A WebSocket-based audio-to-audio model designed for low-latency spoken dialogue and voice agents. Reach for it when migrating from Gemini 2.5 Flash Native Audio or when you need native round-trip audio processing.
Modalities
Text → Audio
Price
$0.0389 / min
Speed
fast
Pricing
Per minute of audio processed. Min billable: 1 minute.
$0.0389 / minWhen to use Gemini 3.1 Flash Live
Where this model earns its cost — and where it doesn't.
Gemini 3.1 Flash Live is a realtime audio-to-audio model from Google. It processes native audio input and returns native audio output in a single WebSocket round-trip, supporting a 131,072-token context window and up to 65,536 output tokens.
On Kyma, it runs behind an OpenAI-compatible endpoint with automatic request failover if a serving path degrades. New accounts receive $0.50 in free credit, and prompt caching is supported, billing repeated prefixes at 10% of the standard input rate. The platform returns exact request cost in usage.cost and the active model ID in the X-Kyma-Model header.
The model does not support reasoning, vision, or structured outputs. It operates strictly on audio modalities and is billed per minute. It serves as the direct successor to Gemini 2.5 Flash Native Audio, which retires on 2026-10-20.
Low-Latency Voice Agents
Handles real-time spoken conversations with native audio input and output in a single WebSocket connection.
Speech Generation Workflows
Converts audio prompts into synthesized speech without intermediate transcription steps.
Interactive Spoken Chat
Powers conversational interfaces that require immediate audio responses for hands-free applications.
Not ideal for: Do not use this model if your application requires text-based reasoning, image understanding, or strictly formatted JSON outputs.
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit, no card required.
Get API key → - 2
Make your first request
Drop in your key and send a chat completion — fully OpenAI-compatible.
curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-3.1-flash-live-preview", "messages": [ {"role": "user", "content": "Explain prompt caching in one paragraph."} ] }' - 3
Stream responses
Add
"stream": trueto receive tokens as they arrive.curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-3.1-flash-live-preview", "stream": true, "messages": [{"role": "user", "content": "Hello!"}] }'
FAQ
Common questions about this model.
How much does Gemini 3.1 Flash Live cost?
How do I use Gemini 3.1 Flash Live?
How is billing calculated for this model?
Can I use this model for text generation or image analysis?
How does Kyma handle model availability and routing?
More models by Google
See all 18 →| Model | Context | Input | Output |
|---|---|---|---|
| 1M | $2.025 | $10.125 | |
| 1M | $0.405 | $3.375 | |
| — | $0.0635 / min | ||
| 1M | $2.025 | $12.15 | |
| 128K | $0.0702 | $0.2006 | |
| — | $0.046 / image | ||
| — | $0.0026 / min | ||
| 1M | $0.3375 | $1.35 | |