---
title: Claude Fable 5.1
url: https://platform.claude.com/docs/it/models/fable-5-1/overview
description: "Claude Fable 5.1 in sintesi: a cosa serve, ID del modello su ogni piattaforma, finestra di contesto, limiti di output, prezzi, disponibilità e risorse per sviluppare con esso."
---

**Latest.** Released September 1, 2026.

For demanding reasoning and long-horizon agentic work

Model ID: `claude-fable-5-1`

Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok

[Announcement](https://www.anthropic.com/claude-fable-and-mythos-5-1) · [What’s new](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1) · [Migration guide](https://platform.claude.com/docs/it/models/fable-5-1/migration-guide)

## Panoramica

Claude Fable 5.1 estende Claude Fable 5 agli stessi prezzi di input e output, con letture dalla cache a un quarto del costo, e offre prestazioni migliori nella programmazione agentica di lunga durata, nella ricerca in più passaggi e nel lavoro su documenti, fogli di calcolo e presentazioni. Per la maggior parte dei carichi di lavoro, inizia con Claude Opus 5.5 (consulta [Scegliere un modello](https://platform.claude.com/docs/it/about-claude/models/choosing-a-model)). Usa Claude Fable 5.1 per il ragionamento impegnativo e il lavoro agentico a lungo orizzonte, oppure quando le tue valutazioni su Claude Opus 5.5 con un effort più elevato risultano ancora insufficienti. Claude Mythos 5.1 offre le stesse capacità solo alle organizzazioni verificate tramite i programmi di verifica di Anthropic, come il [Cyber Verification Program](https://support.claude.com/en/articles/14604842).

Se chiami già Claude Fable 5, tre modifiche sono incompatibili: [l'uso forzato degli strumenti restituisce un errore](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported), [solo Claude Fable 5.1 e Claude Mythos 5.1 possono leggere i blocchi di ragionamento di Claude Fable 5.1](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them) e [la modifica dei turni precedenti invalida i blocchi di ragionamento](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks). Cinque sono aggiuntive: [effort per messaggio](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta) (beta), [messaggi di sistema limitati al turno](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta) (beta), [aggiornamenti di avanzamento leggibili tra le chiamate agli strumenti](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#progress-updates-between-tool-calls-beta) (`display: "updates"`, beta), un [prezzo inferiore per le letture dalla cache](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#pricing) e la [provenienza dei contenuti](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1#content-provenance).

[Novità in Claude Fable 5.1](https://platform.claude.com/docs/it/models/fable-5-1/whats-new-fable-5-1)

## Claude Fable 5.1 e Claude Mythos 5.1

[Claude Mythos 5.1](https://platform.claude.com/docs/it/models/mythos-5-1/overview) offre le stesse capacità solo alle organizzazioni verificate tramite i programmi di verifica di Anthropic, come il [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Condivide le specifiche e i prezzi di Claude Fable 5.1. Per richiedere l'accesso, candidati al programma che copre il tuo caso d'uso oppure contatta il tuo team account di Anthropic, AWS o Google Cloud.

## Come si confronta

| Model                                                                               | Context | Max output | Price / MTok       | Latency  | Thinking             | Default effort | Knowledge cutoff |
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| **Claude Fable 5.1** (this model)                                                   | 1M      | 128K       | $10 / $50          | Slower   | Adaptive (always on) | `high`         | Jun 2026         |
| [Claude Opus 5.5](https://platform.claude.com/docs/it/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/it/models/sonnet-5-5/overview) | 1M      | 128K       | $2 / $10           | Fast     | Adaptive             | `high`         | Jun 2026         |
| [Claude Haiku 5.5](https://platform.claude.com/docs/it/models/haiku-5-5/overview)   | 1M      | 128K       | From $0.10 / $0.50 | Fastest  | Adaptive             | `medium`       | Jun 2026         |

* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.

## Specifiche

### Model IDs

| Platform                                                                                               | Model ID                     |
| :----------------------------------------------------------------------------------------------------- | :--------------------------- |
| Claude API                                                                                             | `claude-fable-5-1`           |
| [Amazon Bedrock](https://platform.claude.com/docs/it/build-with-claude/claude-in-amazon-bedrock)       | `anthropic.claude-fable-5-1` |
| [Google Cloud](https://platform.claude.com/docs/it/build-with-claude/claude-on-vertex-ai)              | `claude-fable-5-1`           |
| [Microsoft Foundry](https://platform.claude.com/docs/it/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-1`           |
| [Claude Platform on AWS](https://platform.claude.com/docs/it/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1`           |

