Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

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...

Modalities
ImageTextVideo
In / out price
₩123 / ₩597
1M
Context
262.14K
Released
Apr 3, 2026

Pricing

Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.

Input (prompt)₩123 / 1M
Output (completion)₩597 / 1M
Cache read₩12 / 1M
Cache write

1,000 input tokens plus 1,000 output tokens costs about ₩0.71955.