Usage

Description

Leverage AI to detect unsafe content with deep context awareness. This endpoint assigns safety scores across 8 categories while adapting to the provided context. It can distinguish playful texts from genuine threats, ensuring accurate moderation for any environment.

Method & Path

Use https://prism.optical-labs.ca/text/ai-moderation to access this endpoint. The method must be POST and the header should contain your secret API key, as shown below:

Body Fields

Field Name	Type	Description
text	String (required)	Text with a length between 1 and 5000 characters
context	String (optional)	Text with a length between 0 and 200 characters
model	String (optional)	ID of the model used. One of: "prism-guard-flash" "prism-guard-pro"

Valid Response

Each successful request to this endpoint costs 10 to 12 credit, depending on the model used. Your usage and remaining credits are always returned in the meta object of the response.

Models

Name	Description	Cost/Request	Execution Time*
prism-guard-flash (default)	Fast, efficient, reliable.	10 credits	0.5 - 3 seconds
prism-guard-pro	Deeper reasoning, higher intelligence.	12 credits	2 - 8 seconds

*Execution times vary based on input length. Expect higher latency for larger requests.

Interactive Preview

Because of the high-compute nature of this endpoint, the interactive preview is not available.

Examples

Basic Request

The simplest request you can make, using only the text field (not recommended):

The response includes the full configuration used for the request, including default values for any undefined parameters:

Custom Context

Add context to help the AI understand the situation: