Source-linked AI model
Google: Gemma 4 26B A4B
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...
- Provider
- Context window
- 262,144 tokens
- Input price
- $0.00000007 per token
- Output price
- $0.00000034 per token
- Source
- OpenRouter