Gemini 3.8 Live
Google · text, image, audio, video → text, audio
Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency, audio-to-audio voice interaction experience, enabling real-time conversations without inference delays. It supports interleaved reasoning, asynchronous and synchronous function calling, and built-in proactive audio processing capabilities.
Input$3 /M
Output$12 /M