Pass IndexThe State of AISign in

Gemini Live 2.5 Flash Native Audio

Gemini Live 2.5 Flash Native Audio is a model by Google for speech, it stands 16th of 16 on τ³-Voice Leaderboard, and 2 sellers in the catalogue publish a price for it.

text + image + audio + video → text + audio · made by Google

$0.5$2per Mtok in / out
Google Vertex AI

Sold by 2 ways

SellerLaneRate
Google 0 ways$0.5per Mtok in$2per Mtok out$3per Mtok in, audio$12per Mtok out, audio
Google apinot on the seller's list todaystandard$0.5per Mtok in$2per Mtok out$3per Mtok in, audio$12per Mtok out, audioai.google.dev · read 2026-08-25
Google Vertex AI cloudstandard$0.5per Mtok in$2per Mtok out$3per Mtok in, audio$12per Mtok out, audioraw.githubusercontent.com · read 2026-09-16

Measured 1 standing

PlaceBoardMetricScore
16thof 16τ³-Voice LeaderboardPass^125.8

About

Gemini Live 2.5 Flash Native Audio — a text and audio model from Google, sold by one company from $0.5 in and $2 out per million tokens, placed 16th of 16 on τ³-Voice Leaderboard.

It takes text, images, audio and video and returns text and audio. The catalogue files it under speak. Only Google Vertex AI sells it, at $0.5 in and $2 out per million tokens. It stands 16th of 16 on τ³-Voice Leaderboard.

Every current figure

Maker
Google
Register
model
Takes
text + image + audio + video
Returns
text + audio
Licence
not read
Sellers
1
Price
$0.5 in and $2 out per million tokens — Google Vertex AI
Boards
1
Best place
16th of 16 — τ³-Voice Leaderboard

Known as 2 names

gemini-live-2.5-flash-native-audiogemini-2.5-flash-native-audio-preview-12-2025