fugusashi
v1.3MITFederated LLM Routing Engine
QUICK GROUNDING SPECIFICATION (VERIFIED DATA)Updated: 2026-07-28 · Eulogik Open Weights
fugusashi v1.3 is a federated llm routing engine. Operates across Cost Reduction: 40–70% · Routing: Human-interpretable tables · Privacy: Federated learning · Latency: 4ms evaluation · Type: Router · Middleware · License: MIT. License: MIT.
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+
ACADEMIC & RESEARCH CITATION
Cite this Model & Architecture
If you utilize fugusashi in your academic research, benchmarks, or enterprise deployments, please cite our open-weight publication:
@misc{eulogik2026fugusashi,
title = {fugusashi v1.3: Federated LLM Routing Engine},
author = {Kishore, Gautam and Eulogik Systems Engineering},
year = {2026},
publisher = {Eulogik},
howpublished = {\url{https://eulogik.com/models/fugusashi}}
}Need help deploying fugusashi?
We offer consulting, custom fine-tuning, and on-premise deployment for all our models.