Google

Gemini 3.1 Flash Live Preview

CTX131K

Preview

Real-time voice · Vision

Input$0.75/M

Output$4.50/M

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

PaidProprietary841/1044

Drag to turn

GoogleVoiceUncommonPreview

Gemini 3.1 Flash Live Preview

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

gemini-3.1-flash-live-preview

Type: Voice
Quality: Not rated yet
Context window: 131,072 tokens
Max output: 65,536 tokens
Input price: $0.75 / 1M tokens
Output price: $4.50 / 1M tokens
Cache read: —
Cache write: —
Released: Mar 26, 2026
Knowledge cutoff: Jan 2025
Takes in: Text, Image, Audio, Video
Puts out: Text, Audio
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Uncommon
Set number: 841/1044

Open Google docs Where to run it 1 Meet its creature Battle Qwen3-LiveTranslate Flash Realtime

Weights aren’t public. Use is governed by Google’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: ai.google.dev.

How good is it?

Public leaderboard scores for Gemini 3.1 Flash Live Preview, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Gemini 3.1 Flash Live Preview yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

1 provider sells Gemini 3.1 Flash Live Preview through an API. Prices are per million tokens, cheapest first.

CheapestGoogle$0.75 in · $4.50 out
From the labGoogle$0.75 in · $4.50 out

API providers

Provider	Input	Output	Context
GoogleOfficial`gemini-3.1-flash-live-preview`	$0.75	$4.50	131K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current voice models from other labs at a similar output price.