Anthropic launches Claude Haiku 5.5: $0.10/M input, 72.4% on OSWorld 2.1, about 75% cheaper than Haiku 4.5 on average
On Oct 7 Anthropic shipped Claude Haiku 5.5 (claude-haiku-5-5), completing the Claude 5.5 family. It targets high-volume, cost-sensitive work such as summaries, compaction, classification and coding subagents, and Anthropic calls it its fastest model at standard speed. Prompts up to 100K cost $0.10 input / $0.50 output per million tokens, and it is the first Haiku with effort levels. It scores 72.4% on the OSWorld 2.1 offline subset (Haiku 4.5: 15.7%) and 39.2% on Terminal-Bench 4.0. Sonnet 5.5 cache reads were cut 50% the same day, and Max/Team plans get monthly API credits.
Key Takeaways
- Pricing: prompts up to 100K cost $0.10 input / $0.50 output / $0.01 cache reads per million tokens ($0.50 / $2.50 above 100K) vs $1 / $5 for Haiku 4.5; Anthropic says about 75% cheaper on average (announcement)
- OSWorld 2.1 offline subset: 72.4% vs 15.7% (Haiku 4.5), 48.9% (GPT-6 Luna), 83.9% (Sonnet 5.5)
- Terminal-Bench 4.0: 39.2% (Haiku 4.5 0.0%, GPT-6 Luna 16.4%); FrontierCode 1.1 Main: 46.4% (Sonnet 5.5 xhigh 52.1%)
- First Haiku with low/medium/high/xhigh/max effort; Claude Code v2.1.293 makes it the default Haiku on the API with 1M context (release notes)
- Same day: Sonnet 5.5 cache reads cut from $0.20 to $0.10/M; Max 5x / 20x get $100 / $200 monthly API credits, Team $20 (Standard) / $100 (Premium) per seat pooled up to $500; not valid for interactive Claude Code, no rollover
Linked Models & Agents:
