Google

Gemini 3.5 Live Translate

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Modèle Audio et Vocal NatifOfficial Source Verified ↗
84
Intelligence Index

Gemini 3.5 Live Translate de Google est un modèle d’IA conçu pour la synthèse vocale naturelle, la transcription audio et le dialogue parlé en temps réel, offrant une fenêtre de contexte de 131K, une vitesse de 130 tokens/s, un indice d’intelligence de 84/100 et un tarif de $5/$20 par million de tokens.

Technical Specifications

Provider
Google
Category
flagship
Release Date
2026-06
Knowledge Cutoff
February 2026
Architecture
Low-latency neural speech-to-speech cross-lingual transformer
Parameters
Confidential
Context Window
131K tokens
Max Output
16K tokens
Cached Input Price
$1 / 1M tokens
Batch API Discount
20% off async batch
Consumer Subscription
$20 / month
Reasoning Mode
No (Standard)
Reasoning Effort Control
Fixed
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
No (Proprietary Cloud)
Input Modalities
audio
Output Modalities
audio, text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
API payloads are excluded from model training by default
Model License & Commercial Rights
Proprietary Commercial API (Google Terms)
Deployment & Cloud Availability
Google AI Studio API, Google Cloud Vertex AI
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
models/gemini-3-5-live-translate
Supported SDK & API Protocol
Google Gemini API (generateContent) + OpenAI-Compatible SDK
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2028+)
Production Rate Limits (RPM & TPM)
10,000 – 30,000 RPM (Tier 5 Enterprise) · 800,000 – 2,000,000 TPM
Long-Context Pricing Tier (>128K / >200K)
Flat rate ($5/1M in) across full 131K window
Prompt Cache Write & TTL Policy
Implicit + Explicit Context Caching at $1/1M with configurable TTL
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Built-in Google Search Grounding + Managed Python Code Execution Sandbox
Fine-Tuning & Distillation Support
Vertex AI Supervised Adapter Tuning & Context Distillation
Multimodal Tokenization Billing
Text BPE (~4 chars/token) · Audio (~25–32 tokens/sec)
Weights Precision & Quantization
Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
Minimum GPU VRAM Requirement
Zero Local VRAM Required (100% Serverless Cloud API)
Supported Inference Engines
Managed Google Cloud API
System Card & Safety Framework
Google DeepMind Frontier Safety Framework Verified
Enterprise Compliance (SOC2 / HIPAA / ZDR)
SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Engineering & Pricing Workbench

Gemini 3.5 Live Translate Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
$480.00$600.00
Monthly Savings: $120.00 (Caching/Batch)
Subscription ($20/mo) vs API

For single-user chat, a $20/mo subscription caps your bill below this API volume.

Break-even point: ~21 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

Gemini 3.5 Live Translate (Active)
$480.00
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Gemini 3.5 Live Translate:

Cascaded Monthly Bill:$133.50/mo
Saves $346.50/mo (72% cost reduction) vs sending 100% of traffic to Gemini 3.5 Live Translate.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (84)Reasoning (84)Knowledge (84)Speed (87)Context (75)Cost Value (58)
Gemini 3.5 Live Translate2026 Frontier Median
Chatbot Arena Elo
1420pts

Strengths

  • Fenêtre de contexte de 131K et capacité de sortie maximale de 16K tokens (Arena Elo 1420)
  • Débit rapide de 130 tokens/seconde avec une latence au premier token (TTFT) de 300 ms
  • Tarification API optimisée ($5/$20 par million de tokens) avec prise en charge du cache de prompts et des schémas JSON stricts

Limitations & Trade-offs

  • Modèle cloud propriétaire ne permettant pas le téléchargement local des poids sur serveur isolé
  • Pour les charges à très fort volume, l’activation du cache de prompts et de l’API Batch est recommandée

Editorial Assessment

Alliant un indice d’intelligence de 84/100, un contexte de 131K et un débit de 130 tok/s, Gemini 3.5 Live Translate s’impose comme une valeur sûre de la gamme Google.

Best for: Conçu pour la synthèse vocale naturelle, la transcription audio et le dialogue parlé en temps réel, l’intégration RAG et les pipelines de production évolutifs.

Frequently Asked Questions about Gemini 3.5 Live Translate

How much does the Gemini 3.5 Live Translate API cost per 1M tokens?+

Gemini 3.5 Live Translate by Google is priced at $5 per 1M input tokens and $20 per 1M output tokens. With prompt caching enabled, cached input tokens cost $1 per 1M tokens, and asynchronous Batch API requests receive a 20% discount.

Should I use a $20/month subscription or the Gemini 3.5 Live Translate pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Gemini 3.5 Live Translate's context window?+

Gemini 3.5 Live Translate features a 131K tokens context window, which equals approximately 98,304 English words or ~262 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 16,384 tokens.

Can I run Gemini 3.5 Live Translate locally on my own GPU (Open Weights)?+

No, Gemini 3.5 Live Translate is a proprietary closed-weights model hosted by Google. It cannot be downloaded for local GPU execution and must be accessed via Google's official API or cloud platform.

Does Google train on data sent to the Gemini 3.5 Live Translate API, and is commercial use allowed?+

API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Google Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Google AI Studio API, Google Cloud Vertex AI.

How does Gemini 3.5 Live Translate perform on coding and reasoning benchmarks?+

Gemini 3.5 Live Translate achieves a composite Intelligence Index of 84/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, N/A% on MMLU-Pro, and 1420 pts on Chatbot Arena Elo.

What is Gemini 3.5 Live Translate best used for?+

Gemini 3.5 Live Translate is best suited for: Conçu pour la synthèse vocale naturelle, la transcription audio et le dialogue parlé en temps réel, l’intégration RAG et les pipelines de production évolutifs.. Assessment: Alliant un indice d’intelligence de 84/100, un contexte de 131K et un débit de 130 tok/s, Gemini 3.5 Live Translate s’impose comme une valeur sûre de la gamme Google.

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: Google Translate & DeepMind Technical Report↗