G
Gemini 3.8 Live Extended Thinking
Gemini 3.8 Live Extended Thinking, a realtime voice model from Google.
model: "gemini-3.8-live-extended-thinking"
GGoogle·Released September 2026
Pricing
- List price
- ~$0.02 / min of conversation
- Text input
- $0.75 / 1M
- Text output
- $4.50 / 1M
- Audio input
- $3.00 / 1M
- Audio output
- $12.00 / 1M
Specifications
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Released
- September 2026
- Capabilities
- RealtimeReasoningTools
Parameters
Model options, set where this model is selected.
| Parameter | Type | Default | Range / options |
|---|---|---|---|
voice | Select | Puck | PuckZephyrCharonKoreFenrirLeda+24 |
Voices · 30
Use this model
// Realtime models power a live voice interface, set as the // voice engine in the interface configuration. // Model id: 0