modelbenchmark.io

Gemini 3 Flash Thinking

Google · gemini-3-flash-preview-thinking

Compare

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Specification

most-agreed values

Context
1M
Max output
66K
Released
2025-12-17
Knowledge cutoff
2025-01
Retires
Open weights
no
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.50
Output
$3.00
Cache read
$0.05

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.50$3.00$0.051M66K

More from Google

most-hosted first