Gemini 3.1 Flash Live Preview

Google's low-latency Gemini Live model. Served via the gateway's /v1/realtime WebSocket endpoint using Gemini's own BidiGenerateContent protocol, with text and audio input/output and function calling.

gemini-3.1-flash-live-preview
BETAGet StartedView uptime
131,072 context
Starting at $0.75/M input tokens
Starting at $4.50/M output tokens
Tools
No ratings yetSign in to rate

Select Provider

All Providers for Gemini 3.1 Flash Live Preview

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Google AI Studio
Context: 131.1k
Input
$0.75
/M tokens
Cache Read
$0.75
/M tokens
Output
$4.5
/M tokens
Audio Output
$12
/M tokens
Get Started