### Pricing

| Feature                                                                                | Value                            |
| :------------------------------------------------------------------------------------- | :------------------------------- |
| Input                                                                                  | $10 / MTok                       |
| Output                                                                                 | $50 / MTok                       |
| [5m cache write](https://platform.claude.com/docs/it/build-with-claude/prompt-caching) | $12.50 / MTok                    |
| [1h cache write](https://platform.claude.com/docs/it/build-with-claude/prompt-caching) | $20 / MTok                       |
| [Cache read](https://platform.claude.com/docs/it/build-with-claude/prompt-caching)     | $0.25 / MTok                     |
| [Batch API](https://platform.claude.com/docs/it/build-with-claude/batch-processing)    | 50% discount on input and output |

[Full price list](https://platform.claude.com/docs/it/about-claude/pricing)

### Capabilities

| Feature                                                                                 | Value                  |
| :-------------------------------------------------------------------------------------- | :--------------------- |
| [Context window](https://platform.claude.com/docs/it/build-with-claude/context-windows) | 1M tokens              |
| Max output                                                                              | 128K tokens            |
| [Thinking](https://platform.claude.com/docs/it/build-with-claude/thinking)              | Adaptive (always on)   |
| [Default effort](https://platform.claude.com/docs/it/build-with-claude/effort)          | `high`                 |
| Comparative latency                                                                     | Slower                 |
| Input → output                                                                          | Text and images → text |
| Reliable knowledge cutoff                                                               | Jun 2026               |
| Training data cutoff                                                                    | Jun 2026               |

### Availability

| Feature                                                                       | Value                                                                                                                                                                                                                                                                                                                                                                                                                   |
| :---------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Status](https://platform.claude.com/docs/it/about-claude/model-deprecations) | Active (latest)                                                                                                                                                                                                                                                                                                                                                                                                         |
| Released                                                                      | September 1, 2026                                                                                                                                                                                                                                                                                                                                                                                                       |
| Retirement                                                                    | Not sooner than September 1, 2027                                                                                                                                                                                                                                                                                                                                                                                       |
| Platforms                                                                     | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/it/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/it/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/it/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/it/build-with-claude/claude-platform-on-aws) |

## Risorse

<CardGroup cols={3}>
  <Card title="Prompting per Claude Fable 5.1" icon="lightbulb" href="https://platform.claude.com/docs/it/build-with-claude/prompt-engineering/prompting-claude-fable-5-1">
    Indicazioni sui prompt specifiche per il modello, per lavori a lungo orizzonte e agentici.
  </Card>

  <Card title="Guida alla migrazione a Claude Fable 5.1" icon="arrow-right" href="https://platform.claude.com/docs/it/models/fable-5-1/migration-guide">
    Cosa cambia quando passi da Claude Fable 5, Claude Opus 5 o Claude Opus 4.8.
  </Card>

  <Card title="Ragionamento preservato" icon="brain" href="https://platform.claude.com/docs/it/build-with-claude/thinking#preserved-thinking">
    Quando i "thinking blocks" (blocchi di ragionamento) di questo modello restano utilizzabili: tra cambi di modello e tra modifiche alla conversazione.
  </Card>

  <Card title="Effort per messaggio" icon="sliders" href="https://platform.claude.com/docs/it/build-with-claude/effort#change-effort-mid-conversation-beta">
    Cambia il livello di "effort" (impegno) a metà conversazione senza invalidare la cache dei prompt.
  </Card>

  <Card title="Rifiuti e fallback" icon="shield" href="https://platform.claude.com/docs/it/build-with-claude/refusals-and-fallback">
    Gestisci i rifiuti del classificatore e riprova con un altro modello Claude.
  </Card>

  <Card title="Ragionamento adattivo" icon="brain" href="https://platform.claude.com/docs/it/build-with-claude/thinking">
    L'unica modalità di ragionamento su Claude Fable 5.1. Regola la profondità con `effort`.
  </Card>
</CardGroup>

## Riferimenti

<CardGroup cols={3}>
  <Card title="Prompt di sistema" icon="text" href="https://platform.claude.com/docs/it/release-notes/system-prompts/claude-fable-5-1">
    Il prompt di sistema che Claude Fable 5.1 usa su claude.ai e nelle app Claude.
  </Card>

  <Card title="System card" icon="file" href="https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card">
    Valutazioni di sicurezza e decisioni di distribuzione per Claude Fable 5.1 e Claude Mythos 5.1.
  </Card>

  <Card title="Prezzi" icon="coins" href="https://platform.claude.com/docs/it/about-claude/pricing">
    Listino prezzi completo, inclusi gli sconti batch e le tariffe della cache dei prompt.
  </Card>

  <Card title="ID dei modelli e versionamento" icon="fingerprint" href="https://platform.claude.com/docs/it/about-claude/models/model-ids-and-versions">
    Come funzionano gli ID dei modelli, gli alias e gli snapshot fissati.
  </Card>

  <Card title="Deprecazioni dei modelli" icon="clock" href="https://platform.claude.com/docs/it/about-claude/model-deprecations">
    Stato del ciclo di vita e impegni di ritiro per ogni modello Claude.
  </Card>
</CardGroup>
