¿Qué modelos ofrece Anthropic?

Anthropic ofrece 26 modelos que monitoreamos: Claude Opus 5 (max), Claude Opus 5 (xhigh), Claude Fable 5 (with fallback), Claude Opus 5 (high), Claude Opus 5 (medium), Claude Opus 4.8 (max), Claude Opus 4.7 (max), Claude Sonnet 5 (max), Claude Opus 5 (low), Claude Sonnet 4.6 (max), Claude Opus 4.6 (max), Claude Opus 4.7 (Non-reasoning, high), Claude Sonnet 5 (Non-reasoning), Claude Opus 4.5, Claude Opus 4.6 (high), Claude 4.5 Sonnet, Claude Sonnet 4.6 (Non-reasoning), Claude Opus 4.5, Claude Sonnet 4.6 (Non-reasoning, Low Effort), Claude 4.5 Haiku, Claude 4.5 Sonnet, Claude 4.5 Haiku, Claude Sonnet 5 (low), Claude Sonnet 5 (xhigh), Claude Sonnet 5 (high) y Claude Sonnet 5 (medium).

Artificial Analysis

Anthropic: inteligencia, rendimiento y precio de sus modelos

Name: Inteligencia
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Anthropic

Análisis de los modelos de Anthropic en métricas clave como calidad, precio, velocidad de salida, latencia, ventana de contexto y más. Este análisis está pensado para ayudarte a elegir el mejor modelo ofrecido por Anthropic para tu caso de uso.

Más inteligente

Claude Opus 5 (max)

Claude Opus 5 (xhigh)

Claude Fable 5 (with fallback)

Claude Opus 5 (high)

Claude Opus 5 (medium)

Índice de inteligencia

26 modelos en total

Más rápido

Claude 4.5 Haiku

100 t/s

Claude 4.5 Haiku

91 t/s

Claude Sonnet 5 (max)

69 t/s

Claude Sonnet 5 (xhigh)

68 t/s

Claude Sonnet 5 (Non-reasoning)

64 t/s

Velocidad de salida

26 modelos en total

Menor precio

Claude 4.5 Haiku

$0.77

Claude 4.5 Haiku

$0.77

Claude Sonnet 5 (max)

$1.54

Claude Sonnet 5 (Non-reasoning)

$1.54

Claude Sonnet 5 (low)

$1.54

Precio combinado (por 1M de tokens)

26 modelos en total

Indica un modelo de razonamiento

Anthropic ofrece 26 modelos, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave entre modelos.

En inteligencia, los mejores modelos en Anthropic son Claude Opus 5 (max) (61), Claude Opus 5 (xhigh) (60) y Claude Fable 5 (with fallback) (60).
En velocidad de salida, los modelos más rápidos son Claude 4.5 Haiku (100 t/s), Claude 4.5 Haiku (91 t/s) y Claude Sonnet 5 (max) (69 t/s). La velocidad varía significativamente entre modelos, con una diferencia del 56% entre el más rápido y el más lento.
En latencia, Claude 4.5 Haiku (1.02s), Claude Sonnet 4.6 (Non-reasoning, Low Effort) (1.52s) y Claude Opus 4.5 (1.52s) ofrecen el menor tiempo hasta el primer token de respuesta.
En precios, Claude 4.5 Haiku ($0.77), Claude 4.5 Haiku ($0.77) y Claude Sonnet 5 (max) ($1.54) ofrecen los menores precios combinados por 1M de tokens.
En tamaño de ventana de contexto, Claude Opus 5 (max) (1M), Claude Opus 5 (xhigh) (1M) y Claude Fable 5 (with fallback) (1M) admiten las ventanas de contexto más grandes en Anthropic.
Claude 4.5 Haiku ofrece la salida más rápida y los mejores precios, lo que lo hace atractivo para aplicaciones sensibles al rendimiento y al costo. Claude Opus 5 (max) lidera en inteligencia para tareas que requieren la máxima calidad.

Aspectos destacados

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Velocidad

Output tokens per second · Higher is better

Precio

USD per 1M tokens (blended) · Lower is better

Evaluaciones de inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Estimate (independent evaluation forthcoming)

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Ventana de contexto

Context Window

Context window: tokens limit · Higher is better

Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Precios

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Resumen de rendimiento

Output Speed vs. Price

Output speed: output tokens per second · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Velocidad

Medida por la velocidad de salida (tokens por segundo)

Output Speed

Output tokens per second · Higher is better

Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latencia

Medida por el tiempo (segundos) hasta el primer token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Tiempo de respuesta de extremo a extremo

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time vs. Price

End-to-end response time: end-to-end seconds to output 500 tokens · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.


