Toxic API

The Toxic API will return the toxicity of text. Text that is considered toxic may contain the following:

  • Profanity
  • Hate speech
  • Threats
  • Insults

Thanks to it's preprocessing and usage of neural networks, the Toxic API is also able to pick up on toxic comments that are nuanced or have attempted to be disguised.

Use cases

Example use cases for this API include:

  • Chat moderation
  • Comment flagging and removal