Back to Text & reasoning

Model comparison

Claude Fable 5.2 vs Claude Fable 5.1

Provider-published facts for Claude Fable 5.2 and Claude Fable 5.1, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.

What changed

What changed from Claude Fable 5.1 to Claude Fable 5.2

Fable 5.2 keeps Fable 5.1's context window, output limit and knowledge cutoff, and its input, output and cache prices are 20% lower. Anthropic reports faster output and fewer unnecessary safety blocks; those are provider claims, not Cody measurements.

SpecClaude Fable 5.1Claude Fable 5.2
Input price$10 / 1M$8 / 1M
Output price$50 / 1M$40 / 1M

Unchanged: context window, maximum output, knowledge cutoff, inputs and tools & agents.

Before you switch from Claude Fable 5.1 to Claude Fable 5.2

  • Update the model ID and check rate limits: Fable 5.2 has its own limit, separate from the one Fable 5.1 and Fable 5 share.
  • Move computer use to the computer_toolset_20260801 toolset; the older computer_20251124 tool returns an error everywhere except Amazon Bedrock.
  • If your code edits earlier messages, rebuilds system or tools, or compacts history between requests, test first: Fable 5.2 rejects thinking blocks whose earlier context changed, on every account.
  • Fable 5.1 cannot read Fable 5.2's thinking blocks, so plan for that before switching a conversation back to 5.1.
  • If you use the advisor tool, set the advisor model to claude-fable-5-2 or claude-mythos-5-2.
  • Re-run effort settings: prompts that ask for less thinking do not stop it thinking at medium effort or above, and a small max_tokens can leave no room for text.
Source: Anthropic

Estimate your cost

Set your usage. Your estimate updates as you type.

Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.

One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.

Advanced options
How this estimate works

Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.

Estimate your cost
ModelEstimated total (USD)
Claude Fable 5.2Anthropic$0.068
Claude Fable 5.1Anthropic$0.085

Quick take

Claude Fable 5.2

Anthropic's model for demanding reasoning and long-horizon agentic work, succeeding Fable 5.1 at lower token prices.

Best for

  • Long-running autonomous projects
  • Demanding reasoning and research
  • Large codebase changes and review

Watch out for

Check integrations before adopting it: forced tool choice, assistant prefill and sampling parameters return errors, and thinking cannot be turned off. Anthropic requires 30-day data retention, and Zero Data Retention needs its express authorization, so confirm this meets your retention rules.

Claude Fable 5.1

Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.

Best for

  • Long-running autonomous projects
  • Large codebase changes and review
  • Complex documents, diagrams, and enterprise workflows

Watch out for

Confirm whether the default 30-day retention, fallback safeguards, and selected cloud marketplace meet your governance requirements before adoption.

Compare the published facts

Claude Fable 5.2 vs Claude Fable 5.1

Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.

Text & reasoningClaude Fable 5.2Claude Fable 5.1
Context windowMaximum combined prompt and working context documented by the provider.1M tokens1M tokens
Maximum outputProvider-published response limit, where available.128K tokens128K tokens
Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.June 2026June 2026
Input priceCurrent standard list price per million input tokens unless noted.$8 / 1M$10 / 1M
Output priceCurrent standard list price per million output tokens unless noted.$40 / 1M$50 / 1M
InputsMedia types accepted by the listed model endpoint.Text, imageText, image
Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list.Tool use, agents, vision, coding workflowsTool use, agents, vision, coding workflows

How to choose

Data policy and API access

Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.

Claude Fable 5.2

Claude Fable 5.2 requires 30-day data retention and is not available under Zero Data Retention unless Anthropic expressly authorizes it. API data is not used for training without express permission.

Claude Fable 5.1

Fable requires 30-day retention for safety monitoring by default. Anthropic says enterprise data is not used for training without explicit permission; eligible enterprises can use EFS/customer-controlled storage or temporary zero-retention arrangements.

Frequently asked questions

Claude Fable 5.2 vs Claude Fable 5.1 FAQ

What is the main difference between Claude Fable 5.2 and Claude Fable 5.1?

Claude Fable 5.2: Anthropic's model for demanding reasoning and long-horizon agentic work, succeeding Fable 5.1 at lower token prices. Claude Fable 5.1: Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.

What changed from Claude Fable 5.1 to Claude Fable 5.2?

Fable 5.2 keeps Fable 5.1's context window, output limit and knowledge cutoff, and its input, output and cache prices are 20% lower. Anthropic reports faster output and fewer unnecessary safety blocks; those are provider claims, not Cody measurements. Changed in the published specs: input price and output price. Unchanged: context window, maximum output, knowledge cutoff, inputs and tools & agents.

Should I choose Claude Fable 5.2 or Claude Fable 5.1?

Best fit for Claude Fable 5.2: Demanding reasoning and research. Best fit for Claude Fable 5.1: Complex documents, diagrams, and enterprise workflows. Test both with your own data and provider route before committing.

Is there a Claude Fable 5.5?

No. Anthropic's models overview lists Claude Fable 5.2, released November 9, 2026, as the current Fable model, with Fable 5.1 and Fable 5 as legacy models. The 5.5 versions are Claude Opus 5.5, Claude Sonnet 5.5 and Claude Haiku 5.5.

Where do the facts in this Claude Fable 5.2 vs Claude Fable 5.1 comparison come from?

From each provider's own documentation, pricing and policy pages for the Text & reasoning category. Cody does not add its own benchmark scores or name a universal winner.