Grok 4.7 early test: highly token-efficient, overnight task used only ~6% quota

xdNiBoR · x · 2026-09-22

A power user's early impressions of Grok 4.7: clear improvements over 4.6, still very cheap, and seemingly highly token-efficient — a large overnight task consumed only about 6% of usage. Verdict: roughly met expectations, and doing more work at the same cost is highly valuable for heavy users.

Related event: Heavy Users Report Big Token Efficiency Gains in Grok 4.7(2 posts)→

Original post →

More from Models

Models channel →