People use Jev to pick a model before a task.
Used Jev to change GPT-6's reasoning effort inside Codex mid-task, raising it when stuck and lowering it for routine steps, cutting Astra costs 50%.
The original post
People use Jev to pick a model before a task. I made it change GPT-6's reasoning effort inside Codex DURING the task. More thinking when stuck. Less for routine steps. 50% lower Astra costs in my tests. Faster runs, without breaking prompt caching.
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the coding & developer tools page.
Related Jev cases
The gains aren’t free: Jev can't generate text Comparing
Dev toolsClassification
Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev
GamesDev tools
The open-source local version Laya's response speed crushes
Dev tools
Whose Codex still hasn't installed Jev's batch ultimate
AgentsDev tools
Keep browsing: all 1173 Jev cases · more from @miu21590 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post