Sakana AIText Generation/v1/ai/chatReasoning

Fugu Max API

Access Sakana AI's Fugu Max through one API key. Multi-agent orchestration at a workhorse price.

Sakana AI's cost-performance Fugu model. Fugu is a learned multi-agent orchestration system that routes work across specialist models, with a 1M token context window and 128K output tokens.

Full Docs Get API Key

Takes 30 seconds.

Fugu Max API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated September 27, 2026.

Token type	Price
Input	$2.95 / 1M tokens
Output (incl. reasoning)	$8.86 / 1M tokens
Context window	1M tokens

What it costs	Per job	Per 1,000
Chat reply1K input + 500 output tokens	$0.0074	$7.38
RAG answer8K input + 800 output tokens	$0.031	$30.69
Agent step with tools30K input + 2K output tokens	$0.106	$106.22
Long document summary100K input + 2K output tokens	$0.313	$312.72

4,900+

Developers

2.3M+

API calls served

184

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see Fugu Max respond in real time.

POST/v1/ai/chatsakana/fugu-max

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

Fugu Max specs

Provider	Sakana AI
Model ID	sakana/fugu-max
Endpoint	/v1/ai/chat
Type	Text Generation
Context window	1M tokens
Max output	128K tokens
Reasoning	Yes
OpenAI-compatible	Yes — /v1/ai/chat/completions

How to get a Fugu Max API key

1
Create an account
Sign up at yepapi.com with Google or email. It takes about 30 seconds.
2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
3
Call Fugu Max
Send a request to /v1/ai/chat with the x-api-key header and model "sakana/fugu-max".
4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓

Multi-agent orchestration

Fugu is not a single monolithic model: a router model is trained to decompose a task and dispatch it across specialist agents, then assemble the result — a different architecture from the frontier labs' dense models.

✓

Price-to-performance

At $2.95 per 1M input and $8.86 per 1M output tokens, Fugu Max is the affordable tier of the family, well-suited to high-volume reasoning and agent workloads.

✓

1M token context, 128K output

Handles up to 1,000,000 input tokens and returns up to 128,000 output tokens per call, so large documents and long agent histories fit in a single request.

✓

Tools, web search and structured output

Supports function calling, JSON schema structured outputs, reasoning effort control, and built-in web search options.

Quick start

Copy this snippet and start making calls with Fugu Max.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "sakana/fugu-max",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Fugu Max vs similar models

Every model below runs on the same API key — switch by changing the model ID.

Model	Provider	Price	Context
Fugu Max	Sakana AI	$2.95 in / $8.86 out per 1M	1M
Fugu Ultra v2	Sakana AI	$7.38 in / $44.31 out per 1M	1M
Nemotron 3 Super	NVIDIA	$0 in / $0 out per 1M	262K
Qwen3.7 Flash	Qwen	$0.04 in / $0.19 out per 1M	1M
Solar Mini 4	Upstage	$0.07 in / $0.30 out per 1M	524K
Nemotron 3.5 Lightning	NVIDIA	$0.10 in / $0.30 out per 1M	262K
DeepSeek V4 Flash	DeepSeek	$0.13 in / $0.27 out per 1M	1.0M
Qwen 3.5 Flash	Qwen	$0.10 in / $0.38 out per 1M	1M

Why use Fugu Max through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

Fugu Max API — pricing, context window & access

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than one large network, Fugu is a learned multi-agent orchestration system: a language model trained to route parts of a task to specialist agents and combine their answers. It offers a 1,000,000-token context window and up to 128,000 output tokens per response.

Through YepAPI you call Fugu Max on an OpenAI-compatible endpoint with a single key — the same key that reaches GPT-6, Claude, Gemini and the SEO, SERP and scraping APIs.

What is Fugu Max?

Fugu Max is Sakana AI's affordable Fugu tier. Sakana's approach differs from the frontier labs: instead of scaling a single dense model, Fugu trains an orchestrator that breaks a problem into parts, hands each to a specialist model, and merges the results. Fugu Max applies that system with a cost-optimised set of agents, so you get multi-step reasoning, tool use and web search at a price closer to a mid-tier model than a flagship. Fugu Ultra v2 is the higher-performance sibling for harder tasks.

Build with Fugu Max via YepAPI

YepAPI serves Fugu Max on the OpenAI-compatible /v1/ai/chat endpoint. Point your base URL at YepAPI, add your key, and set the model string to fugu-max (or sakana/fugu-max). Function calling, structured outputs and reasoning effort pass through unchanged. Stepping up to Fugu Ultra v2 or across to GPT-6 Astra for the hardest steps is a one-string change per request.

Fugu Max API pricing — $2.95 / 1M input, $8.86 / 1M output

Fugu Max costs $2.95 per 1M input tokens and $8.86 per 1M output tokens through YepAPI, pay per token with no minimums. That places it in the mid-tier price band alongside models like GPT-6 Sol, while the multi-agent architecture and 128K output ceiling make it suited to long agentic runs that would be expensive on a flagship.

Fugu Max for agents and high-volume reasoning

Fugu Max fits workloads where many tasks each need real reasoning but the per-task budget is small: research assistants, coding agents on routine tickets, document pipelines that extract, verify and summarise. Built-in web search options let it ground answers without an extra retrieval step, and the 1M-token window keeps long agent transcripts in context.

Start generating in 30 seconds

Pay per call, no subscriptions.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
Marcus T.
SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
Priya S.
Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Jake R.
Indie Hacker

Frequently asked questions

Sakana AI's cost-performance Fugu model. Fugu is a learned multi-agent orchestration system that routes work across specialist models, with a 1M token context window and 128K output tokens.

Fugu Max costs $2.95 per 1M input tokens and $8.86 per 1M output tokens through YepAPI, billed per request with no monthly fee. For example, a chat reply (1K input + 500 output tokens) costs about $0.0074.

Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Fugu Max and every other model — no separate Sakana AI account or waitlist.

Use "sakana/fugu-max" as the model on /v1/ai/chat. The short alias "fugu-max" also works.

Yes. Point the OpenAI SDK at https://api.yepapi.com/v1/ai with your YepAPI key and set model to "sakana/fugu-max". Streaming works the same way, so existing OpenAI code only needs the base URL and key changed.

Fugu Max supports a 1M token context window with up to 128K output tokens per request.