{"slug": "claude-fable-5-2", "title": "Claude Fable 5.2", "summary": "Anthropic released Claude Fable 5.2 on November 9, 2026, a model priced at $8 per million input tokens and $40 per million output tokens with a 1M-token context window, 128K max output, and a June 2026 knowledge cutoff, aimed at long-horizon agentic work and multistep deep research. Claude Fable 5.2 ships with adaptive thinking permanently on, defaults to `high` effort, returns 400 errors for forced tool use and for `temperature`, `top_p` and `top_k` sampling parameters, and requires 30-day data retention rather than zero data retention unless Anthropic expressly authorizes it. The same capabilities are offered to verified organizations as Claude Mythos 5.2 through Anthropic's verification programs such as the Cyber Verification Program, at identical specifications and pricing, and the model is scheduled for retirement no sooner than November 9, 2027.", "body_md": "[Models & pricing](https://platform.claude.com/docs/en/models/overview)Models\n\n# Claude Fable 5.2\n\nFor demanding reasoning and long-horizon agentic work\n\n- 1M\n- 128K\n- $8\n- $40\n\n## Overview\n\nClaude Fable 5.2 is built for demanding reasoning and long-horizon agentic work. Typical uses include agent sessions that run for hours, multistep deep research, and analysis carried through to a finished document, spreadsheet, or deck.\n\n## Claude Fable 5.2 and Claude Mythos 5.2\n\n[Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). It shares Claude Fable 5.2’s specifications and pricing. To request access, apply to the program that covers your use case, or contact your account team.\n\n## How it compares\n\n| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff | \n|---|---|---|---|---|---|---|---|\n| Claude Fable 5.2 | 1M | 128K | $8 / $40 | Moderate | Adaptive (always on) | `high` | Jun 2026 | \n| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 | \n| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 | \n| [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) | 1M | 128K | From $0.10 / $0.50 | Fastest | Adaptive | `medium` | Jun 2026 | \n\n## Specifications\n\n### Model IDs\n\n### Pricing\n\n- Input\n- $8 / MTok\n- Output\n- $40 / MTok\n- [5m cache write](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)\n- $10 / MTok\n- [1h cache write](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)\n- $16 / MTok\n- [Cache read](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)\n- $0.20 / MTok\n- [Batch API](https://platform.claude.com/docs/en/build-with-claude/batch-processing)\n- 50% discount on input and output\n\n### Capabilities\n\n- [Context window](https://platform.claude.com/docs/en/build-with-claude/context-windows)\n- 1M tokens\n- Max output\n- 128K tokens\n- [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)\n- Adaptive (always on)\n- [Default effort](https://platform.claude.com/docs/en/build-with-claude/effort)\n- `high`\n- Comparative latency\n- Moderate\n- Input → output\n- Text and images → text\n- Reliable knowledge cutoff\n- Jun 2026\n- Training data cutoff\n- Jun 2026\n\n### Availability\n\n- [Status](https://platform.claude.com/docs/en/about-claude/model-deprecations)\n- Active (latest)\n- Released\n- November 9, 2026\n- Retirement\n- Not sooner than November 9, 2027\n\n## Good to know\n\n- Adaptive thinking is always on and can’t be turned off. Control thinking depth with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) .\n- Forced tool use (`tool_choice` types`any` and`tool` ) returns a 400 error. See[Thinking and tool choice](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#thinking-and-tool-choice) .\n- Omit `temperature` ,`top_p` , and`top_k` . See[Sampling parameters](https://platform.claude.com/docs/en/build-with-claude/thinking#sampling-parameters) for the values that return a 400 error.\n- Claude Fable 5.2 requires 30-day data retention and isn’t available under zero data retention unless expressly authorized by Anthropic. See [Model-specific data retention requirements](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements) .\n- Query limits and capabilities programmatically with the [Models API](https://platform.claude.com/docs/en/api/models/list) Preview with links to the API reference available — press Tab until focus enters the card, Escape to return..\n\n## Resources\n\nBehavioral differences and prompting patterns specific to Claude Fable 5.2.\n\nWhat changes when you move from Claude Fable 5.1 or from a Claude Opus model.\n\nEditing earlier turns invalidates thinking blocks, for every account.\n\nHow adaptive thinking works. It’s the only thinking mode on Claude Fable 5.2.\n\nThe control for thinking depth, latency, and cost. Choose a level for each workload.\n\nHandle classifier refusals and retry on another Claude model.\n\nFaster output from Claude Fable 5.2 in Messages API requests, at premium pricing.\n\n## Reference\n\nThe system prompt Claude Fable 5.2 uses on claude.ai and the Claude apps.\n\nSafety evaluations and deployment decisions for Claude Fable 5.2 and Claude Mythos 5.2.\n\nFull price list, including batch discounts and prompt caching rates.\n\nHow model IDs, aliases, and pinned snapshots work.\n\nLifecycle status and retirement commitments for every Claude model.\n\nWas this page helpful?", "url": "https://wpnews.pro/news/claude-fable-5-2", "canonical_source": "https://platform.claude.com/docs/en/models/fable-5-2/overview", "published_at": "2026-11-09 19:10:40+00:00", "updated_at": "2026-11-09 19:23:48.942328+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "artificial-intelligence", "generative-ai"], "entities": ["Anthropic", "Claude Fable 5.2", "Claude Mythos 5.2", "Claude Opus 5.5", "Claude Sonnet 5.5", "Claude Haiku 5.5", "Cyber Verification Program"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/claude-fable-5-2", "markdown": "https://wpnews.pro/news/claude-fable-5-2.md", "text": "https://wpnews.pro/news/claude-fable-5-2.txt", "jsonld": "https://wpnews.pro/news/claude-fable-5-2.jsonld"}}