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
GambarTeksVideo
Harga in / out
₩123 / ₩597
1M
Context
262,14 rb
Dirilis
3 Apr 2026

Pricing

Harga dinyatakan dalam KRW. Perubahan pada nilai tukar atau margin akan langsung diterapkan.

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

1.000 token input ditambah 1.000 token output berbiaya sekitar ₩0,71955.