modelbenchmark.io

Gemini 3.8 Live Extended Thinking

Google · gemini-3-8-live-extended-thinking

Compare

Speech generation model for controllable voice, narration, and audio delivery

Specification

gemini listing

Context
131K
Max output
66K
Released
2026-09-15
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, audio
Output
text, audio

Price

US dollars per million tokens · gemini list price

Input
$0.75
Output
$4.50

Rate limits

as listed

Requests per minute
10
Tokens per minute
250,000

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
geminivendor$0.75$4.50——131K66K—
vercel$0.75$4.50——00—

More from Google

most-hosted first