Sakana AI Launches Fugu Max, a Multi-Agent Orchestrator Routing Tasks to Leanest Capable Models
tkasasagi · x · 2026-09-18
Sakana AI announced Fugu Max, now live on Sakana Chat and free for everyone, alongside Fugu Ultra v2.
- The pitch is a "dynamic architecture": instead of treating models as a static menu, Sakana argues the frontier that matters is the capability-vs-cost Pareto frontier.
- Fugu Max orchestrates the company's largest pool of open-weights and specialized models to date, including the NVIDIA Nemotron family, and dynamically routes each task to the leanest model capable of handling it.
- The result, per Sakana, is performance within striking distance of elite models at a fraction of the cost. A blog post and the chat product are both available to try.
Related event: Sakana AI Launches Fugu Max and Fugu Ultra v2(2 posts)→
More from coding & agent
- Junior backend dev asks: is learning RAG, vector DBs and agents worth it yet? — Effective_Emphasis21 · 2026-09-18
- WebMCP draws developer buzz as a way to bring MCP into the browser — nickbaumann_ · 2026-09-18
- Demo: Claude with built-in Cowork and Artifacts builds a multiplayer game from one prompt — felixrieseberg · 2026-09-18
- Six Coding Agents Share the Same Plan Mode Shape but Split on Context After Approval — RunAI_Coder · 2026-09-18
- EvoSkill-GUI: training-free skill evolution lifts GUI agents by up to 16.2% — Bofan Chen · 2026-09-18
- Testing Non-Deterministic LLM Agent Pipelines with Property-Based Assertions — Repulsive_Sugar_5252 · 2026-09-18