article author demo
Replacing model-routing classifiers with Jev
Uses Jev as a four-tier difficulty classifier in place of NVIDIA NeMo Switchyard's router classifiers, with code.
Notes
40 calls (10 per tier): 40/40 correct, median 0.64–0.67 s, $0.000025–0.000027 per call; roughly 3x faster than Gemini 3.5 Flash and 10–11x faster than DeepSeek V4.
author demo — Result shown by its author. About this label
Destinations
Try a walkthrough
- Connect Jev to your app →
Set up the Python SDK, make a typed routing decision and keep the result under your application's control.
- Route the next step of an agent →
Let Jev choose a proposed next step, then apply an explicit allow, review or fallback policy before any tool runs.
Verification levels
- HTTP availability
- Link reachable ·
Method: bounded HTTP request with redirects. HTTP 200 · HTTP response only. Checked destination ↗ · Last reachable - Browser demo scenario
- Not checked
- Build
- Not checked
- Live API test
- Not checked