modelbenchmark.io

DiffusionGemma

Google · diffusiongemma

Compare

DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window.

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-09-19
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.05
Output
$0.15
Cache read
$0.025

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.05$0.15$0.025—262K33K—

More from Google

most-hosted first