Sakana: Fugu Ultra v2: AI model
Fugu Ultra v2 is a multi-agent orchestration system tuned for the hardest tasks from Sakana AI with a 1M-token context window. Reachable from inside Iran through Hormouz.
- Context window:
- 1,000,000 tokens
- Input:
- $5/1M tokens
- Output:
- $30/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: Always thinks · max · xhigh · high
Fugu Ultra v2 is the top model of Sakana AI's Fugu family, and it is not a single model: a trained orchestrator sends parts of each task to a fixed pool of open and specialised models and can call copies of itself. The Ultra version puts answer quality first, for complex multi-step reasoning, autonomous research and full-stack software development. It supports image and PDF input and built-in web search; very long prompts are billed at a higher rate.
It accepts text, image and file (PDF) input and returns text, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting. Fugu Ultra v2 is commonly used for autonomous research, full-stack development, complex multi-step reasoning and deep analysis. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.
Pricing is usage-based: $5 per million input tokens and $30 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sakana/fugu-ultra-v2",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Sakana AI |
|---|---|
| Type | Text, Image |
| Context window | 1,000,000 tokens |
| Pricing | $5.00/M in · $30.00/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sakana/fugu-ultra-v2",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="sakana/fugu-ultra-v2",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "sakana/fugu-ultra-v2",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Sakana: Fugu Ultra v2 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Sakana: Fugu Ultra v2 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Fugu Ultra v2 cost?
- Pricing is usage-based: $5 per million input tokens and $30 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
- How do I access Fugu Ultra v2 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Fugu Ultra v2 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- What context window and capabilities does Fugu Ultra v2 have?
- It has a 1M-token context window, accepts text, image and file (PDF) input, and supports tool calling, structured JSON output and streaming. It always reasons before answering, and you choose how hard it thinks with the reasoning effort setting.
- What is Fugu Ultra v2 good for?
- Typical uses are autonomous research, full-stack development, complex multi-step reasoning and deep analysis.
Updated 2026-10-13