modelbenchmark.io

Gemini 3.7 Flash (Vertex AI, US)

Google · gemini-3-7-flash-us

Compare

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Specification

most-agreed values

Context
1M
Max output
66K
Released
2026-08-13
Knowledge cutoff
2026-03
Retires
Open weights
no
Input
text, image, video, audio, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.75
Output
$3.75
Cache read
$0.075
Cache write
$0.0417

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
edenai$0.75$3.75$0.075$0.04171M66K

More from Google

most-hosted first