Gemini-1

Gemini 1.5 Flash is the high-speed, cost-efficient multimodal model: a distilled version of Pro, built for high-volume, low-latency tasks.

This is your workhorse model: a highly efficient, multimodal AI distilled from Gemini 1.5 Pro via advanced techniques like knowledge distillation. It maintains impressive quality while drastically reducing latency and cost, making it ideal for high-volume applications like chatbots and real-time analysis. The model's key feature is its massive context window, capable of processing up to 1 million tokens (text, image, audio, or video) for deep, cross-modal reasoning over extensive data sets.

https://ai.google.dev/models/gemini