Google DeepMind

Gemini 3.5 Live Translate Preview

Generally availableProprietary16K context

Summary

Gemini 3.5 Live Translate Preview is a proprietary language model from Google DeepMind, released on 9 Jun 2026. It accepts audio and generates audio and text, with a 16K-token context window and up to 16K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $3.50 per million input tokens and $21 per million output tokens (Gemini API), across 1 provider we track.

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date9 Jun 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window16K (16,384 tokens) [models.dev]
Max output16K tokens [models.dev]
Knowledge cutoffJan 2025 [models.dev]
InputAudio [models.dev]
OutputAudio and text [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Gemini 3.5 Live Translate Preview API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Gemini API
gemini-3.5-live-translate-preview
$3.50$21–16Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Gemini 3.5 Live Translate Preview?

Gemini 3.5 Live Translate Preview has a context window of 16,384 tokens (16K) and can generate up to 16,384 tokens in a single response, according to models.dev.

How much does the Gemini 3.5 Live Translate Preview API cost?

Through Gemini API, Gemini 3.5 Live Translate Preview costs $3.50 per million input tokens and $21 per million output tokens. Prices last verified 18 Nov 2026.

Is Gemini 3.5 Live Translate Preview open source?

No. Gemini 3.5 Live Translate Preview is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API.

When was Gemini 3.5 Live Translate Preview released?

Google DeepMind released Gemini 3.5 Live Translate Preview on 9 Jun 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GPT-Realtime-1.5OpenAI23 Feb 202632K$4$16Closed
gpt-realtime-whisperOpenAI7 May 202616K––Closed
Grok Voice STT 1.0xAI4 Aug 202615K––Closed
Arrow 2Quiverai16 Sept 2026131K$4$20Closed
Grok Voice STT 1.0xAI17 Sept 202615K––Closed
Arrow 2 TelosQuiverai16 Sept 2026131K$6$30Closed

Change history

  • Max output changed from 33K to 16K

Sources