@timfduffy 2026-10-07 ♥61 ↻2 original ↗
Haiku 5.5 is quite cheap, matching GPT-6 Luna pricing for short context. Long context is 5x the cost though (2x for Luna). Previous reporting by Epoch has suggested that larger Claudes may use linear/sparse attention, but this pricing structure indicates Haiku may not. https://t.co/BvcE01HIqT
photo

author:timfduffy has-image kind:image kind:tweet on:claude-haiku-5-5 year:2026

cited on: claude-haiku-5-5

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.