AI TOOLS RADAR
Esplora
Tutti i modelli / NVIDIA
nvidia logo
nvidia

NVIDIA: Nemotron 3 Ultra (batch)

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). $0.60 per million input tokens, $3.60 per million output tokens. 512,288 token context window. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

Vedi la fonte su OpenRouter Hugging Face
Panoramica

Specifiche del modello

Contesto
512.288 tokens
Output massimo
461.059 tokens
Architettura
text->text
Tokenizer
Other
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.6
/M tokens
Output
$3.6
/M tokens
Lettura cache
$0.2
/M tokens
API

Configurazione del modello

Parametri predefiniti

temperature
1
top_p
0.95

Ragionamento

Moderato
No
Parametri predefiniti
high
Capacità e modalità
high, medium
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di 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:batch","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
text
Output
text
Ragionamento

Sì · high · medium

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Provider disponibili

3 provider

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

DeepInfra

fp4
Contesto
262K
Output massimo
16K
Input
$0.500
Output
$2.20
Lettura cache
$0.100
Scrittura cache
Non indicato

BaseTen

fp4
Contesto
203K
Output massimo
183K
Input
$0.600
Output
$2.40
Lettura cache
$0.120
Scrittura cache
Non indicato

Venice

fp8
Contesto
256K
Output massimo
33K
Input
$0.625
Output
$3.13
Lettura cache
$0.188
Scrittura cache
Non indicato
nvidia

modelli

Tutti i modelli
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...

Contesto
Non indicato
Input
audio
Output
transcription
Input: $3.33Output: Gratuitoper milione di token
Vedi i dettagli del modello →
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...

Contesto
262K
Input
text
Output
text
Input: $0.080Output: $0.200per milione di token
Vedi i dettagli del modello →
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...

Contesto
1M
Input
text
Output
text
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →
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...

Contesto
33K
Input
text
Output
embeddings
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →