# Claude Haiku 5.5: price, speed and when to use it By GO AI Team · October 21, 2026 Updated: October 21, 2026 Anthropic's Claude Haiku 5.5 costs from $0.10 per million input tokens and adds an effort setting. Benchmarks, limits and when to choose Haiku over Sonnet. ![Illustration titled Claude Haiku 5.5](https://goaichat.app/assets/img/blog/news-2026-10/claude-haiku-5-5.webp) Illustration by GO AI; not an actual product screenshot. ## The short version Choose Haiku 5.5 for frequent, well-defined tasks where speed and cost matter. For complex agent coding, Anthropic itself recommends Sonnet 5.5 or Opus 5.5. Test it on a sample of your real work before switching. Anthropic released Claude Haiku 5.5 on October 7, 2026. It is Anthropic's smallest and fastest model, and the company says it costs around 75% less to run on average than Claude Haiku 4.5 while scoring far higher on its published benchmarks. Small models matter because they handle the high-volume work: summaries, classification, support replies and the sub-tasks that bigger models hand off. Here is what Anthropic announced, where Haiku 5.5 is weaker than Sonnet, and how to test whether it fits your work. ## At a glance - **Released:** October 7, 2026 as claude-haiku-5-5 [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) - **API price:** US$0.10 input / $0.50 output per million tokens up to 100K tokens; $0.50 / $2.50 above [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) - **Where:** Claude Platform, Amazon Web Services, Google Cloud and Microsoft Azure [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) ## What is new in Claude Haiku 5.5 *What the source says* Anthropic calls Haiku 5.5 its cheapest, fastest and most capable small model so far. It is the first Haiku-class model with an adjustable effort setting, from Low to Max, so developers can trade cost and latency against capability. Pricing starts at US$0.10 per million input tokens and $0.50 per million output tokens for requests up to 100,000 tokens, rising to $0.50 and $2.50 for longer requests. Anthropic puts the saving versus Haiku 4.5 at about 75% on average: 90% for requests up to 100K tokens and 50% for longer ones. Source: [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) ## Benchmarks: a big jump over Haiku 4.5, still below Sonnet *What the source says* Anthropic reports 72.4% on the offline subset of OSWorld 2.1, against 15.7% for Haiku 4.5, and 45.9% on Humanity's Last Exam without tools, against 10.2%. On Terminal-Bench 4.0 it scores 39.2%, where Haiku 4.5 scored 0%. In the same tables Sonnet 5.5 scores higher on every benchmark listed, and Anthropic says Sonnet 5.5 and Opus 5.5 remain better choices for complex agentic coding tasks. Source: [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) ## Recommended uses and the limits Anthropic lists *What the source says* Anthropic recommends Haiku 5.5 for high-volume, cost-sensitive work such as summaries, database queries and classification; as a sub-agent working alongside Opus 5.5 or Sonnet 5.5; and for speed-sensitive tasks such as live customer support and browser use. It also lists limits: Haiku 5.5 uses a new tokenizer, so a task consumes slightly more tokens; its cybersecurity safeguards are stricter than Haiku 4.5's; and it runs slower than the Opus models in Fast Mode. - Good fit: summaries, tagging and routing, extraction, short support replies. - Good fit: sub-tasks that a larger model plans and checks. - Weaker fit: long, multi-step coding work that needs careful planning. Source: [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) ## Haiku 5.5 or Sonnet: how to decide *GO AI analysis* The price gap makes Haiku attractive for anything you run thousands of times. As simple arithmetic from Anthropic's published rates: one million short requests of 2,000 input tokens each is 2 billion input tokens, about US$200 on Haiku 5.5 at the under-100K rate before output costs, against ten times that at Haiku 4.5's old input price. Our rule of thumb is to start with the cheapest model that passes a test set of your own examples, and move up only where it fails. Keep the failures: they show exactly which tasks deserve Sonnet. ## Test a small model on a real high-volume task *Practical guide* Collect ten real examples of the task you want to automate, such as customer messages, short documents or support tickets, with the answer you consider correct. Run the prompt below and compare the labels with your own. If most match and the misses are easy to catch, a small model is probably enough. Remove personal data before pasting anything. ```text Classify each message below into one of these categories: [category list]. For each message return: number, category, confidence (high, medium or low) and a one-line reason. If a message fits no category, say so instead of guessing. Messages: [paste 10 messages, one per line] ``` ### Try a prompt with your own details Claude Haiku 5.5 is not confirmed available in GO AI. GO AI's Claude option currently uses Claude Sonnet 5, and you can run the classification test above with it or with the other models in GO AI. [Get the app on the App Store](https://apps.apple.com/app/id6742322421) [Try GO AI web chat](https://app.goaichat.app/) ## What this means for GO AI users Claude Haiku 5.5 is not confirmed available in GO AI. GO AI's Claude option currently uses Claude Sonnet 5, and you can run the classification test above with it or with the other models in GO AI. ## Questions, answered ### How much does Claude Haiku 5.5 cost? US$0.10 per million input tokens and $0.50 per million output tokens up to 100K tokens per request; $0.50 and $2.50 above that. ### Is Claude Haiku 5.5 better than Sonnet 5.5? No. Anthropic's own tables show Sonnet 5.5 ahead on every listed benchmark; Haiku 5.5 wins on speed and price. ### Is Claude Haiku 5.5 available in GO AI? It is not confirmed in GO AI. GO AI's Claude option currently uses Claude Sonnet 5. ## Run your own model test in GO AI Paste the classification prompt into GO AI web chat or GO AI Chat for iPhone, try it with Claude and another model, and keep the results that matter for your work. [Get the app on the App Store](https://apps.apple.com/app/id6742322421) [Try GO AI web chat](https://app.goaichat.app/) ## Read next - [Gemini 3.7 Flash vs Claude Sonnet 5: which fits your work?](https://goaichat.app/blog/gemini-3-7-flash-vs-claude-sonnet-5) - [Which AI model should you choose for your task?](https://goaichat.app/blog/which-ai-model-for-which-task) - [Custom system prompts: reusable instructions and examples](https://goaichat.app/blog/custom-system-prompts) ## Sources and editorial note Reported facts are linked to their sources. GO AI analysis is our interpretation; suggested prompts are not recorded test results. - [Anthropic: Introducing Claude Haiku 5.5](https://www.anthropic.com/news/claude-haiku-5-5) — 2026-10-07