Claude Haiku 5.5 is Anthropic's fastest and cheapest current model, built for high volume, latency sensitive tasks such as classification, extraction, routing, summaries and subagent work. Anthropic released it on October 7, 2026, and it is the first Haiku with an adjustable effort setting.
Key facts
| Item | Claude Haiku 5.5 |
|---|---|
| Maker | Anthropic |
| Released | October 7, 2026 |
| API model ID | claude-haiku-5-5 |
| Context window | 1 million tokens |
| Max output | 128,000 tokens |
| Knowledge cutoff | June 2026 |
| Default effort | medium, with adaptive thinking |
| API price per million tokens | From $0.10 input and $0.50 output, cache reads from $0.01 |
Sources: Anthropic's models overview and pricing page, plus the Haiku 5.5 announcement, checked October 24, 2026.
Pricing details
Haiku 5.5 has two price bands. Prompts up to 100,000 tokens cost $0.10 per million input tokens and $0.50 per million output tokens. Longer prompts cost $0.50 and $2.50. Cache reads start at $0.01 per million tokens, and Batch API requests are half price.
Where to use Claude Haiku 5.5
- API and clouds: on the Anthropic API, Amazon Bedrock, Claude Platform on AWS, Google Cloud and Microsoft Foundry.
- Claude apps: available on every Claude plan, including Free.
- Under bigger models: Anthropic positions it as a cheap subagent that Opus or Sonnet can hand narrow tasks to.
Strengths and limits
Haiku 5.5 is the right pick when cost per request and latency matter most. Anthropic says Claude Sonnet 5.5 and Claude Opus 5.5 remain better for complex agentic coding.
Good first projects
Typical starting points are support ticket triage, tagging and routing incoming messages, pulling fields out of invoices or forms, summarizing long threads before a bigger model reads them, and compacting chat history in long agent sessions. Because it reads up to 1 million tokens, it can also scan large logs or document sets cheaply before passing the relevant parts on.
How it compares
Its direct rival is OpenAI's GPT-6 Luna, priced the same for short prompts. Read Claude Haiku 5.5 vs GPT-6 Luna for a full comparison and Claude Fable vs Opus vs Mythos for the rest of the Claude family. All launch dates are on the release timeline.