Enum ModelType

Types of AI Models. Multi-modal models such as Gemini should be classified under their primary function, typically as Language Models.

[Flags]
public enum ModelType

Name	Description
All	Matches all model types. Used as a wildcard filter.
AudioProcessing	A model that processes or transforms audio signals.
Embedding	A model that produces vector embeddings from text or other inputs.
Image	A model for image tasks: generation, editing, or both.
Language	A large language model capable of text generation, conversation, and reasoning.
Moderation	A model that classifies content for policy violations or harmful material.
MusicGeneration	A model that generates music from text or other prompts.
OpticalCharacterRecognition	A model that recognizes and extracts text from images or documents (OCR).
PixelArtGeneration	A model specialized in generating pixel art assets.
Reranker	A model that reranks a list of documents by relevance to a query.
SoundEffect	A model that generates sound effects from text descriptions.
SpeechToText	A model that transcribes spoken audio into text.
TextToSpeech	A model that synthesizes speech audio from text input.
Unknown	The model type is not known or has not been set.
VideoGeneration	A model that generates video content from text or image prompts.
VoiceChange	A model that converts or transforms one voice into another.