Google / google/gemini-2.5-flash-native-audio-preview-12-2025

Gemini 2.5 Flash Native Audio (Live API) - access through LLMTR

Designed for low-latency spoken interaction with more natural pacing and voice behavior. It stands out in voice assistants, real-time dialogue, and call-like experiences.

Technical specifications

Canonical IDgoogle/gemini-2.5-flash-native-audio-preview-12-2025
ProviderGoogle
Context window128,000 tokens
OperationsREALTIME_SESSION
Modalitiestext, audio, 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$0.500000
REALTIME_SESSIONOUTPUT_TEXTPER_1M_TOKENS$2.00
REALTIME_SESSIONINPUT_AUDIOPER_1M_TOKENS$3.00
REALTIME_SESSIONINPUT_VIDEOPER_1M_TOKENS$3.00
REALTIME_SESSIONOUTPUT_AUDIOPER_1M_TOKENS$12.00

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-2.5-flash-native-audio-preview-12-2025","messages":[{"role":"user","content":"Hello"}]}'

Related models