---
title: Claude Fable 5.1
url: https://platform.claude.com/docs/ko/models/fable-5-1/overview
description: "Claude Fable 5.1 한눈에 보기: 용도, 모든 플랫폼에서의 모델 ID, 컨텍스트 윈도우, 출력 한도, 가격, 가용성, 그리고 이 모델로 구축하기 위한 리소스."
---
**Latest.** Released September 1, 2026.
For demanding reasoning and long-horizon agentic work
Model ID: `claude-fable-5-1`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok
[Announcement](https://www.anthropic.com/claude-fable-and-mythos-5-1) · [What’s new](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1) · [Migration guide](https://platform.claude.com/docs/ko/models/fable-5-1/migration-guide)
## 개요
Claude Fable 5.1은 Claude Fable 5와 동일한 입력 및 출력 가격으로 Claude Fable 5를 확장하며, 캐시 읽기 비용은 4분의 1 수준이고, 장기 실행 에이전틱 코딩, 다단계 리서치, 그리고 문서, 스프레드시트, 슬라이드 작업 성능이 더욱 강화되었습니다. 대부분의 워크로드에서는 Claude Opus 5.5로 시작하세요([모델 선택하기](https://platform.claude.com/docs/ko/about-claude/models/choosing-a-model) 참조). 까다로운 추론 및 장기적 에이전틱 작업이 필요하거나, 더 높은 effort로 설정한 Claude Opus 5.5에서도 평가 결과가 여전히 부족한 경우에는 Claude Fable 5.1을 사용하세요. Claude Mythos 5.1은 [Cyber Verification Program](https://support.claude.com/en/articles/14604842)과 같은 Anthropic의 검증 프로그램을 통해 검증된 조직에만 동일한 기능을 제공합니다.
이미 Claude Fable 5를 호출하고 있다면, 세 가지 변경 사항이 호환성을 깨뜨립니다: [강제 도구 사용은 오류를 반환합니다](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported), [Claude Fable 5.1의 thinking 블록은 Claude Fable 5.1과 Claude Mythos 5.1만 읽을 수 있습니다](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them), 그리고 [이전 턴을 편집하면 thinking 블록이 무효화됩니다](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks). 다섯 가지는 추가 사항입니다: [메시지별 effort](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta)(베타), [턴 범위 시스템 메시지](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta)(베타), [도구 호출 사이의 읽을 수 있는 진행 상황 업데이트](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#progress-updates-between-tool-calls-beta)(`display: "updates"`, 베타), [더 낮은 캐시 읽기 가격](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#pricing), 그리고 [콘텐츠 출처](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1#content-provenance)입니다.
[Claude Fable 5.1의 새로운 기능](https://platform.claude.com/docs/ko/models/fable-5-1/whats-new-fable-5-1)
## Claude Fable 5.1과 Claude Mythos 5.1
[Claude Mythos 5.1](https://platform.claude.com/docs/ko/models/mythos-5-1/overview)은 [Cyber Verification Program](https://support.claude.com/en/articles/14604842)과 같은 Anthropic의 검증 프로그램을 통해 검증된 조직에만 동일한 기능을 제공합니다. Claude Fable 5.1과 동일한 사양 및 가격을 공유합니다. 액세스를 요청하려면 사용 사례에 해당하는 프로그램에 신청하거나 Anthropic, AWS 또는 Google Cloud 계정 팀에 문의하세요.
## 비교
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| **Claude Fable 5.1** (this model) | 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](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-fable-5-1` |
| [Amazon Bedrock](https://platform.claude.com/docs/ko/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-1` |
| [Google Cloud](https://platform.claude.com/docs/ko/build-with-claude/claude-on-vertex-ai) | `claude-fable-5-1` |
| [Microsoft Foundry](https://platform.claude.com/docs/ko/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-1` |
| [Claude Platform on AWS](https://platform.claude.com/docs/ko/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1` |
### Pricing
| Feature | Value |
| :------------------------------------------------------------------------------------- | :------------------------------- |
| Input | $10 / MTok |
| Output | $50 / MTok |
| [5m cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $12.50 / MTok |
| [1h cache write](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $20 / MTok |
| [Cache read](https://platform.claude.com/docs/ko/build-with-claude/prompt-caching) | $0.25 / 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 |
| [Thinking](https://platform.claude.com/docs/ko/build-with-claude/thinking) | Adaptive (always on) |
| [Default effort](https://platform.claude.com/docs/ko/build-with-claude/effort) | `high` |
| Comparative latency | Slower |
| 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 1, 2026 |
| Retirement | Not sooner than September 1, 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) |
## 리소스
장기 및 에이전트 작업을 위한 모델별 프롬프팅 가이드입니다.
Claude Fable 5, Claude Opus 5 또는 Claude Opus 4.8에서 전환할 때 달라지는 점입니다.
이 모델의 사고 블록이 사용 가능한 상태로 유지되는 경우: 모델 전환 시와 대화 변경 시.
프롬프트 캐시를 무효화하지 않고 대화 도중에 effort 수준을 변경합니다.
분류기 거부를 처리하고 다른 Claude 모델로 재시도합니다.
Claude Fable 5.1의 유일한 사고 모드입니다. `effort`로 깊이를 조절하세요.
## 참조
Claude Fable 5.1이 claude.ai 및 Claude 앱에서 사용하는 시스템 프롬프트.
Claude Fable 5.1 및 Claude Mythos 5.1에 대한 안전성 평가 및 배포 결정.
배치 할인 및 프롬프트 캐싱 요금을 포함한 전체 가격표.
모델 ID, 별칭 및 고정된 스냅샷의 작동 방식.
모든 Claude 모델의 수명 주기 상태 및 종료 약속.