Haiku 5.5 at max reasoning burns more tokens than Opus 5.5 max, user finds
haider1 · x · 2026-10-08
User haider1 flags a cost quirk with Anthropic's Haiku 5.5: cheap per task but extremely token-hungry — at max reasoning effort it consumes more tokens than Opus 5.5 max, over 2x more than fable 5.1 max, and far more than the astra models.
He asks where this tradeoff actually makes sense, inviting real-world use cases.
Related event: Claude Haiku 5.5 ranks 2nd in intelligence but real costs spiral(16 posts)→
More from Models
- Tracking how Claude's utopian visions have evolved over time — amplifiedamp · 2026-11-22
- LLMs have always self-corrected: Opus 5.5 caught its own mistake mid-generation in real time — amplifiedamp · 2026-11-22
- DINOv3 patches encode position so strongly by default that you need to clean them up — StephanSturges · 2026-11-22
- Thinking Machines open-sources Inkling-2 Mini: 26.4B MoE with native vision and 1M context — solyarisoftware · 2026-11-22
- Open-weight models can no longer be suppressed: Pirate Face turns model weights into immortal torrents — esrtweet · 2026-11-22
- 'Compression of the RH proof has begun': AI circles buzz over unverified Riemann claim — teortaxesTex · 2026-11-22