AI & Agents
Sakana
Last updated 2026-06-23 · benchmark measured 2026-08-09 — deterministic & reproducible
Sakana Fugu is a multi-agent system delivered through a single API that orchestrates multiple AI models.
Is Sakana production-ready?
Legit.Show scores Sakana 59 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Sakana (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 67/100
- Accessibility — 95/100
- Security — 25/100
- Privacy — 0/100
- Reliability — 100/100
- Standards — 85/100
- Discoverability — 40/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 237 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: OpenGraph image.
Who built it
product account @SakanaAILabs
Who it's for
AI developers · Software engineers · Enterprise teams · Complex task automation · API integration builders
Pricing
Token Plan: Fugu Ultra $5 input/$30 output per 1K tokens (higher rates for context >272K); Fugu Cyber $6 input/$36 output per 1K tokens; Subscription Plan: Standard $20/month, Pro $100/month, Max $200
Visit Sakana → · Alternatives to Sakana → · How this was measured →