Claude Haiku 5.5 replaces Haiku 4.5 - Changelog

Claude Haiku 5.5 (claude-haiku-5-5) replaces Haiku 4.5 in TeamDay's model picker. Anthropic released it on October 7.
1M token context window (up from 200k) and up to 128k output tokens (up from 64k).
Priced by prompt length: $0.10 / $0.50 per million tokens (input / output) for prompts up to 100k tokens, with cache hits at $0.01. Prompts over 100k tokens cost $0.50 / $2.50. Haiku 4.5 was $1 / $5.
It uses Anthropic's newer tokenizer, so the same text counts as about 30% more tokens than on Haiku 4.5.
It's the first Haiku with reasoning effort. TeamDay starts it at medium, Anthropic's default, and you can pick anything from low to max.

Existing agents and chats set to Haiku 4.5 move to Haiku 5.5 automatically. You don't need to do anything.

Opus 5.5: the default for everyday and complex work.
Sonnet 5.5: half Opus 5.5's price, for routine work at volume.
Fable 5.1: the most capable option, for the hardest and longest-running tasks.
Haiku 5.5: fastest and cheapest, for quick answers and high-volume work.