Skip to main content
POST
/
moderations
Create Moderation
curl --request POST \
  --url https://{gatewayBaseURL}/moderations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "model": "<string>"
}
'
{
  "id": "<string>",
  "model": "<string>",
  "results": [
    {
      "flagged": true,
      "categories": {
        "hate": true,
        "hate/threatening": true,
        "harassment": true,
        "harassment/threatening": true,
        "self-harm": true,
        "self-harm/intent": true,
        "self-harm/instructions": true,
        "sexual": true,
        "sexual/minors": true,
        "violence": true,
        "violence/graphic": true
      },
      "category_scores": {
        "hate": 123,
        "hate/threatening": 123,
        "harassment": 123,
        "harassment/threatening": 123,
        "self-harm": 123,
        "self-harm/intent": 123,
        "self-harm/instructions": 123,
        "sexual": 123,
        "sexual/minors": 123,
        "violence": 123,
        "violence/graphic": 123
      }
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

​
x-tfy-metadata
string

Optional metadata for the request

Body

application/json

Text or multi-modal input to classify.

​
input
required

Input (or inputs) to classify. Can be a string, array of strings, or array of multi-modal inputs

​
model
string | null

Model to use for moderation

Response

Moderation result with per-category flags and scores.

​
id
string
required

Unique moderation ID

​
model
string
required

Model used for moderation

​
results
object[]
required

Moderation results per input