Fugu Ultra
Fugu Ultra is a high-performance model developed by Sakana AI that utilizes a multi-agent orchestration system to route tasks. It supports both text and image inputs and features built-in reasoning and tool-calling capabilities.
Fugu Ultra specs and pricing
- Provider: Sakana
- Released: June 24, 2026
- Context window: 1M tokens
- Max output: 128K tokens
- Input: text, images
- Output: text
- Price: $5.00 input / $30 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Fugu Ultra is good at
- Complex reasoning tasks requiring multi-step logic
- Analyzing documents and images within a single workflow
- Automated tasks that require external tool integration
To-dos to try with Fugu Ultra
- Upload a series of technical diagrams and ask the model to summarize the design differences
- Provide a complex project brief and have the model break it down into a sequence of actionable steps
- Use tool-calling to fetch live data and incorporate it into a written report
FAQ
- What is the core architecture of Fugu Ultra? Fugu Ultra is built as a learned multi-agent orchestration system rather than a single monolithic model.
- Can this model process visual information? Yes, Fugu Ultra accepts both text and image inputs.
- How much does Fugu Ultra cost? Fugu Ultra costs $5.00 per million input tokens and $30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 18.2 credits ($1 = 100 credits).
- What is the context window of Fugu Ultra? Fugu Ultra can read up to 1M tokens at once and write up to 128K tokens in one reply.
- Can I use Fugu Ultra without coding? Yes. In todo.is you pick Fugu Ultra as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.