---
title: Claude Sonnet 5.5
url: https://platform.claude.com/docs/es/models/sonnet-5-5/overview
description: "Una descripción general de Claude Sonnet 5.5: para qué sirve, los IDs del modelo en cada plataforma, la ventana de contexto, los límites de salida, los precios, la disponibilidad y las guías y recursos para desarrollar con él."
---
**Latest.** Released September 28, 2026.
The best combination of speed and intelligence
Model ID: `claude-sonnet-5-5`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $2 / MTok · Output pricing: $10 / MTok
[Announcement](https://www.anthropic.com/claude-sonnet-5-5) · [What’s new](https://platform.claude.com/docs/es/models/sonnet-5-5/whats-new-sonnet-5-5) · [Migration guide](https://platform.claude.com/docs/es/models/sonnet-5-5/migration-guide)
## Descripción general
Claude Sonnet 5.5 ofrece la mejor combinación de velocidad e inteligencia. Está diseñado para cargas de trabajo cotidianas de programación, de agentes y empresariales, como generación de código, análisis de datos, creación de contenido, comprensión visual y uso agéntico de herramientas.
## Cómo se compara
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :-------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| [Claude Fable 5.2](https://platform.claude.com/docs/es/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Moderate | Adaptive (always on) | `high` | Jun 2026 |
| [Claude Opus 5.5](https://platform.claude.com/docs/es/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
| **Claude Sonnet 5.5** (this model) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
| [Claude Haiku 5.5](https://platform.claude.com/docs/es/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 5.2, Claude Mythos 5.2, 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.
## Especificaciones
### Model IDs
| Platform | Model ID |
| :--------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------- |
| Claude API | `claude-sonnet-5-5` |
| [Amazon Bedrock](https://platform.claude.com/docs/es/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-sonnet-5-5` |
| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/es/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-sonnet-5-5` |
| [Microsoft Foundry](https://platform.claude.com/docs/es/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-5-5` |
| [Claude Platform on AWS](https://platform.claude.com/docs/es/build-with-claude/claude-platform-on-aws) | `claude-sonnet-5-5` |
| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/es/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-sonnet-5-5` |
### Pricing
| Feature | Value |
| :------------------------------------------------------------------------------------- | :------------------------------- |
| Input | $2 / MTok |
| Output | $10 / MTok |
| [5m cache write](https://platform.claude.com/docs/es/build-with-claude/prompt-caching) | $2.50 / MTok |
| [1h cache write](https://platform.claude.com/docs/es/build-with-claude/prompt-caching) | $4 / MTok |
| [Cache read](https://platform.claude.com/docs/es/build-with-claude/prompt-caching) | $0.10 / MTok |
| [Batch API](https://platform.claude.com/docs/es/build-with-claude/batch-processing) | 50% discount on input and output |
[Full price list](https://platform.claude.com/docs/es/about-claude/pricing)
### Capabilities
| Feature | Value |
| :-------------------------------------------------------------------------------------------------------------------------- | :--------------------- |
| [Context window](https://platform.claude.com/docs/es/build-with-claude/context-windows) | 1M tokens |
| Max output | 128K tokens |
| [Max output (Batch API, beta)](https://platform.claude.com/docs/es/build-with-claude/batch-processing#extended-output-beta) | 300K tokens |
| [Thinking](https://platform.claude.com/docs/es/build-with-claude/thinking) | Adaptive |
| [Default effort](https://platform.claude.com/docs/es/build-with-claude/effort) | `high` |
| Comparative latency | Fast |
| 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/es/about-claude/model-deprecations) | Active (latest) |
| Released | September 28, 2026 |
| Retirement | Not sooner than September 28, 2027 |
| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/es/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/es/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/es/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/es/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/es/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
## Información útil
* El “adaptive thinking” (pensamiento adaptativo) está activado de forma predeterminada. La configuración de pensamiento más baja es `between_tools`, que desactiva el pensamiento inicial. Funciona con un esfuerzo `high` o inferior. Consulta [Novedades de Claude Sonnet 5.5](https://platform.claude.com/docs/es/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).
* Establecer `temperature`, `top_p` o `top_k` devuelve un error 400.
* La longitud mínima de prompt que se puede almacenar en caché es de 512 tokens. Consulta [“Prompt caching” (almacenamiento en caché de prompts)](https://platform.claude.com/docs/es/build-with-claude/prompt-caching#cache-limitations).
* En la [Message Batches API](https://platform.claude.com/docs/es/build-with-claude/batch-processing#extended-output-beta), Claude Sonnet 5.5 admite hasta 300k tokens de salida con el encabezado beta `output-300k-2026-03-24`.
* Consulta los límites y las capacidades de forma programática con la [Models API](https://platform.claude.com/docs/es/api/models/list).
## Recursos
Diferencias de comportamiento y patrones de prompts específicos de Claude Sonnet 5.5.
El control de la profundidad del pensamiento, la latencia y el costo. Elige un nivel para cada carga de trabajo.
Cómo funciona el pensamiento adaptativo, qué configuraciones de pensamiento acepta cada modelo y cómo se conservan los bloques de pensamiento.
## Referencia
La indicación del sistema que Claude Sonnet 5.5 usa en claude.ai y en las aplicaciones de Claude.
Evaluaciones de seguridad y decisiones de implementación para Claude Sonnet 5.5.
Lista completa de precios, incluidos los descuentos por lotes y las tarifas de almacenamiento en caché de prompts.
Cómo funcionan los IDs de modelo, los alias y las instantáneas fijadas.
Estado del ciclo de vida y compromisos de retiro para cada modelo de Claude.