Anthropic Claude Fable 5 — what it is, when to use it and what to use instead

Summary

Claude Fable 5 is the previous release in Anthropic's Fable line, at $10 per million input tokens and $50 per million output tokens with a 1M-token context window. Anthropic marks it as legacy and points to Claude Fable 5.1, which costs the same per token.

Fable 5 was released on 9 June 2026 and was superseded by Claude Fable 5.1 on 1 September 2026. Both models carry the same $10 / $50 price, the same 1M-token context window and the same 128K max output; Fable 5.1 adds a January-to-June 2026 gain in knowledge cutoff and drops cache reads from $1.00 to $0.25 per million tokens.

It accepts text and image input and returns text, with adaptive thinking always on and effort defaulting to high. Anthropic still lists the model as active, so calls keep working, but it is documented as legacy.

No deprecation has been announced. Anthropic commits to keeping Claude Fable 5 available until at least 9 June 2027.

Modality

• Text
• Vision

Use case

• Chat
• Coding
• Reasoning
• Agents & tool use
• Long context

Tier

• Frontier

Access

• Hosted API

Languages

• Multilingual

Specifications

Input price

$10.00 / M tokens

Output price

$50.00 / M tokens

Price band

Flagship

Context window

1M tokens

Max output

128K tokens

Input

Text, image

Output

Text

Knowledge cutoff

January 2026

Tool use

Yes

Structured output

Yes

Weights licence

not published

Model maker

Anthropic

“unknown” means the figure has not been published, or we have not verified it yet — never that the answer is no. “not published” under the weights licence means this model is not offered with downloadable weights. The price band is ours: it bands the blended price (three parts input to one part output) as budget (≤ $0.50), standard (≤ $3), premium (≤ $12) or flagship.

Lifecycle

Anthropic has not announced a deprecation or shutdown date for this model. That is a statement about what has been published, not a guarantee — providers typically announce a shutdown months ahead, and this page updates when they do.

1. Released 9 June 2026
2. Deprecated not announced
3. Retired not announced

Use it for

• Keep an existing Fable 5 integration running while you evaluate Claude Fable 5.1 against it.
• Stay on a fixed model if your integration depends on forced tool use, which Fable 5.1 no longer accepts.
• Compare thinking behaviour between Fable generations before you commit to the migration.

Avoid it when

• You are starting a new integration; Claude Fable 5.1 costs the same per token and has a newer knowledge cutoff.
• Your workload is cache-heavy; Fable 5 charges $1.00 per million cache-read tokens against $0.25 on Fable 5.1.
• Cost per call is a constraint; Claude Opus 5 covers most of the same work at $5 / $25.

Alternatives to consider

• Claude Fable 5.1 Curated

  Anthropic ● Active

  The successor in the same line at an identical $10 / $50, with a newer knowledge cutoff and cheaper cache reads.

  $10.00 in · $50.00 out / M tokens · 1M context

• Claude Opus 5 Curated

  Anthropic ● Active

  Half the price at $5 / $25 with the same 1M-token window, and Anthropic's recommended starting point for most workloads.

  $5.00 in · $25.00 out / M tokens · 1M context

• GPT-6 Astra Curated

  OpenAI ● Active

  OpenAI's top tier at the same $10 / $50, with a 1.05M-token context window and an April 2026 knowledge cutoff.

  $10.00 in · $50.00 out / M tokens · 1.1M context

• Claude Opus 4.5 Derived

  Anthropic ● Active

  Same provider, same tier (frontier), close in price; shares chat, coding, reasoning, agents and long-context.

  $5.00 in · $25.00 out / M tokens · 200K context

• Claude Fable 5 Derived

  Amazon Bedrock ● Active

  Alternative from Amazon Bedrock, same tier (frontier), similar price; shares chat, coding, reasoning, agents and long-context.

  $10.00 in · $50.00 out / M tokens · 1M context

Curated suggestions were picked by a reviewer, with the reason written by hand. Derived suggestions are ranked from the data — shared tags, the same tier and a comparable price band — not from benchmark scores. Check the capability fit yourself: we track lifecycle, price and specifications.

Sources

• platform.claude.com ↗ https://platform.claude.com/docs/en/models/fable-5/overview
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/pricing
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/models/overview
• platform.claude.com ↗ https://platform.claude.com/docs/en/about-claude/model-deprecations

Verified against the source on 10 September 2026. Dataset snapshot 10 September 2026. Providers can change a date without notice — the link above is always the final word.

About this profile

The specifications and dates above are facts from Anthropic, with the sources listed. The summary, the use-for and avoid-when lists and the curated alternatives are our assessment: editorial profile reviewed on 21 September 2026 by llm-researcher.