
What happened
Anthropic released Claude Haiku 5.5 on October 7, 2026 at $0.10 input / $0.50 output per MTok for prompts up to 100K tokens — one-tenth of Haiku 4.5 — with 1M context and five effort levels.
Why it matters
At that price, the same budget buys far more model calls, though the new tokenizer makes the same text about 30% more tokens, so the sticker price overstates the saving.
WHO IT HITSDevelopers and small teams running high-volume, narrow-scope LLM (AI text generation) workloads — summarization, compaction, sub-agent grunt work — get a much cheaper option, but anyone with existing Haiku 4.5 integrations faces a migration that can fail silently in their own code.
Summaries like this, in your inbox every morning.
Haiku 5.5 arrives almost exactly a year after Haiku 4.5 (October 15, 2025) and completes the 5.5 generation, following Opus 5.5 on September 22 and Sonnet 5.5 on September 28. Anthropic bills it as its cheapest, fastest and smartest small model, and the pricing table backs the cheap part: $0.10 input for prompts up to 100K tokens is one-twentieth of Sonnet 5.5's $2.00. The same announcement also halved Sonnet 5.5's cache-read price from $0.20 to $0.10, which Anthropic says cuts Sonnet 5.5 costs by about 20% on most agentic tasks — a saving that reaches teams who never touch Haiku.
The migration story is where the release gets sharp. Because adaptive thinking is on by default and temperature, top_p, top_k and assistant prefill now trigger 400 errors, a model-ID swap is no longer sufficient. The author's own stock-screening tool RakuScan illustrates the trap: it reads response.content[0].text, which was always a text block under Haiku 4.5 but may now be a thinking block with no .text attribute. The resulting AttributeError slips past handlers that only catch Anthropic SDK errors, and the caller has no try block around it, so a fallback notification path never runs — the failure surfaces the next morning as a missing alert.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Foxconn is expanding its FoxBrain LLM into vision-language models and vision-language-action models, targeting…

Cumulative shipments of chips using Alibaba DAMO Academy's XuanTie RISC-V processor IP have surpassed 6 billio…

Researchers ran 91 decoy US accounts across three income levels and three racial groups; ads began appearing a…

The PHLX Semiconductor Index fell eight straight sessions from Oct

NEC opened BluStellar Studio in October on the first floor of its Tokyo Minato headquarters, a corporate-only…

Hakuhodo began offering its "Image Similarity Checker" to client companies on October 19, automatically search…
