Fastest Sakana Models

Quick answer · Updated June 2026

The fastest Sakana model is Fugu Ultra at 44 output tokens per second.

44 t/sSpeed

$5.00Input /M

1MContext

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

1S
fugu-ultra
ReasoningToolsJSON+1$5.00/M · 7.6s ttft · 1M ctx
44 t/s
Speed

Frequently asked

What is the fastest Sakana model?

The fastest Sakana model is Fugu Ultra at 44 output tokens per second.

How many Sakana models are there?

modelgrep tracks 1 Sakana models with live benchmarks, speed, latency and per-provider pricing. 1 of them qualify for this ranking.

More Sakana rankings

Sakana: Smartest LLMs Sakana: Best LLMs for Coding Sakana: Best LLMs for Design & Frontend Sakana: Lowest-Latency LLMs Sakana: Cheapest LLMs Sakana: Best Free LLMs Sakana: Best Reasoning LLMs Sakana: Best Vision LLMs Sakana: Best LLMs for Agents Sakana: Best Open-Source LLMs Sakana: Longest-Context LLMs

All rankings

Small & Fast LLMs Smartest LLMs Best LLMs for Coding Best LLMs for Design & Frontend Lowest-Latency LLMs Cheapest LLMs Best Free LLMs Best Reasoning LLMs Best Vision LLMs Best LLMs for Agents Best Open-Source LLMs Longest-Context LLMs