Gemini 3.5 Live Translate Preview benchmarks, pricing and specs
Gemini 3.5 Live Translate Preview is a Google model with no published release date that takes audio input and produces text and audio. It costs $0.0368 per audio minute and accepts up to 131,072 tokens of context.
- Per audio minute
- $0.0368
- Context window
- 131K
Data verified October 11, 2026 · Dataset 2026-10-12
Key facts
- Provider
- Model family
- Gemini 3.5
- Release date
- Not reported
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Input
- audio
- Output
- text, audio
- Task families
- audio
- Declared capabilities
- realtime voice, speech translation
Gemini 3.5 Live Translate Preview pricing
It is the most expensive of 5 current audio models priced per audio minute.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Google's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
No independent benchmark has published a result for Gemini 3.5 Live Translate Preview yet. It is still compared below on price, context and capabilities.
Strengths, cautions and best uses
Strengths
- Google documents low-latency real-time speech-to-speech translation across 70+ languages
Cautions
- This preview endpoint supports translation only, rather than tools or instructions, and may change before stable release
Best for
- Realtime spoken-language translation
Alternatives to Gemini 3.5 Live Translate Preview
The closest current audiomodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Gemini 3.8 Flash TTS
- 63% cheaper per audio minute, $0.0135 vs $0.0368
Gemini 3.8 Flash-Lite TTS
- 76% cheaper per audio minute, $0.009 vs $0.0368
Eleven Flash v2.5
- From ElevenLabs
Eleven Multilingual v2
- From ElevenLabs
Compare Gemini 3.5 Live Translate Preview with
Other Gemini 3.5 models
Gemini 3.5 Live Translate Preview FAQ
How much does Gemini 3.5 Live Translate Preview cost?
Gemini 3.5 Live Translate Preview costs $0.0368 per audio minute at the standard tier. It is the most expensive of 5 current audio models priced per audio minute. Source: Google, verified October 11, 2026.
What is the context window of Gemini 3.5 Live Translate Preview?
Gemini 3.5 Live Translate Preview accepts up to 131,072 tokens of context. It can return up to 65,536 tokens in one response. That ranks #2 of 7 current audio models by context length.
Is Gemini 3.5 Live Translate Preview open source or API only?
Gemini 3.5 Live Translate Preview is available through Google's API only; its weights are not published.
What are the best alternatives to Gemini 3.5 Live Translate Preview?
The closest current alternatives by price and measured performance are Gemini 3.8 Flash TTS (63% cheaper per audio minute, $0.0135 vs $0.0368), Gemini 3.8 Flash-Lite TTS (76% cheaper per audio minute, $0.009 vs $0.0368), Eleven Flash v2.5 (from ElevenLabs) and Eleven Multilingual v2 (from ElevenLabs).
Sources
- Gemini 3.5 Live Translate · Google · official · verified August 18, 2026 · CC-BY-4.0
- Gemini Live API · Google · official · verified August 18, 2026 · CC-BY-4.0
- Gemini Developer API pricing · Google · official · verified October 11, 2026
Cite this page
Van Data Team. "Gemini 3.5 Live Translate Preview Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/gemini-3-5-live-translate-preview
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Gemini 3.5 Live Translate Preview fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls