Claude Haiku 5.5: New Features, Pricing and Efficient AI Workflows
Analytics Insight, Monday, October 26th, 2026
Anthropic's Claude Haiku 5.5 adds a one million token context, adjustable effort levels and lower pricing than Haiku 4.5.
Analytics Insight reports that Anthropic introduced Claude Haiku 5.5 on October 7, 2026 as its fastest and most cost-efficient small model, claiming it costs about 75% less to operate than Haiku 4.5.
It supports up to one million tokens of context and 128,000 output tokens, up from 200,000 and 64,000, with API pricing of $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100,000 tokens.
It is the first Haiku model with adjustable effort levels and adaptive thinking, and can serve as a subagent alongside Sonnet 5.5 and Opus 5.5.
It is available on the Claude apps, the Claude API, Amazon Bedrock, Google Cloud and Microsoft Foundry.