AI TOOLS RADAR
Explorar
Todos los modelos / NVIDIA
nvidia logo
nvidia

NVIDIA: Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). $0.50 per million input tokens, $2.20 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

Ver fuente en OpenRouter Hugging Face
Resumen

Especificaciones del modelo

Contexto
262.144 tokens
Salida máxima
16.384 tokens
Arquitectura
text->text
Tokenizador
Other
Corte de conocimiento
No indicado
Moderado
No
OPENROUTER

Precios completos

Tarifas sincronizadas desde OpenRouter, por millón de tokens.

Entrada
$0.5
/M tokens
Salida
$2.2
/M tokens
Lectura de caché
$0.1
/M tokens
API

Configuración del modelo

Parámetros predeterminados

temperature
1
top_p
0.95

Razonamiento

Moderado
No
Parámetros predeterminados
high
Capacidades y modalidades
high, medium
API

Inicio rápido

Usa este modelo mediante la API compatible con OpenAI de OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello!"}]}'
Capacidades y modalidades

Entrada → Salida

Entrada
text
Salida
text
Razonamiento

Sí · high · medium

API

Parámetros API compatibles

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Proveedores disponibles

3 proveedores

Proveedores en vivo en OpenRouter

Disponibilidad, latencia, rendimiento y enrutamiento cambian continuamente. Consulta la fuente para datos actuales.

OpenRouter

DeepInfra

fp4
Contexto
262K
Salida máxima
16K
Entrada
$0.500
Salida
$2.20
Lectura de caché
$0.100
Escritura de caché
No indicado

BaseTen

fp4
Contexto
203K
Salida máxima
183K
Entrada
$0.600
Salida
$2.40
Lectura de caché
$0.120
Escritura de caché
No indicado

Venice

fp8
Contexto
256K
Salida máxima
33K
Entrada
$0.625
Salida
$3.13
Lectura de caché
$0.188
Escritura de caché
No indicado
nvidia

modelos

Todos los modelos
nvidia logonvidia

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...

Contexto
No indicado
Entrada
audio
Salida
transcription
Entrada: $3.33Salida: Gratispor millón de tokens
Ver detalles del modelo →
nvidia logonvidia

NVIDIA: Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

Contexto
262K
Entrada
text
Salida
text
Entrada: $0.080Salida: $0.200por millón de tokens
Ver detalles del modelo →
nvidia logonvidia

NVIDIA: Nemotron 3.5 Lightning (free)

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

Contexto
1M
Entrada
text
Salida
text
Entrada: GratisSalida: Gratispor millón de tokens
Ver detalles del modelo →
nvidia logonvidia

NVIDIA: Nemotron 3 Embed 1B (free)

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval...

Contexto
33K
Entrada
text
Salida
embeddings
Entrada: GratisSalida: Gratispor millón de tokens
Ver detalles del modelo →