Grok 4.7 burns nearly 3x tokens per task vs rivals, user claims

Angaisb_ · x · 2026-09-22

A user's test claims Grok 4.7 consumes nearly 3x as many tokens per task as Astra and more than 2x as many as Grok 4.6, arguing OpenAI is the only lab that seems to care about token efficiency — implying the real cost per task may be far higher than the sticker price suggests.

Related event: Grok 4.7 uses ~3x the tokens per task as Astra, tests show(2 posts)→

Original post →

More from Models

Models channel →