Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Multi-agent model for routing expert agents across complex analytical tasks
Quality-first multi-agent model for hard research, analysis, and competitions
Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Sakana Namazusakana/sakana-namazu | 262.144K | $0.95 | $4 | 2026-08-03 | |||
| Fugusakana/fugu | 1M | — | — | 2026-06-15 | |||
| Fugu Ultrasakana/fugu-ultra | 1M | $5 | $30 | 2026-06-15 | |||
| Sakana: Namazusakana/namazu | 262.144K | $0.95 | $4 | — | |||
| Sakana: Fugu Maxsakana/fugu-max | 1M | $2 | $6 | — | |||
| Sakana: Fugu Ultra v2sakana/fugu-ultra-v2 | 1M | $5 | $30 | — |