GPT-6 Luna exposes thinking levels from light to max
seanwbren · x · 2026-09-23
A user spotted that GPT-6 Luna supports adjustable reasoning levels ranging from light thinking all the way to a max setting, continuing OpenAI's tunable thinking-tier design.
More from Models
- Early hands-on: Opus matches GPT-6 Astra at 2D/3D graphics work — cedric_chee · 2026-09-23
- Early tester: Opus 5.5 fixes the writing, no more slop since Opus 4.6 — TheZvi · 2026-09-23
- Early hands-on: Opus 5.5 strong across tasks, reportedly 3x cheaper than Fable — doodlestein · 2026-09-23
- Vibe check: Opus 5.5 is 30% faster, 40% cheaper, pulling Codex converts back to Claude — every · 2026-09-23
- Opinion: Never release your top-tier model before mid and low-tier ones — Angaisb_ · 2026-09-23
- AA Intelligence Index Leak Claims GPT-6 Sol Disappoints, Opus 5.5 Dominates — queenofartists · 2026-09-23