WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,924 posts

minimax-m3.1POST

Using unlimited M3.1 Flash via mcode from Codex to halve quota usage

A user has Codex offload deterministic skills to mcode running M3.1 Flash with GPT as reviewer, already producing Remotion videos this way and reporting roughly half the quota used.

老范讲故事🎙️
@lukfanArchived 4 days agoOriginally posted 2026.10.23
老范讲故事🎙️ @lukfanOriginally posted 2026.10.23
Open original on X

现在MiniMax-M3.1-Flash不限量使用。 于是我给Codex下了指令: mcode cli可用,将技能拆分,部分确定性任务,转移到mcode中去跑,最终由GPT验收。 现在开始重组技能执行过程,前提是不能降低最终交付质量。 我昨天已经用这个方式,Codex调用mcode,mcode跑remotion做视频了。 省一半额度。

x.com/lukfan/status/2113469542114767162Archived 2026.10.24 12:11