Haiku 5.5 targets the inexpensive end of agent work
Provider benchmarks and workload-dependent savings are not matched independent reruns. Tokenization, cache use, effort, retries and the prompt-length tier affect total cost; larger models remain better suited to complex tasks.
What was claimed?
Anthropic released Haiku 5.5 for narrow, high-volume tasks with adjustable effort. Input/output prices are $0.10/$0.50 per million tokens up to 100K prompt tokens, and $0.50/$2.50 above that boundary.
What does the evidence support?
Company claim, independent confirmation unresolved
Summarization, classification and compaction are useful places to test accepted-result cost. Sonnet 5.5 cache reads also fall to $0.10 per million tokens.
What are the limits?
Provider benchmarks and workload-dependent savings are not matched independent reruns. Tokenization, cache use, effort, retries and the prompt-length tier affect total cost; larger models remain better suited to complex tasks.
Claim or evidence date: 2026-10-07. Last verified: .
Colors classify evidence; they do not rank truthfulness. Explore hype versus reality →