Een moderation aanmaken

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
  }
}

Gebruik deze endpoint om door gebruikers gegenereerde content te controleren voordat je die naar een model-endpoint stuurt. Verstuur een OpenAI-compatibel moderation-verzoek met een model en een input-waarde.

Gebruik een CometAPI API-sleutel in de bearer-header: Authorization: Bearer $COMETAPI_KEY.

Request body

Veld	Type	Vereist	Beschrijving
`input`	string of array	Ja	De te controleren content. Gebruik een string voor één tekstinput, een array van strings voor batchcontroles van tekst, of OpenAI-stijl multimodal onderdelen zoals tekst plus `image_url`.
`model`	string	Ja	Moderation model ID. Gebruik `omni-moderation-latest` voor tekst- en image moderation, tenzij je een specifieke moderation model-vereiste hebt.

Voor multimodal moderation verstuur je OpenAI-stijl multimodal input met een model dat dit ondersteunt, zoals omni-moderation-latest. Openbare image URL’s moeten door CometAPI-servers kunnen worden gedownload. Gebruik voor een kopieerbare image-test een base64 data URL.

Request examples

Verstuur één tekststring wanneer je slechts één tekstinput hoeft te classificeren:

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."
  }'

Verstuur een array van strings wanneer je meerdere tekstinputs in één request wilt controleren:

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."
    ]
  }'

Verstuur tekst plus een image URL wanneer je moderation-input een image bevat die CometAPI kan downloaden:

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"
        }
      }
    ]
  }'

Gebruik een base64 data URL wanneer je een op zichzelf staand image-request nodig hebt:

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"
        }
      }
    ]
  }'

Response shape

De response bevat id, model, results en usage. Elk item in results meldt of de overeenkomende input is gemarkeerd, category-booleans, category-scores en inputtypes die op elke category zijn toegepast. Voor een batch-tekstrequest bevat results één item per inputstring. Gebruik usage voor velden voor facturatie en monitoring.

Autorisaties

Authorization

string

header

vereist

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

Body

application/json

model

string

vereist

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

Voorbeeld:

"omni-moderation-latest"

input

vereist

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.

Voorbeeld:

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

Respons

Moderation decisions and token usage.

string

vereist

Moderation request ID.

Voorbeeld:

"modr-1594"

model

string

vereist

Model used for moderation.

Voorbeeld:

"omni-moderation-latest"

results

object[]

vereist

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

Show child attributes

usage

object

vereist

Token usage for the moderation request.

Show child attributes

Create embeddings

Huidige API-sleutel ophalen

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
  }
}

Contentmoderatie

API-sleutels

Request body

Request examples

Response shape

Autorisaties

Body

Respons

​Request body

​Request examples

​Response shape

Autorisaties

Body

Respons

Request body

Request examples

Response shape