AI Model Watch
Models / Google

Gemini 3.5 Live Translate

Preview

Real-time speech-to-speech translation across 70+ languages. NOT on Google's deprecations table at all (checked 2026-08-19) — it was found by diffing the models and pricing pages against the catalog — so no release date and no lifecycle field is published for it anywhere first-party, and released stays null. Audio-only billing: input $3.50 or $0.0053 per minute, output $21.00 or $0.0315 per minute, at 25 tokens per second of audio, which Google states works out to roughly $0.0368 per minute. Google's current models page publishes no input/output token limits for this endpoint (read 2026-08-19), so context_window and max_output_tokens are null rather than carried over from a page that no longer states them. Lifecycle read first-party from Google's deprecations table on 2026-08-19.

Gemini 3.5 Live Translate by Google costs $3.50 per 1M input tokens and $21 per 1M output tokens ($7.88/1M blended). It is in preview.

Last verified: 19 Aug 2026 · sourced from official provider documentation

Provider
Google
Status
Preview
Input price
$3.50 / 1M tokens
Output price
$21 / 1M tokens
Cached input
—
Blended price
$7.88 / 1M tokens
Context window
—
Max output
—
Modality
text, audio, audio-out
Open weights
No — API only
Knowledge cutoff
—
Released
—
API string
gemini-3.5-live-translate-preview

Source: Google official documentation ↗

See also

Explore more

All Google models→

Prices, context windows and lifecycle status for every Google model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Gemini 3.5 Live Translate — questions & answers

How much does Gemini 3.5 Live Translate cost?

Gemini 3.5 Live Translate is priced at $3.50 per 1M input tokens and $21 per 1M output tokens ($7.88/1M blended at a 3:1 input-to-output ratio).

Is Gemini 3.5 Live Translate deprecated?

No — Gemini 3.5 Live Translate is in preview and not currently scheduled for deprecation or retirement in our tracker.

Does Gemini 3.5 Live Translate support image or vision input?

Our catalog lists Gemini 3.5 Live Translate's modalities as text, audio, audio-out; image/vision input is not among them.

Can I self-host Gemini 3.5 Live Translate?

No — Gemini 3.5 Live Translate is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini 3.5 Live Translate?

The API model identifier for Gemini 3.5 Live Translate is "gemini-3.5-live-translate-preview" when calling Google's API.