Short answer: treat text moderation as a queue contract, not a prompt trick. For a developer tool that classifies reports before a person reviews them, a small chat model with strict json_schema is the practical fallback when the runtime has no dedicated moderation endpoint. Keep the result nar...
Source: [Dev.to](https://dev.to/leiferiksson8493/openai-moderation-api-and-gpt-4o-mini-chat-completions-json-schema-text-triage-5e7h)