Fugu Ultra v2 overview
Fugu Ultra v2 by Sakana AI
Fugu Ultra v2 API orchestrates specialised AI agents across complex, multi-step coding, research and agentic workloads, now with file input and always-on reasoning.
Fugu Ultra v2 specs
- Model ID
sakana/fugu-ultra-v2- Developer
- Sakana AI
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What is Fugu Ultra v2 API?
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family and the direct successor to Fugu Ultra. Rather than a standard monolithic language model, it is a learned multi-agent orchestration system: a model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.
It is optimised for complex, multi-step reasoning, coding and agentic workflows. Orchestration tokens are billed as standard input and output tokens. Compared with Fugu Ultra it adds document (file) input alongside text and images, and reasoning is always on.
Complex coding and code review
Coordinates expert agents across a large codebase, surfacing issues that a single-pass review misses.
Research and paper reproduction
From a single instruction, reads a paper, implements it, runs training and analyses the gap between reported and reproduced results.
Long-context document work
The 1,000,000-token context window plus file input suits contract review, due diligence and multi-document synthesis in one request.
Agentic workflows
Always-on reasoning, tool calling and web search make it suited to long-running autonomous tasks rather than single-turn chat.
Use cases
Complex multi-step reasoning is a documented use case for Fugu Ultra v2. It is also documented as suited to autonomous research and full-stack software development.
It is documented for coding-related work, including real-world software engineering and code review. It is also documented for visual reasoning and data interpretation, including chart analysis and document or chart analysis.
Capabilities
- File input
- Reasoning
- Streaming
- Structured outputs
- Function calling
- Vision
- Web search
Fugu Ultra v2 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 v2 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Fugu Ultra v2 | $5.29 | $31.74 |
| Sakana Namazu | $1.01 | $4.23 |
| Fugu Max | $2.12 | $6.35 |
| Fugu Ultra | $5.29 | $31.74 |
 GPT Chat Latest | $5.29 | $31.74 |
How to use the Fugu Ultra v2 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-v2",
"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-v2",
"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-v2",
"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 v2
Fugu Ultra v2 FAQ
What is Fugu Ultra v2?
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family and the successor to Fugu Ultra. Rather than a monolithic language model, it is a learned multi-agent orchestration system that routes tasks across a swappable pool of underlying models and recursively calls instances of itself.
How does Fugu Ultra v2 differ from Fugu Ultra?
It adds document (file) input alongside text and images, and reasoning is always on. The 1,000,000-token context window and the orchestration approach carry over unchanged.
Who builds Fugu Ultra v2?
Sakana AI.
How large is the context window?
1,000,000 tokens, with up to 128,000 tokens of output.
How is orchestration billed?
Orchestration tokens are billed as standard input and output tokens. Requests above 272,000 tokens move to a higher pricing tier.
What inputs and outputs does Fugu Ultra v2 support?
It takes image, text and file input and returns text.
Does Fugu Ultra v2 support tool calling?
Yes. It supports function calling, structured outputs, streaming and web search.
What is Fugu Ultra v2 best suited for?
Complex, multi-step work where depth matters more than latency: thorough code review, research and paper reproduction, long-document synthesis, and long-running agentic workflows.
How do I call Fugu Ultra v2 on AI/ML API?
Send a request to the chat completions endpoint with the model id sakana/fugu-ultra-v2. The model also answers to the alias fugu-ultra-v2.
What is the Fugu Ultra v2 model ID?
Use sakana/fugu-ultra-v2 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.