Fugu Max
Developed by Sakana, Fugu Max is a cost-performance model that utilizes a multi-agent orchestration system to route tasks. It supports text, image, and file inputs, and features built-in reasoning and tool-calling capabilities.
Fugu Max specs and pricing
- Provider: Sakana
- Released: September 11, 2026
- Context window: 1M tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $2.00 input / $6.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Fugu Max is good at
- Analyzing complex documents and images
- Tasks requiring multi-step reasoning
- Automated workflows using external tools
To-dos to try with Fugu Max
- Upload a 500-page technical manual and summarize the troubleshooting section.
- Analyze a set of project diagrams and generate a list of potential implementation risks.
- Use tool-calling to fetch live data and incorporate it into a written report.
FAQ
- What is the core architecture of Fugu Max? Fugu Max is not a single monolithic model, but rather a learned multi-agent orchestration system designed to route tasks effectively.
- Can this model process visual information? Yes, Fugu Max accepts both image and file inputs in addition to standard text.
- How much does Fugu Max cost? Fugu Max costs $2.00 per million input tokens and $6.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.44 credits ($1 = 100 credits).
- What is the context window of Fugu Max? Fugu Max can read up to 1M tokens at once and write up to 128K tokens in one reply.
- Can I use Fugu Max without coding? Yes. In todo.is you pick Fugu Max 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.