Back to models
Gemini 3.1 Flash Live
ZDRReal-time voice and dialogue model
Capabilities:Real-time voiceSpeech & AudioVisionLong context (1M)Streaming
Modalities
Text input tokens
Image input
Audio generation
Price
See pricing
Context Length
1M tokens
Parameters
-
Providers
Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
Reasoning effortⓘAll
| Provider |
|---|
Google |
Observed reliability
Success rate across observed provider requests. This is historical sample data, not live health or an uptime guarantee.
Not enough observations
Last 7 days
There are not enough valid request observations to report a success rate.
Benchmarks
Dated third-party measurements with source links.
No verified benchmark snapshot is available for this model.
API Integration
Use the DOS API to integrate Gemini 3.1 Flash Live into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.
</>Run inference
curl https://api.dos.ai/v1/audio/generations \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-live",
"prompt": "Create a cinematic scene",
"duration": 180
}'