google
Gemini 3.8 Live Extended Thinking
Gemini 3.8 Live Extended Thinking is Google's real-time audio model with extended thinking capabilities. It combines spoken interaction with additional reasoning for voice assistants and other conversational applications.
websocket realtimetextaudio
Overview
- Type
- realtime
- Context
- —
- Max output
- —
- Input / output
- text, audio / text, audio
API
Model identifier
google/gemini-3.8-live-extended-thinkingProviders and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Operational | — | — | — / — / — | $0.75/M | $4.50/M | — / — | — | — | — | Yes |
Pricing
input
0.00000075
output
0.0000045
audio input token cost
0.000003
audio output token cost
0.000012
Capabilities
websocket realtimetextaudio
Supported parameters
max tokens
Yes
temperature
Yes
stop
Yes
reasoning
Yes
include reasoning
Yes
Reasoning options
options
{
"type": "effort",
"values": [
"low",
"high"
]
}
Metadata
type
realtime
context window
—
max output
—
released
Sep 15, 2026
temperature control
Yes
zero data retention
none
no training
all
api specifications
v2, v3, v4