Anthropic · Claude Fable
Claude Fable 5.1
Anthropic's current model for demanding reasoning and long-horizon agentic work, at the same headline price as Fable 5 but with prompt-cache reads cut to a quarter of the cost, and stronger long-running coding, research and document work.
A genuine upgrade for long-horizon work, but migrate deliberately rather than by swapping the model ID: audit your integration against the three breaking changes first, then compare cost using the new, much cheaper cache-read price rather than assuming the headline rate tells the whole story.
Use it for
- Very long and difficult agentic coding and research projects
- Document, spreadsheet and slide work that runs across many steps
- Hard reasoning with auditable outputs
Anthropic still recommends starting with Claude Opus 5 for most workloads; reach for Fable 5.1 only when the task genuinely needs demanding reasoning or long-horizon depth, or Opus 5 at higher effort already falls short. It is not a safe drop-in for an existing Fable 5 integration: forced tool use, cross-model thinking blocks and edited earlier turns all behave differently.
Effort without the jargon
The task is genuinely long-horizon; thinking cannot be disabled, so the effort parameter, defaulting to high, is the real cost and depth control.
Advanced recordCost, limits, privacy and operations
Fable 5.1 costs the same per token as Fable 5 but caching is a quarter of the price, so a workflow that rereads the same long context repeatedly gets materially cheaper even though the headline rate did not move.
- API cost
- Officially disclosedClaude API list price: US$10 per million input tokens and US$50 per million output tokens, unchanged from Fable 5. Prompt-cache reads cost US$0.25 per million tokens, a quarter of the standard 10% cache-read rate used elsewhere in the lineup. A 5-minute cache write is US$12.50 per million tokens and a 1-hour write is US$20; the Batch API gives a 50% discount on input and output.
- Context window
- Officially disclosed1,000,000 tokens
- Maximum output
- Officially disclosed128,000 tokens (synchronous Messages API)
- Knowledge cutoff
- Officially disclosedReliable knowledge: June 2026; training data: June 2026
- Recorded inputs
- Text · Images
- Recorded output
- Text
Data handling is a product decision
Depends on surfaceAnthropic says commercial API inputs and outputs are deleted from its backend within 30 days by default, with exceptions for stored services, agreed controls, safety enforcement and law. Consumer Claude and cloud platforms have separate terms.
Operational constraints
- Adaptive thinking is always on and defaults to high effort; it cannot be disabled.
- Forced tool use is not supported, unlike Fable 5.
- Thinking blocks are tied to the model that produced them and are not readable by an earlier model.
- Editing an earlier turn in a conversation invalidates that turn's thinking blocks.
- The dateless API ID is a pinned snapshot rather than an automatically moving alias.
Unknown means the cited official record does not disclose a safe value. It is not an estimate. Prices are provider list prices in USD where stated and can change before this record's review date.
Keep the evidence separate
Anthropic describes Fable 5.1 as extending Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, bringing stronger long-running agentic coding, multistep research and document, spreadsheet and slide work. It lists three breaking changes for existing Fable 5 callers (forced tool use is unsupported, thinking blocks are tied to the model that produced them, and editing earlier turns invalidates thinking blocks) and five additive changes, including per-message effort and turn-scoped system messages, both in beta.
No sufficiently useful independent note has been added yet. That absence is not filled with our guess.
No Human Bit result is claimed; use this as evaluation guidance only.
Not scheduled
No Human Bit result is claimed for this model yet.