Our platform supports a multi-model architecture. Currently, Google Gemini (Gemini 2.0 Flash and Gemini 2.5 Pro) and OpenAI GPT (GPT-4o, GPT-4o mini, and GPT-5 mini) models are ready to use. You can select a different AI model for each assistant based on task complexity and budget. Token consumptions are deducted from your unified credit pool according to model multipliers (e.g., Gemini 2.0 Flash 1.0x, GPT-4o 10.0x).