Gemini 3.8 Live

Realtime voice Google Verified Released Sep 15, 2026
  • In Input modalities: TextImageAudio Out Output modalities: TextAudio
  • Reasoning· low, medium, high
  • Tool use

Prices

1 offering · prices as listed
Gemini API (opens in a new tab) Official Global · USD gemini-3.8-live
ConditionsInput/ 1M tokensOutput/ 1M tokensAudio
Input/ 60 secondsOutput/ 60 seconds
Standard ——$0.005$0.018
Text tokens $0.75$4.50——
Image tokens $1.00———
Audio tokens $3.00$12.00——
Video tokens $1.00———

Prices from Gemini API pricing (opens in a new tab) (checked Nov 3, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Max input
128K
Max output
65.54K
Structured output
—
Built-in tools
Web search
Knowledge cutoff
Jan 2025
Model ID

Not stated on Google’s pages: reasoning can be off, voices, languages.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers realtime voice models yet. We will cite one when its license allows.

  • Sep 15, 2026Release Google releases Gemini 3.8 Live models Gemini 3.8 Live (gemini-3.8-live) and Gemini 3.8 Live Extended Thinking (gemini-3.8-live-extended-thinking) are generally available as audio-to-audio models on the Live API.
  1. 2 new prices on Gemini API Audio (Input) $0.005 · Audio (Output) $0.018
  2. New realtime voice model

Sources

Google’s official policies: data use, privacy, terms →

Google · United States · ai.google.dev

Snapshots, the same family and other models from this provider