Sakana AI Launches Fugu Max and Fugu Ultra v2 for Cheaper, Stronger Multi-Agent Orchestration
Sakana AI released Fugu Max and Fugu Ultra v2, API-only orchestrator models that route tasks across model pools to cut costs and boost multi-step reasoning.
Sakana AI released Fugu Max and Fugu Ultra v2, two orchestrator models that route queries across a pool of third-party and open-weights models, including the NVIDIA Nemotron family. Fugu Max is priced at $2 per million input and $6 per million output tokens, 40-60% cheaper per output token than Sonnet 5, GPT 5.6 Terra, and Kimi K3, and reportedly wins 6 benchmarks including Terminal Bench 2.1 and GPQA Diamond. Fugu Ultra v2 targets complex multi-step reasoning, scoring 48.3 on Chartography and 74.3 on DeepSWE. Both are live through Sakana's OpenAI-compatible API only, with no open weights and no EU/EEA availability.
- Fugu Max costs $2/$6 per million input/output tokens, 40-60% below Sonnet 5, GPT 5.6 Terra, and Kimi K3
- Sakana reports best overall scores on six benchmarks including Terminal Bench 2.1, GPQA Diamond, and SWEFish
- Fugu Ultra v2 scores 48.3 on Chartography and 74.3 on DeepSWE, ahead of pricier frontier models
- Both ship via an OpenAI-compatible API only; no open weights and no EU/EEA availability
- Architecture builds on ICLR 2026 papers TRINITY and Conductor using fine-tuning, evolution, and reinforcement learning
- AI models
- Fugu MaxFugu Ultra v2NVIDIA Nemotron
From the original article
3 min read at marktechpost.com
Sakana AI has released Fugu Max and Fugu Ultra v2, 2 models built on the same learned orchestration architecture. Fugu Max routes tasks to lean open and specialized models, including NVIDIA Nemotron, at $2/$6 per 1M tokens. Fugu Ultra v2 targets peak capability, scoring 48.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.