Jev Routes Codex Models by Task

Yoshinobu Matsubara uses Jev in Codex to route tasks among GPT-6 Astra, GPT-5.6 Sol, Terra, and Luna, aiming to reduce token consumption. Video generation is routed to MiniMax Hailuo (H3).

View on X cost100円以下time30秒

Yoshinobu Matsubara@corocorodev𝕏

Codexにルーター「Jev」を噛ませてモデル自動最適化ルーティングを構築。タスクに応じてGPT-6 Astra 、GPT-5.6 Sol、Terra、Lunaを賢く切り替えることで、トークン消費を極限まで圧縮。さらに動画生成はMiniMax Hailuo（H3）に流し込み、このクオリティのライブ映像を【30秒 / 100円以下】で出力できました。

Sep 21, 2026X postsView on X

The author says the setup produced live footage in 30 seconds for under 100 yen.

Also filed under Triage & routing

Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using Jev AI. It is designed to speed up agent loops by routing decisions without relying on large generative LLMs at every step.
Local Candidate Scoring with Jev
Bev performs local Jevfire-style candidate scoring using ternary models and a System One API. Its probabilities are candidate-relative.
Team Agent Workspace for Routing and Model Selection
Agentconnect is a team agent workspace that uses Jev typed decisions for response routing and model selection.
Desktop AI Assistant with Jev Plugin
PyGPT is a desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.