---
title: Claude Fable 5.2
url: https://platform.claude.com/docs/zh-TW/models/fable-5-2/overview
description: Claude Fable 5.2 概覽：其用途、各平台上的模型 ID、上下文視窗、輸出限制、定價、可用性，以及使用它進行建置的資源。
---
**Latest.** Released November 9, 2026.
For demanding reasoning and long-horizon agentic work
Model ID: `claude-fable-5-2`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $8 / MTok · Output pricing: $40 / MTok
[Announcement](https://www.anthropic.com/claude-fable-and-mythos-5-2) · [What’s new](https://platform.claude.com/docs/zh-TW/models/fable-5-2/whats-new-fable-5-2) · [Migration guide](https://platform.claude.com/docs/zh-TW/models/fable-5-2/migration-guide)
## 概覽
Claude Fable 5.2 專為高要求的推理與長時程的代理式工作而打造。典型用途包括持續數小時的代理工作階段、多步驟的深度研究，以及一路進行到產出完整文件、試算表或簡報的分析工作。
## Claude Fable 5.2 與 Claude Mythos 5.2
[Claude Mythos 5.2](https://platform.claude.com/docs/zh-TW/models/mythos-5-2/overview) 僅向通過 Anthropic 驗證計畫（例如 [Cyber Verification Program](https://support.claude.com/en/articles/14604842)）驗證的組織提供相同的功能。它與 Claude Fable 5.2 共用相同的規格和定價。若要申請存取權限，請申請涵蓋您使用案例的計畫，或聯絡您的客戶團隊。
## 比較
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :------------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| **Claude Fable 5.2** (this model) | 1M | 128K | $8 / $40 | Moderate | Adaptive (always on) | `high` | Jun 2026 |
| [Claude Opus 5.5](https://platform.claude.com/docs/zh-TW/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/zh-TW/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
| [Claude Haiku 5.5](https://platform.claude.com/docs/zh-TW/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 5.2, Claude Mythos 5.2, 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.
## 規格
### Model IDs
| Platform | Model ID |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------ | :--------------------------- |
| Claude API | `claude-fable-5-2` |
| [Amazon Bedrock](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-2` |
| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5-2` |
| [Microsoft Foundry](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-2` |
| [Claude Platform on AWS](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-platform-on-aws) | `claude-fable-5-2` |
| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5-2` |
### Pricing
| Feature | Value |
| :---------------------------------------------------------------------------------------- | :------------------------------- |
| Input | $8 / MTok |
| Output | $40 / MTok |
| [5m cache write](https://platform.claude.com/docs/zh-TW/build-with-claude/prompt-caching) | $10 / MTok |
| [1h cache write](https://platform.claude.com/docs/zh-TW/build-with-claude/prompt-caching) | $16 / MTok |
| [Cache read](https://platform.claude.com/docs/zh-TW/build-with-claude/prompt-caching) | $0.20 / MTok |
| [Batch API](https://platform.claude.com/docs/zh-TW/build-with-claude/batch-processing) | 50% discount on input and output |
[Full price list](https://platform.claude.com/docs/zh-TW/about-claude/pricing)
### Capabilities
| Feature | Value |
| :----------------------------------------------------------------------------------------- | :--------------------- |
| [Context window](https://platform.claude.com/docs/zh-TW/build-with-claude/context-windows) | 1M tokens |
| Max output | 128K tokens |
| [Thinking](https://platform.claude.com/docs/zh-TW/build-with-claude/thinking) | Adaptive (always on) |
| [Default effort](https://platform.claude.com/docs/zh-TW/build-with-claude/effort) | `high` |
| Comparative latency | Moderate |
| 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/zh-TW/about-claude/model-deprecations) | Active (latest) |
| Released | November 9, 2026 |
| Retirement | Not sooner than November 9, 2027 |
| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/zh-TW/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
## 須知事項
* 「Adaptive thinking」（自適應思考）始終開啟且無法關閉。請使用 [effort 參數](https://platform.claude.com/docs/zh-TW/build-with-claude/effort)控制思考深度。
* 強制「tool use」（工具使用）（`tool_choice` 類型 `any` 和 `tool`）會回傳 400 錯誤。請參閱[思考與工具選擇](https://platform.claude.com/docs/zh-TW/models/fable-5-2/whats-new-fable-5-2#thinking-and-tool-choice)。
* 請省略 `temperature`、`top_p` 和 `top_k`。請參閱[取樣參數](https://platform.claude.com/docs/zh-TW/build-with-claude/thinking#sampling-parameters)以了解會回傳 400 錯誤的值。
* Claude Fable 5.2 需要 30 天的資料保留，且除非經 Anthropic 明確授權，否則無法在「zero data retention」（零資料保留）下使用。請參閱[特定模型的資料保留要求](https://platform.claude.com/docs/zh-TW/manage-claude/api-and-data-retention#model-specific-data-retention-requirements)。
* 使用 [Models API](https://platform.claude.com/docs/zh-TW/api/models/list) 以程式化方式查詢限制和功能。
## 資源
Claude Fable 5.2 特有的行為差異和提示模式。
從 Claude Fable 5.1 或 Claude Opus 模型遷移時會有哪些變化。
對於所有帳戶，編輯先前的回合會使思考區塊失效。
自適應思考的運作方式。這是 Claude Fable 5.2 上唯一的思考模式。
控制思考深度、延遲和成本的設定。為每個工作負載選擇一個等級。
處理分類器拒絕，並改用另一個 Claude 模型重試。
在 Messages API 請求中以進階定價從 Claude Fable 5.2 獲得更快的輸出。
## 參考
Claude Fable 5.2 在 claude.ai 和 Claude 應用程式上使用的系統提示。
Claude Fable 5.2 和 Claude Mythos 5.2 的安全評估與部署決策。
完整價目表，包括批次折扣和提示快取費率。
模型 ID、別名和固定快照的運作方式。
每個 Claude 模型的生命週期狀態和停用承諾。