									Análisis adicional
Claude Opus 5 (max)	1M	Propietario	61	$2.03	54	75.90	85.19	--	Modelo Proveedor
Claude Opus 5 (xhigh)	1M	Propietario	60	$1.56	55	24.63	33.65	--	Modelo Proveedor
Claude Fable 5 (with fallback)	1M	Propietario	60	$2.75	63	91.02	99.01	--	Modelo Proveedor
Claude Opus 5 (high)	1M	Propietario	59	$1.06	54	12.83	22.05	--	Modelo Proveedor
Claude Opus 5 (medium)	1M	Propietario	56	$0.62	53	6.13	15.59	--	Modelo Proveedor
Claude Opus 4.8 (max)	1M	Propietario	56	$1.80	61	9.50	17.66	--	Modelo Proveedor
Claude Opus 4.7 (max)	1M	Propietario	54	$1.97	50	14.07	23.97	--	Modelo Proveedor
Claude Sonnet 5 (max)	1M	Propietario	53	$1.53	69	161.06	168.30	--	Modelo Proveedor
Claude Opus 5 (low)	1M	Propietario	51	$0.36	49	2.68	12.91	--	Modelo Proveedor
Claude Sonnet 4.6 (max)	1M	Propietario	47	$1.14	53	103.01	112.54	--	Modelo Proveedor
Claude Opus 4.6 (max)	1M	Propietario	44*	--	42	20.75	32.53	--	Modelo Proveedor
Claude Opus 4.7 (Non-reasoning, high)	1M	Propietario	43*	--	45	1.68	12.70	--	Modelo Proveedor
Claude Sonnet 5 (Non-reasoning)	1M	Propietario	42	$0.37	64	1.64	9.42	--	Modelo Proveedor
Claude Opus 4.5	200k	Propietario	41*	--	51	14.01	23.84	--	Modelo Proveedor
Claude Opus 4.6 (high)	1M	Propietario	38*	--	39	2.80	15.51	--	Modelo Proveedor
Claude 4.5 Sonnet	1M	Propietario	36	$0.41	42	11.57	23.41	--	Modelo Proveedor
Claude Sonnet 4.6 (Non-reasoning)	1M	Propietario	36*	--	44	1.56	12.89	--	Modelo Proveedor
Claude Opus 4.5	200k	Propietario	35*	--	46	1.52	12.38	--	Modelo Proveedor
Claude Sonnet 4.6 (Non-reasoning, Low Effort)	1M	Propietario	34*	--	43	1.52	13.21	--	Modelo Proveedor
Claude 4.1 Opus	200k	Propietario	34*	--	--	--	--	--	Modelo Proveedor
Claude 4 Opus	200k	Propietario	31*	--	--	--	--	--	Modelo Proveedor
Claude 4.5 Haiku	200k	Propietario	30	$0.24	100	16.79	21.78	--	Modelo Proveedor
Claude 4.5 Sonnet	1M	Propietario	29*	--	41	1.70	13.85	--	Modelo Proveedor
Claude 4 Sonnet	1M	Propietario	29	--	--	--	--	--	Modelo Proveedor
Claude 4.1 Opus	200k	Propietario	28*	--	--	--	--	--	Modelo Proveedor
Claude 4 Opus	200k	Propietario	25*	--	--	--	--	--	Modelo Proveedor
Claude 4 Sonnet	1M	Propietario	25*	--	--	--	--	--	Modelo Proveedor
Claude 4.5 Haiku	200k	Propietario	24*	--	91	1.02	6.49	--	Modelo Proveedor
Claude 3 Opus	200k	Propietario	12*	--	--	--	--	--	Modelo Proveedor
Claude Sonnet 5 (low)	1M	Propietario	--	--	61	1.85	10.02	--	Modelo Proveedor
Claude Sonnet 5 (xhigh)	1M	Propietario	--	--	68	22.03	29.42	--	Modelo Proveedor
Claude Sonnet 5 (high)	1M	Propietario	--	--	60	5.77	14.08	--	Modelo Proveedor
Claude Sonnet 5 (medium)	1M	Propietario	--	--	62	2.65	10.73	--	Modelo Proveedor

Definiciones clave

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Price per token to write prompt tokens into the cache so that later requests can hit them, represented as USD per million tokens. Some providers charge a premium over the standard input price to create a cache entry (e.g. Anthropic), while others cache automatically with no separate write fee.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

Preguntas frecuentes

Preguntas comunes sobre Anthropic

El modelo más inteligente disponible en Anthropic es Claude Opus 5 (max), con una puntuación de 61 en el Índice de Inteligencia.

