Gemini 3 Flash Preview

Gemini 3 Flash Preview is Google's speed- and cost-optimized frontier model, combining Pro-level multimodal reasoning with lower latency and cost for high-throughput interactive and agentic workflows. It supports 1M-token context, multimodal inputs (text, image, video, audio, PDF), tool use, code execution, and computer use, and is available via the Gemini API, Vertex AI, and Google AI Studio. Source: supabase.