Its Claude API identifier is claude-haiku-5-5.
The comparison table lists pricing from $0.10 per million input tokens and $0.50 per million output tokens. It specifies a 1 million-token context window, a 128,000-token maximum output, adaptive thinking, and medium default effort. The documentation lists matching model IDs for Amazon Bedrock, Google Cloud, Microsoft Foundry, and Claude Platform on AWS.
The source describes Haiku 5.5 as the fastest model in the current Claude lineup. It does not provide benchmark results, measured latency, request limits, regional availability, or a workload-level cost comparison with prior Haiku models. Those claims cannot be established from the supplied documentation.