GPT-6.1 Sol Quota Nearly Impossible to Exhaust at Medium, User Observes
bytebot · x · 2026-10-05
A user reports GPT-6.1 Sol at medium reasoning is almost impossible to hit quota limits with, unlike GPT-6 Astra which burns through at the same setting. Opus 5.5 and Sonnet 5.5 also seem strangely token-efficient. Unverified usage observations.
More from Models
- Ethan Mollick slams OpenAI's GPTs shutdown: enterprises and educators left behind — emollick · 2026-10-05
- Midjourney CEO shares model arena leaderboards with per-model notes, dumps full data — DavidSHolz · 2026-10-05
- Stealthy German lab Aleph Alpha drops open-weight Kolibri: 78B params, 3.46B active, 1M context — skdh · 2026-10-05
- FrontierMath Tier 3, predicted by Terence Tao to resist AI for years, now saturated — Eliv_nurotic · 2026-10-05
- ChatGPT is now 'full of upsell slop', complains paying Pro plan user — weswinder · 2026-10-05
- Matt Shumer: Claude Opus 5.5 with Codex-level computer use would be unbeatable — mattshumer_ · 2026-10-05