Google / google/gemini-3.1-flash-live-preview

Gemini 3.1 Flash Live Preview - access through LLMTR

Stands out in real-time voice applications that need spoken dialogue, acoustic nuance, and multimodal awareness. A strong preview layer for voice-first assistants.

Technical specifications

Canonical IDgoogle/gemini-3.1-flash-live-preview
ProviderGoogle
Context window128,000 tokens
OperationsREALTIME_SESSION
Modalitiestext, audio, image, video

Pricing

A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
REALTIME_SESSIONINPUT_TEXTPER_1M_TOKENS$0.750000
REALTIME_SESSIONOUTPUT_TEXTPER_1M_TOKENS$4.50
REALTIME_SESSIONINPUT_AUDIOPER_MINUTE$0.005000
REALTIME_SESSIONINPUT_IMAGEPER_MINUTE$0.002000
REALTIME_SESSIONINPUT_VIDEOPER_MINUTE$0.002000
REALTIME_SESSIONOUTPUT_AUDIOPER_MINUTE$0.018000
REALTIME_SESSIONTOOL_CALLPER_1K_CALLS$14.00

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.1-flash-live-preview","messages":[{"role":"user","content":"Hello"}]}'

Related models