¿Dónde puedo acceder a Granite 4.0 H Small?

Artificial Analysis

IBM

•

Open weights model

•

Released septiembre de 2025

Granite 4.0 H Small Benchmarks y análisis de proveedores de API

Comparación de modelos

Este análisis está pensado para ayudarte a elegir el mejor proveedor de API de Granite 4.0 H Small para tu caso de uso.

Más rápido

Velocidad de salida

0 proveedores en total

Menor latencia

Tiempo hasta el primer token

0 proveedores en total

Menor precio

Precio combinado (por 1M de tokens)

0 proveedores en total

Actualmente no hay proveedores de API disponibles para Granite 4.0 H Small.

Los benchmarks de proveedores no están disponibles para este modelo.

Consulta la página del modelo Granite 4.0 H Small para ver detalles del modelo y cómo se compara su inteligencia con otros modelos.

Velocidad

Output tokens per second · Higher is better

No data available

Latencia

Seconds to first answer token received · Lower is better

No data available

Precio

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

No data available

Actualización: La carga de trabajo predeterminada de medición de rendimiento se actualizó a 10k tokens de entrada para reflejar mejor los casos de uso en producción. Aún puedes seleccionar distintas cargas de trabajo arriba.

Precios

Precios: aciertos de caché, entrada y salida: Granite 4.0 H Small

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

No data available

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.

Costo por tarea del Intelligence Index: Granite 4.0 H Small

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Velocidad de salida vs. precio: Granite 4.0 H Small

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

Most attractive quadrant

No data available

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).

Velocidad

Medida por la velocidad de salida (tokens por segundo)

Velocidad de salida: Granite 4.0 H Small

Velocidad de salida: tokens de salida por segundo · 10,000 input tokens

No data available

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 or the median across providers where a first-party API is not available.

Tiempo por tarea del Intelligence Index: Granite 4.0 H Small

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

No data available

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Costo por tarea vs. tiempo por tarea: Granite 4.0 H Small

Weighted average cost (USD) per Intelligence Index task · Weighted average decode time (minutes) per Intelligence Index task

Most attractive quadrant

No data available

Latencia

Medida por el tiempo (segundos) hasta el primer token

Tiempo hasta el primer token: Granite 4.0 H Small

Seconds to first token received · Lower is better · 10,000 input tokens

No data available

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.

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

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

Tiempo de respuesta de extremo a extremo: Granite 4.0 H Small

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

No data available

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

Métricas clave de comparación y funciones de API



No results.

Preguntas frecuentes

Preguntas comunes sobre los proveedores de Granite 4.0 H Small

Granite 4.0 H Small no está disponible actualmente a través de ningún proveedor de API que midamos. Como modelo de pesos abiertos, puede alojarse por cuenta propia.

Granite 4.0 H Small Benchmarks y análisis de proveedores de API

Más rápido

Menor latencia

Menor precio

Velocidad

Latencia

Precio

Precios

Precios: aciertos de caché, entrada y salida: Granite 4.0 H Small

Cache Hit

Costo por tarea del Intelligence Index: Granite 4.0 H Small

Cost per Intelligence Index Task

Velocidad de salida vs. precio: Granite 4.0 H Small

Output Speed

Velocidad

Velocidad de salida: Granite 4.0 H Small

Output Speed

Model Performance Representation

Tiempo por tarea del Intelligence Index: Granite 4.0 H Small

Time per Intelligence Index Task

Costo por tarea vs. tiempo por tarea: Granite 4.0 H Small

Cost per Intelligence Index Task

Latencia

Tiempo hasta el primer token: Granite 4.0 H Small

Latency (Time to First Token)

Median

Tiempo de respuesta de extremo a extremo

Tiempo de respuesta de extremo a extremo: Granite 4.0 H Small

End-to-End Response Time

Métricas clave de comparación y funciones de API

Preguntas frecuentes

¿Dónde puedo acceder a Granite 4.0 H Small?