Gemini 3.8 Live Extended Thinking

Google · Veröffentlicht Sept. 2026

Ist es das Richtige für dich?

Real-time voice agents that must reason through multi-step problems mid-conversation
Calling tools and APIs in the background while the conversation continues
Multilingual voice: Google says it detects and switches between 97 languages mid-conversation

Workloads that need structured outputs, context caching, code execution or the Batch API, none of which the model supports
Inputs above 131,072 tokens
Sensitive data on the free tier, which Google's pricing page marks as used to improve its products

Excellent

Top Artificial Analysis Speech to Speech Index score (82.6) with background reasoning

Very Good

Async function calling while audio streams; vendor-reported 68.6% on τ-Voice

Poor

Structured outputs are not supported on this model

Eingabe

$0.75 / 1M (text)

Ausgabe

$4.50 / 1M (text)

Kontext

131K in, 65K out; audio $3/$12 per 1M

Benchmark	Wert	Quelle
Artificial Analysis Speech to Speech Index (High)	82.6	Quelle
Big Bench Audio (vendor-reported)	97.7%	Quelle
τ-Voice (vendor-reported)	68.6%	Quelle
Sierra τ-Voice-banking (vendor-reported)	35.1%	Quelle

Die Uhr läuft ab dem ersten Tag. Änderungen erscheinen hier, sobald sich unser Urteil weiterentwickelt.