Model key: nsfw

Detect unsafe and sensitive topics. Useful for detecting content that might be inappropriate for children. Sensitive topics include, but are not limited to, violence, weapons, drugs, politics, religion, etc.

NSFW Response Example:
{
  "label": "UNSAFE",
  "score": 0.67743,
  "label_scores": {
    "UNSAFE": 0.67743,
    "SENSITIVE": 0.321657,
    "NEUTRAL": 0.000897
  }
}

Labels

LabelDescription
UNSAFEViolence, weapons, drugs, sexual, etc.
SENSITIVEPolitics, religion, etc.
NEUTRAL

Supported languages

This model works in the following languages:

  • English en
  • Spanish es
  • French fr
  • German de
  • Italian it
  • Portuguese pt
  • Russian ru
  • Japanese ja
  • Indonesian id
  • Chinese zh
  • Dutch nl
  • Polish pl
  • Swedish sv

The model might work on other launguages we haven't tested. Feel free to try it on launguages that are not listed above and provide us with feedback.

Limitations

This model has a 1.000 characters per request limit. You can still post texts with more than 1.000 characters, but it will increase the quota usage. For example, a 1.500 characters text will count as 2 requests.

Was this page helpful?