Opprett en 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
  }
}

Bruk dette endepunktet til å kontrollere brukergenerert innhold før du sender det til et model-endepunkt. Send en OpenAI-kompatibel moderation-forespørsel med en model og en input-verdi.

Bruk en CometAPI API-nøkkel i bearer-headeren: Authorization: Bearer $COMETAPI_KEY.

Forespørselstekst

Felt	Type	Påkrevd	Beskrivelse
`input`	string eller array	Ja	Innholdet som skal kontrolleres. Bruk en string for én tekstinput, en array med strings for batch-kontroller av tekst, eller OpenAI-lignende Multimodal-deler som tekst pluss `image_url`.
`model`	string	Ja	Moderation model ID. Bruk `omni-moderation-latest` for moderation av tekst og bilder med mindre du har et spesifikt krav til moderation-model.

For Multimodal moderation, send OpenAI-lignende Multimodal input med en model som støtter det, for eksempel omni-moderation-latest. Offentlige bilde-URL-er må kunne lastes ned av CometAPI-servere. For en kopierbar bildetest bruker du en base64 data-URL.

Eksempler på forespørsler

Send en enkelt tekststreng når du bare trenger å klassifisere én tekstinput:

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."
  }'

Send en array med strings når du vil kontrollere flere tekstinputer i én forespørsel:

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."
    ]
  }'

Send tekst pluss en bilde-URL når moderation-inputen din inkluderer et bilde som CometAPI kan laste ned:

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"
        }
      }
    ]
  }'

Bruk en base64 data-URL når du trenger en selvstendig bildeforespørsel:

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"
        }
      }
    ]
  }'

Svarformat

Svaret inkluderer id, model, results og usage. Hvert element i results rapporterer om den tilsvarende inputen ble flagget, kategori-booleans, kategoripoeng og inputtyper brukt på hver kategori. For en batch-forespørsel med tekst inneholder results ett element per inputstreng. Bruk usage for felter knyttet til fakturering og overvåking.

Autorisasjoner

Authorization

string

header

påkrevd

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

Kropp

application/json

model

string

påkrevd

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

Eksempel:

"omni-moderation-latest"

input

påkrevd

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.

Eksempel:

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

Svar

Moderation decisions and token usage.

string

påkrevd

Moderation request ID.

Eksempel:

"modr-1594"

model

string

påkrevd

Model used for moderation.

Eksempel:

"omni-moderation-latest"

results

object[]

påkrevd

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

Show child attributes

usage

object

påkrevd

Token usage for the moderation request.

Show child attributes

Sist endret 23. juni 2026

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
  }
}

Innholdsmoderering

API-nøkler

Forespørselstekst

Eksempler på forespørsler

Svarformat

Autorisasjoner

Kropp

Svar

​Forespørselstekst

​Eksempler på forespørsler

​Svarformat

Autorisasjoner

Kropp

Svar

Forespørselstekst

Eksempler på forespørsler

Svarformat