¿Qué modelos ofrece Nebius?

Nebius ofrece 28 modelos que monitoreamos: Kimi K3, MiniMax-M3 (FP8), Kimi K2.6, Kimi K2.7 Code (FP4), GLM-5.1 (FP8, Base), Nemotron 3 Ultra, GLM-5.1 (FP8, Base), Kimi K2.6, Qwen3.5 397B A17B (Base, FP4), MiniMax-M2.5 (FP4), Qwen3.5 397B A17B (Base, FP4), NVIDIA Nemotron 3 Super, gpt-oss-120b (high) (Base), Qwen3 235B 2507, Qwen3 Next 80B A3B (FP8), Nemotron 3 Nano Omni 30B A3B Reasoning (FP8), gpt-oss-120b (low) Base, NVIDIA Nemotron 3 Nano, Qwen3 32B Base, Hermes 4 70B (FP8), Llama 3.3 70B Base, Llama Nemotron Ultra Base, Qwen3 30B A3B 2507, Hermes 4 405B (FP8), Hermes 4 405B (FP8), Qwen3 32B Base, Gemma 3 27B (FP8) y Hermes 4 70B (FP8).

Artificial Analysis

Nebius: inteligencia, rendimiento y precio de sus modelos

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

Nebius

Análisis de los modelos de Nebius 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 Nebius para tu caso de uso.

Más inteligente

Kimi K3

MiniMax-M3 (FP8)

Kimi K2.6

Kimi K2.7 Code (FP4)

GLM-5.1 (FP8, Base)

Índice de inteligencia

28 modelos en total

Más rápido

NVIDIA Nemotron 3 Super

345 t/s

Nemotron 3 Ultra

334 t/s

NVIDIA Nemotron 3 Nano

319 t/s

Nemotron 3 Nano Omni 30B A3B Reasoning (FP8)

309 t/s

gpt-oss-120b (low) Base

242 t/s

Velocidad de salida

28 modelos en total

Menor precio

Nemotron 3 Nano Omni 30B A3B Reasoning (FP8)

$0.08

NVIDIA Nemotron 3 Nano

$0.08

Qwen3 32B Base

$0.12

Qwen3 30B A3B 2507

$0.12

Qwen3 32B Base

$0.12

Precio combinado (por 1M de tokens)

28 modelos en total

Indica un modelo de razonamiento

Nebius ofrece 28 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 Nebius son Kimi K3 (57), MiniMax-M3 (FP8) (44) y Kimi K2.6 (44).
En velocidad de salida, los modelos más rápidos son NVIDIA Nemotron 3 Super (345 t/s), Nemotron 3 Ultra (334 t/s) y NVIDIA Nemotron 3 Nano (319 t/s).
En latencia, Qwen3 30B A3B 2507 (1.05s), Hermes 4 70B (FP8) (1.37s) y Qwen3 235B 2507 (1.44s) ofrecen el menor tiempo hasta el primer token de respuesta.
En precios, Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) ($0.08), NVIDIA Nemotron 3 Nano ($0.08) y Qwen3 32B Base ($0.12) ofrecen los menores precios combinados por 1M de tokens.
En tamaño de ventana de contexto, MiniMax-M3 (FP8) (1M), Kimi K3 (1M) y Kimi K2.6 (262k) admiten las ventanas de contexto más grandes en Nebius.

