Fugu Ultra overview
Fugu Ultra by Sakana AI
Fugu Ultra API orchestrates specialized AI agents to tackle complex, multi-step tasks, delivering strong results in coding and research.
Fugu Ultra specs
- Model ID
sakana/fugu-ultra- Developer
- Sakana AI
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What is Fugu Ultra API?
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family, released on June 15, 2026. Unlike a standard monolithic language model, it is a learned multi-agent orchestration system trained to dynamically route tasks across a swappable pool of underlying models and recursively coordinate instances of itself.
Fugu Ultra is grounded in two ICLR 2026 papers, TRINITY and Conductor, which show how a system can learn to assemble, route, and coordinate expert agents for each task without relying on hand-designed workflows.
Complex coding and code review
Fugu Ultra coordinates expert agents to catch bugs other models miss. Users report it surfaces 20+ issues where other tools find only 3, making it the go-to model for thorough code review.
Research and paper reproduction
From a single instruction, Fugu Ultra autonomously reads a paper, implements it, runs training, evaluates results, and analyzes gaps, for hours, without supervision.
Cybersecurity analysis
Given a scoped instruction, Fugu Ultra drives a full security assessment end-to-end: recon, XSS/SQLi checks, auth review, and a structured report with evidence and retest steps, staying in scope throughout.
Competitive ML and Kaggle
Fugu Ultra runs hundreds of experiments autonomously, adapting hyperparameters and training recipes to find the best result, outperforming frontier models on ML research benchmarks.
Patent and literature investigation
Mapping 20+ papers and patents, normally 3–4 days of work, can be completed in hours, including connections between papers a human researcher might miss.
Fugu Ultra vs. the Alternatives
Use cases
Fugu Ultra is documented as suited for Kaggle competitions, where its deeper expert-agent orchestration is used to tackle hard, high-stakes optimization problems.
It is also documented for paper reproduction, where users rely on it to reconstruct and verify complex research workflows and results.
Another stated use case is cybersecurity analysis, with early users applying it to demanding security work and complete cybersecurity assessments.
It is further documented for literature and patent investigations, where it is used for deep document-oriented research and analysis.
Capabilities
- Reasoning
- Streaming
- Structured outputs
- Function calling
- Web search
Fugu Ultra API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $5.29 | 1M tokens |
| Output | $31.74 | 1M tokens |
| Cached input | $0.529 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Fugu Ultra vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Fugu Ultra | $5.29 | $31.74 |
| Sakana Namazu | $1.01 | $4.23 |
| Fugu Max | $2.12 | $6.35 |
| Fugu Ultra v2 | $5.29 | $31.74 |
 GPT Chat Latest | $5.29 | $31.74 |
How to use the Fugu Ultra API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "sakana/fugu-ultra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "sakana/fugu-ultra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "sakana/fugu-ultra",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Fugu Ultra
Related articles
Fugu Ultra FAQ
What is the context window of Fugu Ultra?
Fugu Ultra has a 1,000,000 tokens context window and can return up to 128,000 tokens.
What inputs and outputs does Fugu Ultra support?
Fugu Ultra takes image, text as input and returns text.
What is the model ID for Fugu Ultra?
Use sakana/fugu-ultra as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was Fugu Ultra released?
Fugu Ultra became available on June 24, 2026.
How much does Fugu Ultra cost?
Fugu Ultra costs $5.29 input and $31.74 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Fugu Ultra support streaming?
Yes, Fugu Ultra can stream responses as they are generated.
Can Fugu Ultra read images?
Yes, Fugu Ultra accepts image input alongside text.
Who created Fugu Ultra?
Fugu Ultra was built by Sakana AI.