ABOUT THIS MODEL

A federated LLM router with human-interpretable routing logic. Reduces inference costs by 40–70% by intelligently routing requests across model tiers. Privacy-preserving by design.

KEY HIGHLIGHTS
  • Evaluates prompts in 4ms and routes to cheapest competent model
  • Human-readable decision tables — no black-box routing
  • Privacy-preserving via federated learning
  • Drop-in middleware for any LLM API pipeline
SPECIFICATIONS
Cost Reduction40–70%
RoutingHuman-interpretable tables
PrivacyFederated learning
Latency4ms evaluation
TypeRouter · Middleware
LicenseMIT
Downloads5+

Need help deploying fugusashi?

We offer consulting, custom fine-tuning, and on-premise deployment for all our models.