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 | Plan | Est. / month | Included | Source date |
|---|---|---|---|---|
| free | $0.00 | — | 2026-09-18 | |
| standard | $0.48 | — | 2026-09-18 |