---
id: "sakana/fugu-max"
also: ["sakana/fugu-max-20260911", "vercel/sakana/fugu-max"]
card_usd_per_m: "2.0 in, 6.0 out, at sakana"
cheapest_list_usd_per_m: "2.0 in, 6.0 out, at sakana on openrouter"
cheapest_effective_usd_per_m: "1.7221 in, 6.0 out, at sakana on openrouter"
context: 1000000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-09-11"
reasoning: ["max", "xhigh", "high"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "web_search_options"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 2
---
# Sakana: Fugu Max

Fugu Max orchestrates our largest pool of models to push the cost–performance Pareto frontier. It dynamically finds efficient combinations of expert agents, aiming to improve model performance and cost efficiency together.