Claude Fable 5.2

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.

Models & pricing https://platform.claude.com/docs/en/models/overview Models Claude Fable 5.2 For demanding reasoning and long-horizon agentic work - 1M - 128K - $8 - $40 Overview Claude 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. Claude Fable 5.2 and Claude Mythos 5.2 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. How it compares | Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff | |---|---|---|---|---|---|---|---| | Claude Fable 5.2 | 1M | 128K | $8 / $40 | Moderate | Adaptive always on | high | Jun 2026 | | 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 | | Claude Sonnet 5.5 https://platform.claude.com/docs/en/models/sonnet-5-5/overview | 1M | 128K | $2 / $10 | Fast | Adaptive | high | Jun 2026 | | 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 | Specifications Model IDs Pricing - Input - $8 / MTok - Output - $40 / MTok - 5m cache write https://platform.claude.com/docs/en/build-with-claude/prompt-caching - $10 / MTok - 1h cache write https://platform.claude.com/docs/en/build-with-claude/prompt-caching - $16 / MTok - Cache read https://platform.claude.com/docs/en/build-with-claude/prompt-caching - $0.20 / MTok - Batch API https://platform.claude.com/docs/en/build-with-claude/batch-processing - 50% discount on input and output Capabilities - Context window https://platform.claude.com/docs/en/build-with-claude/context-windows - 1M tokens - Max output - 128K tokens - Thinking https://platform.claude.com/docs/en/build-with-claude/thinking - Adaptive always on - Default effort https://platform.claude.com/docs/en/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 - Status https://platform.claude.com/docs/en/about-claude/model-deprecations - Active latest - Released - November 9, 2026 - Retirement - Not sooner than November 9, 2027 Good to know - 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 . - 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 . - 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. - 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 . - 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.. Resources Behavioral differences and prompting patterns specific to Claude Fable 5.2. What changes when you move from Claude Fable 5.1 or from a Claude Opus model. Editing earlier turns invalidates thinking blocks, for every account. How adaptive thinking works. It’s the only thinking mode on Claude Fable 5.2. The control for thinking depth, latency, and cost. Choose a level for each workload. Handle classifier refusals and retry on another Claude model. Faster output from Claude Fable 5.2 in Messages API requests, at premium pricing. Reference The system prompt Claude Fable 5.2 uses on claude.ai and the Claude apps. Safety evaluations and deployment decisions for Claude Fable 5.2 and Claude Mythos 5.2. Full price list, including batch discounts and prompt caching rates. How model IDs, aliases, and pinned snapshots work. Lifecycle status and retirement commitments for every Claude model. Was this page helpful?