---
title: Claude Sonnet 5.5
url: https://platform.claude.com/docs/ko/models/sonnet-5-5/overview
description: "Claude Sonnet 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 September 28, 2026.

The best combination of speed and intelligence

Model ID: `claude-sonnet-5-5`

Context window: 1M tokens · Max output: 128K tokens · Input pricing: $2 / MTok · Output pricing: $10 / MTok

[Announcement](https://www.anthropic.com/claude-sonnet-5-5) · [What’s new](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5) · [Migration guide](https://platform.claude.com/docs/ko/models/sonnet-5-5/migration-guide)

## 개요

Claude Sonnet 5.5는 속도와 지능의 최상의 조합을 제공합니다. 다섯 가지 "breaking change"(호환성을 깨는 변경 사항)가 이미 Claude Sonnet 5에서 실행 중인 코드에 영향을 미칩니다:

* [`between_tools`로 사전 사고를 끄세요](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).
* [강제 도구 사용은 오류를 반환합니다](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#forced-tool-use-is-not-supported).
* [사고 블록은 모델 및 대화에 연결됩니다](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them).
* [Claude API와 Google Cloud에서는 이전 `computer_20251124` 컴퓨터 사용 도구가 허용되지 않습니다](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported).
* [어드바이저 도구는 Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, Claude Haiku 5.5를 어드바이저로 거부합니다](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings).

또 하나의 변경 사항은 요청을 실패시키지 않으면서 응답 형태를 바꿉니다: [도구 호출 사이의 텍스트가 `thinking` 블록으로 반환됩니다](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#text-between-tool-calls). 해당 텍스트를 사용자에게 스트리밍하는 애플리케이션은 텍스트를 반환하는 `display` 값을 설정하거나 `between_tools`로 사전 사고를 끄기 전까지 도구 호출 사이에 아무것도 출력하지 않게 됩니다.

[Claude Sonnet 5.5의 새로운 기능](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-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** (this model)                                                | 1M      | 128K       | $2 / $10           | Fast     | Adaptive             | `high`         | Jun 2026         |
| [Claude Haiku 5.5](https://platform.claude.com/docs/ko/models/haiku-5-5/overview) | 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-sonnet-5-5`           |
| [Amazon Bedrock](https://platform.claude.com/docs/ko/build-with-claude/claude-in-amazon-bedrock)       | `anthropic.claude-sonnet-5-5` |
| [Google Cloud](https://platform.claude.com/docs/ko/build-with-claude/claude-on-vertex-ai)              | `claude-sonnet-5-5`           |
| [Microsoft Foundry](https://platform.claude.com/docs/ko/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-5-5`           |
| [Claude Platform on AWS](https://platform.claude.com/docs/ko/build-with-claude/claude-platform-on-aws) | `claude-sonnet-5-5`           |

### Pricing

| Feature                                                                                | Value                            |
| :------------------------------------------------------------------------------------- | :------------------------------- |
| Input                                                                                  | $2 / MTok                        |
| Output                                                                                 | $10 / MTok                       |
| [5m cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $2.50 / MTok                     |
| [1h cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $4 / MTok                        |
| [Cache read](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching)     | $0.10 / MTok                     |
| [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)                                              | `high`                 |
| Comparative latency                                                                                                         | Fast                   |
| 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                                                                      | September 28, 2026                                                                                                                                                                                                                                                                                                                                                                                                      |
| Retirement                                                                    | Not sooner than September 28, 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. 가장 낮은 사고 설정은 `between_tools`이며, 이 설정은 "up-front thinking"(사전 사고)을 끕니다. 이 설정은 `high` effort 이하에서 작동합니다. [Claude Sonnet 5.5의 새로운 기능](https://platform.claude.com/docs/ko/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking)을 참조하세요.
* `temperature`, `top_p` 또는 `top_k`를 기본값이 아닌 값으로 설정하면 400 오류가 반환됩니다.
* 캐시 가능한 최소 프롬프트 길이는 512 토큰입니다. [프롬프트 캐싱](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching#cache-limitations)을 참조하세요.
* [Message Batches API](https://platform.claude.com/docs/ko/build-with-claude/batch-processing#extended-output-beta)에서 Claude Sonnet 5.5는 `output-300k-2026-03-24` 베타 헤더를 사용하여 최대 300k 출력 토큰을 지원합니다.
* [Models API](https://platform.claude.com/docs/ko/api/models/list)를 사용하여 한도와 기능을 프로그래밍 방식으로 조회하세요.

## 리소스

<CardGroup cols={3}>
  <Card title="Claude Sonnet 5.5 프롬프팅" icon="lightbulb" href="https://platform.claude.com/docs/ko/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5">
    Claude Sonnet 5.5에 특화된 동작 차이와 프롬프팅 패턴입니다.
  </Card>

  <Card title="Effort" icon="sliders" href="https://platform.claude.com/docs/ko/build-with-claude/effort">
    사고 깊이, "latency"(지연 시간), 비용을 조절하는 제어 설정입니다. 워크로드별로 수준을 선택하세요.
  </Card>

  <Card title="적응형 사고" icon="brain" href="https://platform.claude.com/docs/ko/build-with-claude/thinking">
    적응형 사고의 작동 방식, 각 모델이 허용하는 사고 설정, 그리고 사고 블록이 보존되는 방식을 설명합니다.
  </Card>
</CardGroup>

## 참조

<CardGroup cols={3}>
  <Card title="시스템 프롬프트" icon="text" href="https://platform.claude.com/docs/ko/release-notes/system-prompts/claude-sonnet-5-5">
    Claude Sonnet 5.5가 claude.ai 및 Claude 앱에서 사용하는 시스템 프롬프트입니다.
  </Card>

  <Card title="시스템 카드" icon="file" href="https://www.anthropic.com/document/claude-sonnet-5-5-system-card">
    Claude Sonnet 5.5의 안전성 평가 및 배포 결정 사항입니다.
  </Card>

  <Card title="가격" icon="coins" href="https://platform.claude.com/docs/ko/about-claude/pricing">
    배치 할인 및 프롬프트 캐싱 요금을 포함한 전체 가격표입니다.
  </Card>

  <Card title="모델 ID 및 버전 관리" icon="fingerprint" href="https://platform.claude.com/docs/ko/about-claude/models/model-ids-and-versions">
    모델 ID, 별칭, 고정 스냅샷의 작동 방식을 설명합니다.
  </Card>

  <Card title="모델 지원 중단" icon="clock" href="https://platform.claude.com/docs/ko/about-claude/model-deprecations">
    모든 Claude 모델의 수명 주기 상태와 종료 약속 사항입니다.
  </Card>
</CardGroup>