fugu-ultra-v2
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 that routes work across models.
料金： 入力：100 万トークンあたり 1200 クレジット（約 $6.00）、出力：100 万トークンあたり 7200 クレジット（約 $36.00）。
料金更新日
今日はどんなお手伝いができますか？
このデモページにはクライアントの完全な記憶機能はありません。すべての機能をご利用いただくには、クライアントまたは CLI から接続してください。
Sakana AI のほかの AI モデル
Fugu Ultra v2 API on ModelFold
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 that routes work across models. Try Fugu Ultra v2 in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the Fugu Ultra v2 API
Fugu Ultra v2 at a glance
Fugu Ultra v2 is a chat model from Sakana AI. It accepts text, images and files (such as PDF) as input and returns text, with a context window of up to 1M tokens.
Use it without hosting anything
On ModelFold you call Fugu Ultra v2 with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of Fugu Ultra v2
Up to 1M tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Understands images and files (such as PDF)
Besides text, Fugu Ultra v2 accepts images and files (such as PDF) as input, so a single request can combine instructions with visual or other media.
Function calling
Fugu Ultra v2 supports tool (function) calling: describe your functions in the request and the model returns structured calls your code can run — the basis for agents and integrations.
Adjustable reasoning effort
Choose a reasoning effort level (low, medium or high) per request to balance depth of thinking against speed and token usage.
Structured outputs
Ask for JSON that follows a schema (response_format), which makes extraction, classification and system integrations more reliable.
How to Use Fugu Ultra v2 on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how Fugu Ultra v2 responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "fugu-ultra-v2" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with Fugu Ultra v2
Autonomous agents
Build agents that plan multi-step tasks, call your tools and APIs, and keep working toward a goal across long sessions.
Analysis and complex reasoning
Work through research questions, data interpretation, planning and other problems that need careful step-by-step reasoning.
AI coding assistants
Generate, explain, debug and refactor code, review pull requests and work through multi-file changes in developer tools and IDE plugins.
Long-document workflows
Feed in long reports, contracts, manuals or codebases and ask for summaries, comparisons and answers grounded in the material.
Frequently Asked Questions
What is Fugu Ultra v2?⌄
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 that routes work across models.
Which inputs does Fugu Ultra v2 support?⌄
Fugu Ultra v2 accepts text, images and files (such as PDF) and returns text. Through ModelFold you can send text and images (OpenAI-style image_url content); in the Playground you can also attach documents, which are converted to text.
How long is the context window of Fugu Ultra v2?⌄
Up to 1M tokens, shared between your input and the model’s output.
Does Fugu Ultra v2 support function calling?⌄
Yes. Fugu Ultra v2 supports tools / function calling through the standard tools parameter of the chat completions API.
How is Fugu Ultra v2 billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call Fugu Ultra v2 through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "fugu-ultra-v2", using your ModelFold API key as the Bearer token.
| 入力 | 1200 クレジット 1M tokens≈ $6.00 |
| 出力 | 7200 クレジット 1M tokens≈ $36.00 |
トークン単位で課金し、入力と出力は別料金です。思考トークンは出力に含まれます。Playground でも同じ計算を使います。
API ドキュメントを見る →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"fugu-ultra-v2","messages":[{"role":"user","content":"Hello"}]}'