---
title: Claude Haiku 5.5
url: https://platform.claude.com/docs/it/models/haiku-5-5/overview
description: "Claude Haiku 5.5 in sintesi: a cosa serve, ID del modello su ogni piattaforma, finestra di contesto, limiti di output, prezzi, disponibilità e le guide e risorse per sviluppare con esso."
---
**Latest.** Released October 7, 2026.
For high-volume, latency-sensitive tasks such as classification, extraction, and routing
Model ID: `claude-haiku-5-5`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: From $0.10 / MTok · Output pricing: From $0.50 / MTok
[Announcement](https://www.anthropic.com/claude-haiku-5-5) · [What’s new](https://platform.claude.com/docs/it/models/haiku-5-5/whats-new-haiku-5-5) · [Migration guide](https://platform.claude.com/docs/it/models/haiku-5-5/migration-guide)
## Panoramica
Claude Haiku 5.5 è progettato per carichi di lavoro ad alto volume e sensibili alla "latency" (latenza), come classificazione, instradamento, estrazione e attività di subagenti. Supporta l'"adaptive thinking" (ragionamento adattivo) con il parametro effort, una "context window" (finestra di contesto) da 1M token e fino a 128k token di output. Utilizza lo stesso tokenizer più recente di Claude 4.7 e dei modelli successivi, quindi lo stesso testo corrisponde a circa il 30% di token in più rispetto a Claude Haiku 4.5. I suoi blocchi di ragionamento funzionano solo nell'account che li ha prodotti o in un account collegato a esso.
Per le modifiche al codice, consulta la [guida alla migrazione](https://platform.claude.com/docs/it/models/haiku-5-5/migration-guide). Per ID dei modelli, prezzi e limiti, consulta la [panoramica di Claude Haiku 5.5](https://platform.claude.com/docs/it/models/haiku-5-5/overview). Per indicazioni sulla scrittura dei prompt, consulta [Prompting per Claude Haiku 5.5](https://platform.claude.com/docs/it/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).
[Novità di Claude Haiku 5.5](https://platform.claude.com/docs/it/models/haiku-5-5/whats-new-haiku-5-5)
## Come si confronta
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| [Claude Fable 5.1](https://platform.claude.com/docs/it/models/fable-5-1/overview) | 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** (this model) | 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-haiku-5-5` |
| [Amazon Bedrock](https://platform.claude.com/docs/it/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-5-5` |
| [Google Cloud](https://platform.claude.com/docs/it/build-with-claude/claude-on-vertex-ai) | `claude-haiku-5-5` |
| [Microsoft Foundry](https://platform.claude.com/docs/it/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-5-5` |
| [Claude Platform on AWS](https://platform.claude.com/docs/it/build-with-claude/claude-platform-on-aws) | `claude-haiku-5-5` |
### Pricing
| Feature | Value |
| :------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------- |
| Input | $0.10 / MTok for prompts up to 100,000 tokens; $0.50 / MTok for prompts over 100,000 tokens |
| Output | $0.50 / MTok for prompts up to 100,000 tokens; $2.50 / MTok for prompts over 100,000 tokens |
| [5m cache write](https://platform.claude.com/docs/it/build-with-claude/prompt-caching) | $0.125 / MTok for prompts up to 100,000 tokens; $0.625 / MTok for prompts over 100,000 tokens |
| [1h cache write](https://platform.claude.com/docs/it/build-with-claude/prompt-caching) | $0.20 / MTok for prompts up to 100,000 tokens; $1 / MTok for prompts over 100,000 tokens |
| [Cache read](https://platform.claude.com/docs/it/build-with-claude/prompt-caching) | $0.01 / MTok for prompts up to 100,000 tokens; $0.05 / MTok for prompts over 100,000 tokens |
| [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 |
| [Max output (Batch API, beta)](https://platform.claude.com/docs/it/build-with-claude/batch-processing#extended-output-beta) | 300K tokens |
| [Thinking](https://platform.claude.com/docs/it/build-with-claude/thinking) | Adaptive |
| [Default effort](https://platform.claude.com/docs/it/build-with-claude/effort) | `medium` |
| Comparative latency | Fastest |
| 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 | October 7, 2026 |
| Retirement | Not sooner than October 7, 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) |
## Da sapere
* L'"adaptive thinking" (ragionamento adattivo) è attivo per impostazione predefinita. Controlla la profondità del ragionamento con il [parametro effort](https://platform.claude.com/docs/it/build-with-claude/effort).
* Ometti `temperature`, `top_p` e `top_k`. Consulta [Rimuovi i parametri di campionamento](https://platform.claude.com/docs/it/models/haiku-5-5/migration-guide#remove-sampling-parameters) per i valori che restituiscono un errore 400.
* Sulla [Message Batches API](https://platform.claude.com/docs/it/build-with-claude/batch-processing#extended-output-beta), Claude Haiku 5.5 supporta fino a 300k token di output con l'header beta `output-300k-2026-03-24`.
* La lunghezza minima di un prompt memorizzabile nella cache è di 512 token. Consulta [Cache dei prompt](https://platform.claude.com/docs/it/build-with-claude/prompt-caching#cache-limitations).
* Interroga limiti e capacità in modo programmatico con la [Models API](https://platform.claude.com/docs/it/api/models/list).
## Risorse
Differenze comportamentali e schemi di prompting specifici per Claude Haiku 5.5.
Scegli un modello e un livello di effort, struttura i prompt e trasmetti l'output in streaming per risposte più rapide.
Claude Haiku 5.5 determina quando e quanto ragionare. Regola la profondità con `effort`.
Come viene conteggiata e gestita la "context window" (finestra di contesto).
## Riferimento
Il prompt di sistema che Claude Haiku 5.5 utilizza su claude.ai e nelle app Claude.
Valutazioni di sicurezza e decisioni di distribuzione per Claude Haiku 5.5.
Listino prezzi completo, inclusi gli sconti batch e le tariffe della cache dei prompt.
Come funzionano gli ID dei modelli, gli alias e gli snapshot fissati.
Stato del ciclo di vita e impegni di ritiro per ogni modello Claude.