modelbenchmark.io

Gemini 3.5 Flash Thinking

Google · gemini-3-5-flash-thinking

Compare

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Specification

most-agreed values

Context
1M
Max output
66K
Released
2026-05-19
Knowledge cutoff
2025-01
Retires
Open weights
no
Input
text, image, video, audio
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.50
Output
$9.00
Cache read
$0.15
Cache write
$0.0833

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
302ai$1.50$9.001M66K
nano-gpt$1.50$9.00$0.15$0.08331M66K

More from Google

most-hosted first