Claude Haiku 5.5
- Score
- 43.4 · rank 19
- Price
- Paid
- API
- Yes
- Weights
- No
WHAT IT DOES
Claude Haiku 5.5 is Anthropic's October 7, 2026 small model, replacing Haiku 4.5 as the recommended fast, cheap Claude. For prompts up to 100,000 tokens it costs $0.10 per million input tokens and $0.50 per million output, 90% below Haiku 4.5 and the same as OpenAI's GPT-6 Luna; above 100,000 tokens the price is $0.50 and $2.50. Cache reads are $0.01 per million. Anthropic says about 90% of Haiku requests fall under the 100,000-token line, so the average cost falls by around 75%. In Anthropic's tests it scores 1620 on GDPval-AA v2.1 against Luna's 1437, 72.4% on OSWorld 2.1 against 48.9%, and 39.2% on Terminal-Bench 4.0 against 16.4%. It is the first Haiku with adjustable effort levels, from low to max, and supports computer and browser use in beta through the SDKs. Output is text only.
WHY WE PICKED IT
It resets what a small model costs and what it can do at that price: on Anthropic's tables it beats GPT-6 Luna on every shared benchmark at the same per-token rate, and the independent Intelligence Index puts its max-effort setting above Luna's too. For high-volume classification, extraction, routing and sub-agent work, it is the new default to test first.
QUICK FACTS
STRENGTHS
- ✓$0.10 / $0.50 per million tokens under 100K, 90% below Haiku 4.5
- ✓Ahead of GPT-6 Luna on GDPval-AA, OSWorld 2.1 and Terminal-Bench 4.0 in Anthropic's tests
- ✓First Haiku with adjustable effort, low to max
- ✓Computer and browser use in beta
- ✓Available on the Claude Platform, AWS, Google Cloud and Microsoft Azure
LIMITATIONS
- ⚠Prompts over 100,000 tokens cost five times more per token
- ⚠New tokenizer uses slightly more tokens per task
- ⚠Tighter cybersecurity limits than Haiku 4.5; penetration testing is blocked
- ⚠Text output only
- ⚠Benchmarks are Anthropic's own apart from the Intelligence Index
GETTING STARTED
Call model id claude-haiku-5-5 on the Claude Platform, AWS, Google Cloud or Microsoft Azure. Effort defaults to medium; raise it for harder agentic steps and lower it for bulk extraction. It uses Anthropic's newer tokenizer, which spends slightly more tokens per task than Haiku 4.5's, so measure cost on your own traffic rather than from the price sheet. Keep prompts under 100,000 tokens where you can, since the price is five times higher above that line.
BENCHMARKS
OFFICIAL LINKS
PRICING
Requires a paid subscription.
FEATURED IN GUIDES
CLAUDE.md In Practice: What Actually Earns A Place In The File
The most-starred CLAUDE.md on GitHub has four rules, not twelve, and the error rates everyone quotes...
Open Models: What They Cannot Do
The benchmark gap has largely closed: open models now score within a point of the closed frontier on...
Hardware For Local AI Models: What The Memory Shortage Changed
Capacity decides whether a model runs. Bandwidth decides how fast it talks, and it is the number mos...
How To Run AI Models Locally: Hardware, Quantisation And Engines
Running a frontier open model locally is a memory problem before it is a speed problem, and a bandwi...
Uncensored AI Models: What Abliteration Actually Does To Them
Abliteration removes a model's ability to refuse by deleting one direction from its activations. It ...
EXPLORE ALTERNATIVES
Compare Claude Haiku 5.5 with 5+ similar llms AI tools.
FREQUENTLY ASKED QUESTIONS
Is Claude Haiku 5.5 free?
No, Claude Haiku 5.5 requires a paid subscription.
Does Claude Haiku 5.5 have an API?
Yes, Claude Haiku 5.5 offers an API for programmatic integration.
What is Claude Haiku 5.5 best for?
Claude Haiku 5.5 is best for Best Low-Cost Small Model. Claude Haiku 5. It resets what a small model costs and what it can do at that price: on Anthropic's tables it beats GPT-6 Luna on every shared benchmark at the same per-token rate, and the independent Intelligence Index puts its max-effort setting above Luna's too. For high-volume classification, extraction, routing and sub-agent work, it is the new default to test first.
What platforms does Claude Haiku 5.5 support?
Claude Haiku 5.5 supports api.
Is Claude Haiku 5.5 open source?
No, Claude Haiku 5.5 is not open source.
How do I get started with Claude Haiku 5.5?
Call model id claude-haiku-5-5 on the Claude Platform, AWS, Google Cloud or Microsoft Azure. Effort defaults to medium; raise it for harder agentic steps and lower it for bulk extraction. It uses Anthropic's newer tokenizer, which spends slightly more tokens per task than Haiku 4.5's, so measure cos...
How do I use Claude Haiku 5.5?
Claude Haiku 5.5 is a large language model for text generation, analysis, and conversation. Use the API for programmatic access. Enter prompts or questions to get responses. It excels at $0.10 / $0.50 per million tokens under 100k, 90% below haiku 4.5.
FEATURED ON CURATEDAI
Work on Claude Haiku 5.5? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.
