Skip to content
AI Atlas
ModelActivefamily · Gemini

Gemini 3.1 Flash Live Preview

Googleai.google.dev/gemini-api/docs/models/gemini-3.1-

Our high-quality, low-latency audio-to-audio (A2A) model designed for real-time dialogue and voice-first AI applications.

quality75

Updated 1 h ago · first seen 11 Sept 2026

model_01M293V7TPKHRK142S7K178ANB

Context
131.1K tokens
T1 · 1 h ago

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Audio

1 claims · 1 propertiesShow all properties

Audioaudio1

Claim history for Audio
ValueValid from → toStatusSourceConfidenceExtractor
YescurrentcurrentGoogle AI for Developers (Gemini API docs)T1highdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →