Back to Explore
Google: Gemma 4 26B A4B (free)
Google·Released 2026-04-03
Open Source262K ctxMultimodal
About
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Related Models
Pricing
Input
$0.00
per 1M tokens
Output
$0.00
per 1M tokens
Blended
$0.00
per 1M tokens
Cheaper than 92% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.00
Monthly
$0.00
vs. Similar Models
Olmo 3 7B Think
$0.00
Arcee AI: Trinity Large Preview (free)
$0.00
Arcee AI: Trinity Large Thinking (free)
$0.00
Arcee AI: Trinity Mini (free)
$0.00
Performance
Context Window
262K
tokens
Larger than 60% of models
Max Output
33K
tokens
13% of context
Context Window Comparison
MoonshotAI: Kimi K2.6
262KSame
MoonshotAI: Kimi K2.7 Code
262KSame
Nex AGI: Nex-N2-Pro
262KSame