El modelo más rápido en Anthropic por velocidad de salida es Claude 4.5 Haiku, con 100.3 tokens por segundo.

El modelo con el menor tiempo hasta el primer token de respuesta en Anthropic es Claude 4.5 Haiku, con 1.02s. Una menor latencia significa una respuesta inicial más rápida.

El modelo más económico en Anthropic por precio combinado es Claude 4.5 Haiku, a $0.77 por 1M de tokens (proporción 7:2:1 de aciertos de caché/entrada/salida).

Los precios en Anthropic varían hasta 10x entre modelos, desde $0.77 por 1M de tokens para Claude 4.5 Haiku hasta $7.70 por 1M de tokens para Claude Fable 5 (with fallback).

Sí, Anthropic ofrece una API compatible con OpenAI, lo que facilita cambiar desde OpenAI o usar integraciones existentes del SDK de OpenAI.

9 de 26 modelos en Anthropic admiten el modo JSON para salida estructurada.

Sí, los 26 modelos en Anthropic admiten llamadas a funciones (uso de herramientas).

Sí, Anthropic ofrece 18 modelos de razonamiento: Claude Opus 5 (max), Claude Opus 5 (xhigh), Claude Fable 5 (with fallback), Claude Opus 5 (high), Claude Opus 5 (medium), Claude Opus 4.8 (max), Claude Opus 4.7 (max), Claude Sonnet 5 (max), Claude Opus 5 (low), Claude Sonnet 4.6 (max), Claude Opus 4.6 (max), Claude Opus 4.5, Claude 4.5 Sonnet, Claude 4.5 Haiku, Claude Sonnet 5 (low), Claude Sonnet 5 (xhigh), Claude Sonnet 5 (high) y Claude Sonnet 5 (medium). Los modelos de razonamiento usan pensamiento extendido para resolver problemas complejos antes de responder.

Sí, el rendimiento de un proveedor puede variar con el tiempo debido a cambios de infraestructura, balanceo de carga y actualizaciones. Medimos continuamente a todos los proveedores y mostramos las tendencias históricas de rendimiento en los gráficos "a lo largo del tiempo".

Al elegir un modelo en Anthropic, considera: inteligencia (para tareas sensibles a la calidad), velocidad de salida (para tareas intensivas en rendimiento), latencia (para aplicaciones interactivas que requieren primeras respuestas rápidas), precios (para cargas de trabajo sensibles al costo) y funcionalidades como el tamaño de la ventana de contexto, el modo JSON o las llamadas a funciones.

Anthropic: inteligencia, rendimiento y precio de sus modelos

Más inteligente

Más rápido

Menor precio

Inteligencia

Velocidad

Precio

Evaluaciones de inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Intelligence Index vs. Price

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Cache Pricing by Provider

Model Performance Representation

Ventana de contexto

Context Window

Context Window for RAG

Context Window

Precios

Intelligence Index vs. Price

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Cache Pricing by Provider

Model Performance Representation

Resumen de rendimiento

Output Speed vs. Price

Output Speed

Price

Velocidad

Output Speed

Output Speed

Model Performance Representation

Latencia

Latency: Time To First Answer Token

Time to First Answer Token

Tiempo de respuesta de extremo a extremo

End-to-End Response Time vs. Price

Price

End-to-End Response Time

Median

Definiciones clave

Context Window

Output Speed

Latency (Time to First Token)

Index Cost per Task

Input Price

Cache Hit

Cache Write

Output Price

Time Period

Preguntas frecuentes

¿Qué modelos ofrece Anthropic?

¿Cuál es el modelo más inteligente en Anthropic?

¿Cuál es el modelo más rápido en Anthropic?

¿Qué modelo tiene la menor latencia en Anthropic?

¿Cuál es el modelo más barato en Anthropic?

¿Cuánto varían los precios entre modelos en Anthropic?

¿Es Anthropic compatible con OpenAI?

¿Anthropic admite el modo JSON?

¿Anthropic admite llamadas a funciones?

¿Anthropic ofrece modelos de razonamiento?

¿El rendimiento de Anthropic cambia con el tiempo?

¿Cómo elijo un modelo en Anthropic?