Sakana's Fugu Max routes a mixed model pool at $2/$6 per 1M tokens, claims tier-best benchmark score
SakanaAILabs · x · 2026-09-11
Sakana AI 官宣 Fugu Max，主打「模型池编排」架构：同时调度 NVIDIA Nemotron 及开源/闭源模型混合池，通过可替换的多模型路由实现抗中断韧性——官方称「模型韧性不是备份功能，而是架构本身」。
- 定价：输入 $2 / 输出 $6 每百万 token
- 性能宣称接近顶级前沿模型，但成本低 2-6 倍
- 同档 6 个关键 benchmark 综合得分最佳
More from Infra
- MySQL recursive CTEs time out at 500M rows; C# BFS answers in 2.7ms vs NebulaGraph 23.6ms — JeremyCMorgan · 2026-10-28
- Token demand on OpenRouter grew 27x to 165T weekly, open models now serve 72% — FinanceYF5 · 2026-10-28
- AI's unusual bet: buying compute for years, selling intelligence by the token — vaibhavbetter · 2026-10-28
- OpenAI's Will Depue says compute locks in US primacy as 'end of human history' nears — willdepue · 2026-10-28
- Malaysia has overtaken Singapore in data center capacity, planned buildout 10x — bytebot · 2026-10-28
- Why Cloudflare Is the Best Platform to Build AI Agent Operating Systems — ritakozlov · 2026-10-28