The fastest Sakana model is Fugu Ultra at 7 output tokens per second.
AI models ranked by output speed (tokens per second, p50). The fastest large language models — and the fastest AI models overall — for low-latency and high-throughput applications.
The fastest Sakana model is Fugu Ultra at 7 output tokens per second.
modelgrep tracks 1 Sakana models with live benchmarks, speed, latency and per-provider pricing. 1 of them qualify for this ranking.