Membuat moderation

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
  }
}

Gunakan endpoint ini untuk memeriksa konten buatan pengguna sebelum Anda mengirimkannya ke endpoint model. Kirim permintaan moderation yang kompatibel dengan OpenAI dengan nilai model dan input.

Gunakan kunci API CometAPI di bearer header: Authorization: Bearer $COMETAPI_KEY.

Body permintaan

Field	Type	Required	Description
`input`	string atau array	Ya	Konten yang akan diperiksa. Gunakan string untuk satu input teks, array string untuk pemeriksaan teks batch, atau bagian multimodal bergaya OpenAI seperti teks plus `image_url`.
`model`	string	Ya	model ID moderation. Gunakan `omni-moderation-latest` untuk moderation teks dan gambar kecuali Anda memiliki kebutuhan model moderation yang spesifik.

Untuk moderation multimodal, kirim input multimodal bergaya OpenAI dengan model yang mendukungnya, seperti omni-moderation-latest. URL gambar publik harus dapat diunduh oleh server CometAPI. Untuk pengujian gambar yang dapat disalin, gunakan URL data base64.

Contoh permintaan

Kirim satu string teks jika Anda hanya perlu mengklasifikasikan satu input teks:

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."
  }'

Kirim array string jika Anda ingin memeriksa beberapa input teks dalam satu permintaan:

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."
    ]
  }'

Kirim teks plus URL gambar saat input moderation Anda menyertakan gambar yang dapat diunduh oleh CometAPI:

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"
        }
      }
    ]
  }'

Gunakan URL data base64 saat Anda memerlukan permintaan gambar yang berdiri sendiri:

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"
        }
      }
    ]
  }'

Bentuk respons

Respons mencakup id, model, results, dan usage. Setiap item dalam results melaporkan apakah input yang sesuai ditandai, boolean kategori, skor kategori, dan tipe input yang diterapkan pada setiap kategori. Untuk permintaan teks batch, results berisi satu item per string input. Gunakan usage untuk field penagihan dan pemantauan.

Otorisasi

Authorization

string

header

wajib

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

Body

application/json

model

string

wajib

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

Contoh:

"omni-moderation-latest"

input

wajib

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.

Contoh:

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

Respons

Moderation decisions and token usage.

string

wajib

Moderation request ID.

Contoh:

"modr-1594"

model

string

wajib

Model used for moderation.

Contoh:

"omni-moderation-latest"

results

object[]

wajib

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

Show child attributes

usage

object

wajib

Token usage for the moderation request.

Show child attributes

Create embeddings

Sebelumnya

Dapatkan API key saat ini

Selanjutnya

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
  }
}

Moderasi konten

Kunci API

Body permintaan

Contoh permintaan

Bentuk respons

Otorisasi

Body

Respons

​Body permintaan

​Contoh permintaan

​Bentuk respons

Otorisasi

Body

Respons

Body permintaan

Contoh permintaan

Bentuk respons