jevbooks

← All projects

llm-router

inikhildubey/llm-router

Routes LLM requests by scoring prompt complexity.

Classification & Routing1.00Runner-up: Verification & GuardrailsFunnelTraffic light
Automated README summary

Automatically summarized from the README on 10 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

An intelligent gateway that scores incoming prompt complexity and routes to the most cost-effective LLM tier. For developers seeking to reduce LLM costs while maintaining quality.

How it uses Jev

Jev's System One decision-making concept inspired the triage step, which uses an async LLM-based complexity score (0-10). The score is mapped to a model tier via thresholds, then the request is dispatched via litellm.

Technique worth stealing

Using a fast, calibrated complexity score to triage requests before expensive execution.

Try it

uvicorn app:app --reload

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.34
  • Shows a System One patternnot found in the excerpt0.22
  • Describes handling uncertaintynot found in the excerpt0.06
  • Reports measured numbersnot found in the excerpt0.06
  • Is a runnable toolFound in material0.86
  • Top-10 learning shortlist signalnot found in the excerpt0.19
  • Is a replica of the modelunclear0.55
  • Solves a common problem (0–2)score on a 0–2 scale1.90 / 2
  • About JevFound in material0.61
Signals
Jev is core to the project0.34Shows a System One pattern0.22Describes handling uncertainty0.06Reports measured numbers0.06Is a runnable tool0.86Top-10 learning shortlist signal0.19Is a replica of the model0.5500.51Solves a common problem (0–2)1.90 / 2012

no-judgment band (0.40–0.60)

Design patterns
Traffic light0.83Funnel0.81Fail open, fail closed0.40Ghostwriter0.2000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 10 Oct 2026.