Claude Haiku 5.5
As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced at $1/million input and $5/million output - relatively exp…
Marked important, but published more than 30 days ago, so it moved down to this band.
On this page12 sections
The editors' notes below — why it matters, the context, the learning path — are written in Chinese.
Record
The signal
#As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced at $1/million input and $5/million output - relatively expensive even back then, and a full 10x the price of OpenAI's GPT-6 Luna, released last month. The new Haiku exactly matches the price of GPT-6 Luna - $0.10/$0.50 - up to 100,000 tokens. Beyond 100,000 tokens the price increases 5x to $0.50/$2.50. Luna itself has a price increase at 272,000 tokens but only to $0.20/$0.75. Haiku 5.5 also uses a new, less generous tokenizer. My Claude Token Counter tool shows that the same long prompt uses around 1.25x as many tokens with Haiku 5.5 compared to Haiku 4.5, so there's a hidden price increase there. If your workloads fit in 100,000 tokens, Haiku is the same price as Luna and reports higher benchmark scores. Above 100,000 tokens, Luna looks like a much better deal. The most recent release of llm-anthropic finally fixed it so I don't need to ship a new version of that plugin for every new model. I tested the new model like this: llm install -U llm-anthropic llm anthropic refresh llm -m claude-haiku-5.5 "Generate an SVG of a pelican riding a bicycle" -o thinking_effort low Pelicans Here are pelicans for low, medium, high, xhigh, and max. The new Haiku doesn't let you disable reasoning, and defaults to medium. I got a good bicycle frame for everything beyond low. The low effort pelican cost 0.0936 cents and took 7 seconds. This max effort pelican (with a reasoning trace that start…
Why now
Why it matters
#最便宜的一档第一次在操作电脑和终端任务上有了可用的成绩，子智能体、批量摘要这类调用的成本结构会跟着变。但新分词器和关不掉的推理意味着账单不会按标价降九成，要按自己的提示重新算。
Background
Technical context
#Anthropic 的模型按档位分为 Fable、Opus、Sonnet 和 Haiku，Haiku 是最便宜、最快的一档。分词器决定一段文字被切成多少 token，换分词器后同样的文字可能计费更多。推理档位越高，思考 token 越多，而思考 token 按输出计费。
Audience
Who should care
#Next
Learning path
#- 先读本站 9 月 28 日的 Claude Sonnet 5.5 信号，看同一代里上一档的成绩与价格
- 读《模型选型与约束匹配》，想清楚哪些调用真的需要大模型
- 拿自己的 20 条典型提示，分别统计 Haiku 4.5 与 5.5 的 token 数与费用
- 读《推理服务容量规划》，把推理档位带来的延迟下限算进容量
Network
Where it sits in the network
#How this signal connects to neighbouring technologies, skills and background knowledge. Follow any link to keep exploring.
Further thought
Follow-up questions
#- 你的提示里有多少超过 10 万 token？按分段价算，实际单价是多少？
- 换成 Haiku 5.5 后，同样的提示 token 数变了多少？
- 哪些子任务可以从 Sonnet 下放到 Haiku 5.5？用什么指标判断没有变差？
Publication record
Featured in
#The briefings that carried this signal, newest first; the last row is the weekly review of its week. The tag is the section it ran in.
技术简报 - 2026-10-08
Immediate attentionWeekly review · Oct 5 – Oct 11
Worth tracking
Sources