Opus 5.5's token usage is far more reasonable: 13-hour session on a 20x Max plan
majidmanzarpour · x · 2026-09-25
A developer reports his site now runs all chats on Claude Code: no more typing "continue," and noticeably smarter responses. He also notes Opus 5.5's token usage is much more reasonable — a single session ran 13 hours on max reasoning under a 20x Max plan.
More from Models
- CLM-8B part of scaling-ladder effort; multimodal CLM-35B due next month — viksit · 2026-09-25
- Polymarket gives SSI 53% odds of releasing its first public model by October 31 — Polymarket · 2026-09-25
- Psychometric profiling of nine LLMs shows score vectors can identify model identity — anselm · 2026-09-25
- Claude Opus 5.5 shows progress on 'sparks of AGI'-style task, higher tiers teased — iruletheworldmo · 2026-09-25
- AI pundit Tibo goes quiet after Opus 5.5 crushes rivals he said Anthropic couldn't serve — rexplosive · 2026-09-25
- User says Meta's Muse is good enough to 'retire' his self-built OpenClaw setup — analisereal · 2026-09-25