Claude Haiku 5.5
Anthropic's newest small model, built for high-volume, cost-sensitive work. Available in the Claude API and Claude Code.

Details
- Costs about 75% less to run than Haiku 4.5 on average: $0.10 input and $0.50 output per million tokens for prompts under 100K tokens, $0.50 and $2.50 above that
- First Haiku model with an adjustable effort setting, so you can trade speed for more careful answers
- Anthropic positions it as a helper model that Opus 5.5 or Sonnet 5.5 can hand smaller tasks to, and for speed-sensitive uses like live customer support and browser automation
- 1M token context window, and it is now the default Haiku model on the Anthropic API (model id claude-haiku-5-5)
- Available on the Claude Platform API, in Claude Code, and through AWS, Google Cloud, and Microsoft Azure
Best for
Repetitive jobs run at volume: summarizing, classifying, tagging, and pulling data out of documents.
When to use it
You're running the same task hundreds or thousands of times and cost or speed matters more than top-end reasoning.
Who benefits
Teams building their own agents or automations on the Claude API, especially ones that hand smaller steps to a cheaper model.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →