Gemma 4 26B A4B
AvailableGemma 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...
- Context
- 262.1K tokens
- Max output
- 235.9K tokens
- Input / 1M tokens
- $0.076per 1M tokens
- Output / 1M tokens
- $0.26per 1M tokens
- Listed since
- Apr 3, 2026
Prices and model data from OpenRouter
Where it's availableProviders · 1
| Provider | Input / 1M tokens | Output / 1M tokens | Status |
|---|---|---|---|
| OpenRouter | $0.076 | $0.26 | Available |
Published benchmark results
From independent leaderboards, each credited to its publisher.