sakana

Fugu Max

text inputimage inputtext outputlanguageGateway catalog

Use an endpoint supported by this model.

Get a key for this setup →
Thinking guide →
const response = await fetch('https://api.minirouter.sh/v1/chat/completions', {  method: 'POST',  headers: {    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,    'Content-Type': 'application/json',  },  body: JSON.stringify({    model: 'sakana/fugu-max',    messages: [{ role: 'user', content: 'Why is the sky blue?' }],    max_tokens: 1024,  }),}) const data = await response.json()console.log(data.choices[0].message.content)
Read docs →
Input / 1M
$2.1
Output / 1M
$6.3
Context
1M
Max output
1M
Overview

Overview

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.
Model type
language
Context window
1,000,000
Maximum output
1,000,000
Input / 1M tokens
$2.1
Output / 1M tokens
$6.3
Released
2026-09-10

Prices include the MiniRouter fee. Compatibility snapshot: 2026-08-06. Input: text, image. Output: text. Compare text-model alternatives or estimate token costs for your workload.

Endpoints

Endpoints

Authenticate with a MiniRouter API key. Requests cannot carry provider credentials or OIDC upstream authentication; to use your own provider key, save it in Provider keys.
Paths
/v1/chat/completions/v1/messages/v1/responses
Structured output

Not enforced; a requested format is dropped and the answer is plain text. How it works

Captured parameters: max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning.

API

API

Switch between Chat Completions, Messages and client configurations in the setup panel. Every snippet keeps the model ID unchanged.
Base URLhttps://api.minirouter.sh/v1
Model IDsakana/fugu-max
Providers

Providers

MiniRouter selects from the configured routes below. Priority is the catalog order, not a latency or availability score.
ProviderPriorityInput / 1MOutput / 1MParametersAccess
vercel
1$2.1$6.3max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoningMiniRouter balance

Every model, one key.