Jev in production › Model and agent routing
opencode-jev-router
opencode-jev-router asks Jev how much reasoning each OpenCode step needs; the author measured the same 44/44 pass rate as fixed high effort with 14% fewer tokens (robertn702).
14%measured against a baseline, as published by the source
- Use
- Model and agent routing
- Industry
- Developer tools
- Form
- Open-source tool
- Stage
- Beta
- Plugs into
- OpenCode
- Listed
- 2026-09-30
- Found via
- github
- Repository
- robertn702/opencode-jev-router
- Stars
- 10
- Forks
- 0
- Last push
- 2026-10-06
- Language
- TypeScript
- License
- MIT
The README opens with
Keep the quality. Spend less reasoning. An OpenCode plugin that asks Jev how much reasoning each step needs, so one model handles quick edits and hard debugging without you switching effort levels by hand.
Across the tested GPT-6 Astra task mix, Jev and fixed high effort each solved 44/44 attempts, and Jev used 14% fewer output tokens (including reasoning) and finished 9% faster on average. Results on other workloads may differ. See the evaluation.
Badge
For the project's own README, linking back here:
Also used for model and agent routing
- Hermes Jev Skills ~0.4 s per turn
- Jev Codex Router ≈ −60 %
- Quicksilver 86%
- Grok Bot Jev Router 13.0×
- Jevstiller 4,000
- jev-use ~230 ms
- DuoMind 36%
- jevcache (kushals256) 394ms