Gemini 3.1 Flash Live
Google DeepMind · · 1 days after Lyria 3
Partially verified
0 of 1 published values traced to a source2 primary sources, 2 archived1 not researched yet
Why this status
Cited to official documentation. Not verified because the release date could not be found in any cited primary source — the value may be correct, but this dataset cannot yet show where it came from.
What these states mean · How records are judged · Has this record changed?
An audio-to-audio model for real-time dialogue.
Details
| Released | March 26, 2026 |
|---|---|
| Company | Google DeepMind |
| Family | Gemini Live |
| Era | Agentic systems |
| Type | Audio |
| Modalities | Text + Audio + Video → Text + Audio |
| Capabilities | Reasoning, Function calling |
| Weights | Proprietary |
| Licence | Not applicable — proprietary |
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
Sources
Record status: partly verified · confidence 60/100 · 2 of 2 primary
Cited to official documentation. Not verified because the release date could not be found in any cited primary source — the value may be correct, but this dataset cannot yet show where it came from.
- ai.google.dev Official documentation archived
- ai.google.dev Official documentation archived
Primary means published by the organisation that made the model. Verified records require at least one.
Gemini Live family
- Gemini 3.1 Flash Live March 26, 2026
- Gemini 3.8 Live September 15, 2026
- Gemini 3.8 Live Extended Thinking September 15, 2026
Compare Gemini 3.1 Flash Live with another model →
See Gemini 3.1 Flash Live on the interactive timeline →