Moderation

Screen a prompt

Evaluate a text prompt against content policies before generation. This endpoint is experimental and may change.

post/v1/moderation/prompt

Request

Base URL
https://api.creem.io
Auth
API key in header x-api-key
TypeScript
https://skmtc.dev/creem/apis/creem-api/docs/v1/moderation/prompt/post.ts
A function with typed inputs. Its response is checked against the schema.

promptstring required

The text prompt to evaluate against content policies.

external_idstring

An optional identifier to associate this request with.

Prompt screening result

idstring required

Unique identifier for the moderation result.

objectstring required

Object type.

promptstring required

The prompt that was screened.

external_idstring

The external identifier provided in the request.

decision'allow' | 'deny' | 'flag' required

The moderation decision.

{
  "object": "moderation_result"
}

Sep 8, 20266d8c90726b62 Revision changes
- info
  added the non-success response with the status