

範例:

"omni-moderation-latest"

input

必填

Content to check. Use a string for one text input, an array of strings for batch text checks, or OpenAI-style multimodal parts such as text plus image_url when the selected model supports it.

範例:

"I want to check this text before sending it to a model."

回應

Moderation decisions and token usage.

string

必填

Moderation request ID.

範例:

"modr-1594"

model

string

必填

Model used for moderation.

範例:

"omni-moderation-latest"

results

object[]

必填

Moderation decisions. For batch text input, this array contains one result per input string.

Show child attributes

usage

object

必填

Token usage for the moderation request.

Show child attributes

建立嵌入

取得目前的 API 金鑰

curl https://api.cometapi.com/v1/moderations \
  -X POST \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -d '{
  "model": "omni-moderation-latest",
  "input": "I want to bake cookies for my family."
}'

{
  "id": "modr-1594",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "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,
        "sexual": false,
        "sexual/minors": false,
        "violence": false,
        "violence/graphic": false
      },
      "category_scores": {
        "harassment": 0.0001,
        "harassment/threatening": 0.0001,
        "hate": 0.0001,
        "hate/threatening": 0.0001,
        "illicit": 0.0001,
        "illicit/violent": 0.0001,
        "self-harm": 0.0001,
        "self-harm/intent": 0.0001,
        "self-harm/instructions": 0.0001,
        "sexual": 0.0001,
        "sexual/minors": 0.0001,
        "violence": 0.0001,
        "violence/graphic": 0.0001
      },
      "category_applied_input_types": {
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm": [
          "text"
        ],
        "self-harm/intent": [
          "text"
        ],
        "self-harm/instructions": [
          "text"
        ],
        "sexual": [
          "text"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text"
        ],
        "violence/graphic": [
          "text"
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 0,
    "total_tokens": 12,
    "input_tokens": 12,
    "output_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    },
    "input_tokens_details": null,
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  }
}

​請求主體

​請求範例

​回應結構

授權

主體

回應

請求主體

請求範例

回應結構