Sakana AI has released Fugu Max and Fugu Ultra v2 , 2 new models in its Sakana Fugu family. Fugu is not a single foundation model. It is a learned orchestrator that routes work across a pool of other models behind 1 API. The new release tunes that architecture for 2 missions. Fugu Max targets the best output per dollar. Fugu Ultra v2 targets the highest capability on hard, multi-step tasks. Is it deployable? Yes, as a hosted API. Both models are live today through Sakana’s OpenAI-compatible API. There are no open weights to self-host, and Sakana does not offer the service in the EU/EEA. Why Sakana Frames This as a 2-Axis Problem Sakana’s argument is direct. Real workloads are judged on capability and cost together. Sending a simple data lookup to a multi-trillion-parameter model wastes money. A better system picks the cheapest machinery that can still solve the task. Sakana team describes this with the Pareto frontier . On that frontier, gaining quality costs more, and cutting cost loses quality. Fugu Max and Fugu Ultra v2 share 1 core orchestration architecture. Only the optimization target differs. The release follows a fast cadence. Fugu entered beta in April, reached general availability in June, and added Fugu-Cyber and a Claude Code interface in July. How Fugu Orchestration Works The Sakana Fugu’s Technical Report describes Fugu models as language models in their own right. They read a query and build an agentic scaffold for it on the fly. Training combines large-scale fine-tuning, evolutionary algorithms, and reinforcement learning. The system builds on 2 ICLR 2026 p
Source: MarkTechPost