---
title: Claude Haiku 5.5
url: https://platform.claude.com/docs/ko/models/haiku-5-5/overview
description: "Claude Haiku 5.5 한눈에 보기: 용도, 모든 플랫폼의 모델 ID, 컨텍스트 윈도우, 출력 한도, 가격, 가용성, 그리고 이 모델로 구축하기 위한 가이드와 리소스를 소개합니다."
---
**Latest.** Released October 7, 2026.
For high-volume, latency-sensitive tasks such as classification, extraction, and routing
Model ID: `claude-haiku-5-5`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: From $0.10 / MTok · Output pricing: From $0.50 / MTok
[Announcement](https://www.anthropic.com/claude-haiku-5-5) · [What’s new](https://platform.claude.com/docs/ko/models/haiku-5-5/whats-new-haiku-5-5) · [Migration guide](https://platform.claude.com/docs/ko/models/haiku-5-5/migration-guide)
## 개요
Claude Haiku 5.5는 분류, 라우팅, 추출, 서브에이전트 작업과 같이 대량 처리가 필요하고 "latency"(지연 시간)에 민감한 작업을 위해 설계되었습니다. effort 매개변수를 사용하는 "adaptive thinking"(적응형 사고), 1M 토큰 "context window"(컨텍스트 윈도우), 최대 128k 출력 토큰을 지원합니다. Claude 4.7 이후 모델과 동일한 새로운 "tokenizer"(토크나이저)를 사용하므로, 동일한 텍스트가 Claude Haiku 4.5보다 약 30% 더 많은 토큰으로 계산됩니다. 사고 블록은 해당 블록을 생성한 계정 또는 그 계정에 연결된 계정에서만 작동합니다.
코드 변경 사항은 [마이그레이션 가이드](https://platform.claude.com/docs/ko/models/haiku-5-5/migration-guide)를 참조하세요. 모델 ID, 가격 및 제한 사항은 [Claude Haiku 5.5 개요](https://platform.claude.com/docs/ko/models/haiku-5-5/overview)를 참조하세요. 프롬프팅 지침은 [Claude Haiku 5.5 프롬프팅](https://platform.claude.com/docs/ko/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5)을 참조하세요.
[Claude Haiku 5.5의 새로운 기능](https://platform.claude.com/docs/ko/models/haiku-5-5/whats-new-haiku-5-5)
## 다른 모델과의 비교
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| [Claude Fable 5.1](https://platform.claude.com/docs/ko/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
| [Claude Opus 5.5](https://platform.claude.com/docs/ko/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
| [Claude Sonnet 5.5](https://platform.claude.com/docs/ko/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
| **Claude Haiku 5.5** (this model) | 1M | 128K | From $0.10 / $0.50 | Fastest | Adaptive | `medium` | Jun 2026 |
* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
## 사양
### Model IDs
| Platform | Model ID |
| :----------------------------------------------------------------------------------------------------- | :--------------------------- |
| Claude API | `claude-haiku-5-5` |
| [Amazon Bedrock](https://platform.claude.com/docs/ko/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-5-5` |
| [Google Cloud](https://platform.claude.com/docs/ko/build-with-claude/claude-on-vertex-ai) | `claude-haiku-5-5` |
| [Microsoft Foundry](https://platform.claude.com/docs/ko/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-5-5` |
| [Claude Platform on AWS](https://platform.claude.com/docs/ko/build-with-claude/claude-platform-on-aws) | `claude-haiku-5-5` |
### Pricing
| Feature | Value |
| :------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------- |
| Input | $0.10 / MTok for prompts up to 100,000 tokens; $0.50 / MTok for prompts over 100,000 tokens |
| Output | $0.50 / MTok for prompts up to 100,000 tokens; $2.50 / MTok for prompts over 100,000 tokens |
| [5m cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $0.125 / MTok for prompts up to 100,000 tokens; $0.625 / MTok for prompts over 100,000 tokens |
| [1h cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $0.20 / MTok for prompts up to 100,000 tokens; $1 / MTok for prompts over 100,000 tokens |
| [Cache read](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $0.01 / MTok for prompts up to 100,000 tokens; $0.05 / MTok for prompts over 100,000 tokens |
| [Batch API](https://platform.claude.com/docs/ko/build-with-claude/batch-processing) | 50% discount on input and output |
[Full price list](https://platform.claude.com/docs/ko/about-claude/pricing)
### Capabilities
| Feature | Value |
| :-------------------------------------------------------------------------------------------------------------------------- | :--------------------- |
| [Context window](https://platform.claude.com/docs/ko/build-with-claude/context-windows) | 1M tokens |
| Max output | 128K tokens |
| [Max output (Batch API, beta)](https://platform.claude.com/docs/ko/build-with-claude/batch-processing#extended-output-beta) | 300K tokens |
| [Thinking](https://platform.claude.com/docs/ko/build-with-claude/thinking) | Adaptive |
| [Default effort](https://platform.claude.com/docs/ko/build-with-claude/effort) | `medium` |
| Comparative latency | Fastest |
| Input → output | Text and images → text |
| Reliable knowledge cutoff | Jun 2026 |
| Training data cutoff | Jun 2026 |
### Availability
| Feature | Value |
| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Status](https://platform.claude.com/docs/ko/about-claude/model-deprecations) | Active (latest) |
| Released | October 7, 2026 |
| Retirement | Not sooner than October 7, 2027 |
| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/ko/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/ko/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/ko/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/ko/build-with-claude/claude-platform-on-aws) |
## 알아두면 좋은 점
* "Adaptive thinking"(적응형 사고)은 기본적으로 켜져 있습니다. [effort 매개변수](https://platform.claude.com/docs/ko/build-with-claude/effort)로 사고 깊이를 제어하세요.
* `temperature`, `top_p`, `top_k`는 생략하세요. 400 오류를 반환하는 값은 [샘플링 매개변수 제거하기](https://platform.claude.com/docs/ko/models/haiku-5-5/migration-guide#remove-sampling-parameters)를 참조하세요.
* [Message Batches API](https://platform.claude.com/docs/ko/build-with-claude/batch-processing#extended-output-beta)에서 Claude Haiku 5.5는 `output-300k-2026-03-24` 베타 헤더를 사용하여 최대 300k 출력 토큰을 지원합니다.
* 캐시 가능한 최소 프롬프트 길이는 512 토큰입니다. [프롬프트 캐싱](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching#cache-limitations)을 참조하세요.
* [Models API](https://platform.claude.com/docs/ko/api/models/list)를 사용하여 한도와 기능을 프로그래밍 방식으로 조회하세요.
## 리소스
Claude Haiku 5.5에 특화된 동작 차이와 프롬프팅 패턴입니다.
더 빠른 응답을 위해 모델과 effort 수준을 선택하고, 프롬프트를 구성하고, 출력을 스트리밍하세요.
Claude Haiku 5.5는 언제, 얼마나 사고할지 스스로 결정합니다. `effort`로 깊이를 조정하세요.
컨텍스트 윈도우가 계산되고 관리되는 방식입니다.
## 참고 자료
Claude Haiku 5.5가 claude.ai 및 Claude 앱에서 사용하는 시스템 프롬프트입니다.
Claude Haiku 5.5에 대한 안전성 평가 및 배포 결정 사항입니다.
배치 할인 및 프롬프트 캐싱 요금을 포함한 전체 가격표입니다.
모델 ID, 별칭, 고정 스냅샷이 작동하는 방식입니다.
모든 Claude 모델의 수명 주기 상태와 종료 관련 약속입니다.