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
Kimi K3	1.05M	Abierto	57	$2.53	80	1.74	33.00	25.00	Modelo Proveedor
GLM-5.2 (max) (FP4)	432k	Abierto	51	$0.90	--	--	--	--	Modelo Proveedor
MiniMax-M3 (FP8)	1.05M	Abierto	44	$0.40	154	1.99	18.23	12.99	Modelo Proveedor
DeepSeek V4 Pro (max)	1M	Abierto	44	$0.77	--	--	--	--	Modelo Proveedor
Kimi K2.6	262k	Abierto	44	$0.66	113	1.98	45.93	39.51	Modelo Proveedor
DeepSeek V4 Pro (high)	1M	Abierto	43	$0.85	--	--	--	--	Modelo Proveedor
Kimi K2.7 Code (FP4)	256k	Abierto	42	$0.56	220	1.78	14.16	10.11	Modelo Proveedor
GLM-5.1 (FP8, Base)	200k	Abierto	40	$0.49	29	1.80	148.88	129.94	Modelo Proveedor
Nemotron 3 Ultra	256k	Abierto	38	$0.54	334	2.26	10.57	6.81	Modelo Proveedor
GLM-5.1 (FP8, Base)	200k	Abierto	35*	--	28	1.81	19.77	--	Modelo Proveedor
Kimi K2.6	262k	Abierto	35*	--	116	1.97	6.29	--	Modelo Proveedor
GLM-5.2 (FP4)	432k	Abierto	34	--	--	--	--	--	Modelo Proveedor
Qwen3.5 397B A17B (Base, FP4)	262k	Abierto	34	$0.33	96	1.99	40.39	33.19	Modelo Proveedor
MiniMax-M2.5 (FP4)	196k	Abierto	34*	--	98	1.82	27.30	20.38	Modelo Proveedor
Qwen3.5 397B A17B (Base, FP4)	262k	Abierto	32*	--	104	2.03	6.85	--	Modelo Proveedor
DeepSeek V4 Pro	1.05M	Abierto	31*	--	--	--	--	--	Modelo Proveedor
NVIDIA Nemotron 3 Super	256k	Abierto	25	$0.29	345	1.79	9.03	5.79	Modelo Proveedor
gpt-oss-120b (high) (Base)	128k	Abierto	24	$0.06	242	1.03	11.37	8.27	Modelo Proveedor
Qwen3 235B 2507	262k	Abierto	18*	--	56	1.44	10.34	--	Modelo Proveedor
Qwen3 Next 80B A3B (FP8)	262k	Abierto	17	$0.04	100	1.05	26.01	19.96	Modelo Proveedor
Nemotron 3 Nano Omni 30B A3B Reasoning (FP8)	65.5k	Abierto	15*	--	309	1.01	9.11	6.48	Modelo Proveedor
gpt-oss-120b (low) Base	128k	Abierto	15	$0.02	242	1.00	11.34	8.27	Modelo Proveedor
NVIDIA Nemotron 3 Nano	262k	Abierto	14	$0.02	319	1.03	8.88	6.28	Modelo Proveedor
Qwen3 32B Base	32.8k	Abierto	12	--	27	2.02	94.91	74.31	Modelo Proveedor
Hermes 4 70B (FP8)	128k	Abierto	10*	--	88	1.39	29.85	22.77	Modelo Proveedor
Llama 3.3 70B Base	128k	Abierto	9	$0.02	17	2.67	32.38	--	Modelo Proveedor
Llama Nemotron Ultra Base	131k	Abierto	9*	--	51	2.34	51.13	39.03	Modelo Proveedor
Qwen3 30B A3B 2507	262k	Abierto	9*	--	72	1.05	8.04	--	Modelo Proveedor
Hermes 4 405B (FP8)	128k	Abierto	9*	--	36	2.39	71.65	55.40	Modelo Proveedor
Hermes 4 405B (FP8)	128k	Abierto	9*	--	35	2.39	16.71	--	Modelo Proveedor
Qwen3 32B Base	32.8k	Abierto	9*	--	27	1.91	20.52	--	Modelo Proveedor
Gemma 3 27B (FP8)	110k	Abierto	7	$0.08	25	3.28	23.05	--	Modelo Proveedor
Hermes 4 70B (FP8)	128k	Abierto	7*	--	94	1.37	6.69	--	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 Nebius

El modelo más inteligente disponible en Nebius es Kimi K3, con una puntuación de 57 en el Índice de Inteligencia.

El modelo más rápido en Nebius por velocidad de salida es NVIDIA Nemotron 3 Super, con 345.5 tokens por segundo.

El modelo con el menor tiempo hasta el primer token de respuesta en Nebius es Qwen3 30B A3B 2507, con 1.05s. Una menor latencia significa una respuesta inicial más rápida.

El modelo más económico en Nebius por precio combinado es Nemotron 3 Nano Omni 30B A3B Reasoning (FP8), a $0.08 por 1M de tokens (proporción 7:2:1 de aciertos de caché/entrada/salida).

Los precios en Nebius varían hasta 54x entre modelos, desde $0.08 por 1M de tokens para Nemotron 3 Nano Omni 30B A3B Reasoning (FP8) hasta $4.20 por 1M de tokens para Kimi K3.

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

Sí, los 28 modelos en Nebius admiten el modo JSON para salida estructurada.

Sí, los 28 modelos en Nebius admiten llamadas a funciones (uso de herramientas).

Sí, Nebius ofrece 18 modelos de razonamiento: Kimi K3, MiniMax-M3 (FP8), Kimi K2.6, Kimi K2.7 Code (FP4), GLM-5.1 (FP8, Base), Nemotron 3 Ultra, Qwen3.5 397B A17B (Base, FP4), MiniMax-M2.5 (FP4), NVIDIA Nemotron 3 Super, gpt-oss-120b (high) (Base), Qwen3 Next 80B A3B (FP8), Nemotron 3 Nano Omni 30B A3B Reasoning (FP8), gpt-oss-120b (low) Base, NVIDIA Nemotron 3 Nano, Qwen3 32B Base, Hermes 4 70B (FP8), Llama Nemotron Ultra Base y Hermes 4 405B (FP8). Los modelos de razonamiento usan pensamiento extendido para resolver problemas complejos antes de responder.

Sí, los 28 modelos en Nebius son modelos de pesos abiertos.

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 Nebius, 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.

Nebius: inteligencia, rendimiento y precio de sus modelos

Más inteligente

Más rápido

Menor precio

Inteligencia

Velocidad

Precio