Set Haiku 5.5 autocompact to 100K to stay in cheaper tier

Anthropic's Lydia Hallie says API-billed users can set Haiku 5.5's autocompact window to 100K to remain in the cheaper token pricing tier.

The setting is saved per model, so it applies only to Haiku, including subagents, and is configured with /model haiku followed by /autocompact 100k.

Per the background post, prompts under 100K tokens cost $0.10/$0.50 per million tokens with $0.01 cache reads, versus $0.50/$2.50 with $0.05 cache reads above 100K.