Skip to content
Dashboard

Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is Google's open-weight mixture-of-experts model with 26B total parameters and roughly 4B active per forward pass. Built on the Gemini 3 architecture, it supports function-calling, structured JSON output, native vision, and 140+ languages within a context window of 262.1K tokens.

File InputReasoningTool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'google/gemma-4-26b-a4b-it',
prompt: 'Why is the sky blue?'
})

More models by Google

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
2.4s
195tps
$1.50/M
$7.50/M
Read:$0.15/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
07/21/2026
1M
1.0s
479tps
$0.30/M
$2.50/M
Read:$0.03/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
07/21/2026
1M
2.2s
201tps
$1.50/M
$9/M
Read:$0.15/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
05/19/2026
1M
0.6s
251tps
$0.25/M
$1.50/M
Read:$0.03/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
03/03/2026
1M
4.4s
113tps
$2/M
$12/M
Read:
$0.2/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
02/19/2026
1M
0.8s
181tps
$0.50/M
$3/M
Read:
$0.05/M
Write:
$14/K
+ input costs
+3
google logo
vertex logo
12/17/2025