Rules checked against first-party pages on July 21, 2026

Choose among Fugu, Fugu Ultra, and Fugu Cyber

Answer three factual questions. The result follows the visible rule order below and can also say that no managed Fugu model is the safe starting point.

Your constraints

What this tool will return

A starting option, the exact reasons that fired, and a reminder to verify it on your own workload.

The complete decision order

  1. Region first. Official product pages say Fugu is currently unavailable in the EU and EEA, so the tool stops instead of naming a model.
  2. Auditability before performance. If every internal route must be visible, compare a self-managed graph before using a managed pool.
  3. Defensive security. Fugu Cyber is the documented specialist, but it requires access approval and is pay-as-you-go only.
  4. Provider exclusions. Standard Fugu lets you remove specific agents from its pool; Ultra uses a fixed full pool.
  5. Quality-first work. Ultra is the documented full-pool option and routes between one and three agents.
  6. General default. Start with standard Fugu, then keep it only if a blind task evaluation justifies the cost and latency.

Sources: Sakana AI model catalog and Sakana AI product page.

What is deliberately not in the score

Budget is not used because Sakana AI does not publish a fixed token allowance for each subscription on the public pricing page. Vendor benchmark ranks are not treated as your expected result. The chooser also does not infer legal or security authorization from a dropdown.