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
輸入 / 輸出價格
￦123 / ￦597
1M
Context
26.21萬
發佈日期
2026年4月3日
Pricing
價格以 KRW 為單位。匯率或利潤變動會立即反映。
| 輸入 (prompt) | ￦123 / 1M |
| 輸出 (completion) | ￦597 / 1M |
| Cache read | ￦12 / 1M |
| Cache write | — |
1,000 個輸入 tokens 加上 1,000 個輸出 tokens 的費用約為 ￦0.71955。