Claude Haiku 5.5 from Anthropic is now available on AI Gateway .

Haiku 5.5 is built for high-volume, cost-sensitive tasks such as summarization, context compaction, database queries, and classification. It can also handle coding subtasks alongside larger Claude models. It's the fastest Claude model at standard speed, making it useful for latency-sensitive applications such as live customer support and browser automation.

It's also the first Haiku model with adjustable effort . Choose low , medium , high , xhigh , or max to balance response quality, latency, and token usage. Adaptive thinking is enabled by default. You can disable thinking at low , medium , or high ; xhigh and max require it.

Haiku 5.5 supports Zero Data Retention on AI Gateway. Its biology and cybersecurity safeguards may cause it to decline some requests.

Use anthropic/claude-haiku-5.5 as the model ID in the AI SDK , compatible APIs , or coding agents . Set AI_GATEWAY_API_KEY for the API examples below.…