Claude Haiku 5.5: a small model at a much lower price
What is it?
Anthropic's new small model is built for high-volume work such as summarization, classification and subagents (helper agents a larger model delegates pieces of a task to). It has a 1M-token context window and is the first Haiku-class model to support the effort setting, which controls how much it reasons. Pricing for requests up to 100K tokens is $0.10 input and $0.50 output per million tokensVendor claim. Anthropic also halved cache-read pricing for Sonnet 5.5 on the same day.
Why does it matter?
Anthropic says it is about 75% cheaper than Haiku 4.5 on averageVendor claim. Moving the costliest steps of an agent pipeline (summarizing, compacting, lookups) onto this model could change your unit economics. It also reports 72.4% on the OSWorld 2.1 computer-use benchmarkVendor claim. The same day, a browser and computer-use toolset (beta) was added to the SDK, so this is a good time to try a low-cost browser automation agent.
Maturity
GAAvailable now on the API and on AWS, Google Cloud and Microsoft Foundry. Code written for Haiku 4.5 may break, though. budget_tokens now returns a 400 error, adaptive thinking is on by default, and the tokenizer has changed. Read the migration guide first.
How to track it
- Independent checks on the ~75%-cheaper claim and the OSWorld 2.1 score: watch the Artificial Analysis model page for measurements.
- When the SDK browser and computer-use toolset leaves beta, plus further Haiku 5.5 changes: check the Claude Platform release notes weekly.
- Fixes for migration issues (
budget_tokens400 errors, tokenizer change): watch for updates to the migration guide.