AI TOOLS RADAR
Explorar
Todos os modelos / NVIDIA
N
nvidia

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...

Ver fonte no OpenRouter Hugging Face
Visão geral

Especificações do modelo

Context
262.144 tokens
Saída máxima
131.072 tokens
Arquitetura
text->text
Tokenizador
Other
Limite de conhecimento
Not provided
Moderado
Não
Recursos e modalidades

Input → Output

Input
text
Output
text
Raciocínio

Não

API

Parâmetros de API compatíveis

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provedores disponíveis

2 provedores

DeepInfra

bf16
Context
262K
Saída máxima
131K
Input
$0.080
Output
$0.200
Leitura de cache
$0.040
Gravação de cache
Not provided

CoreWeave

bf16
Context
262K
Saída máxima
236K
Input
$0.100
Output
$0.250
Leitura de cache
$0.050
Gravação de cache
Not provided
nvidia

models

Todos os modelos
Nnvidia

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...

Context
Not provided
Input
audio
Output
transcription
Input: $3.33Output: Freeper 1M tokens
Ver detalhes do modelo →
Nnvidia

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...

Context
1M
Input
text
Output
text
Input: FreeOutput: Freeper 1M tokens
Ver detalhes do modelo →
Nnvidia

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...

Context
33K
Input
text
Output
embeddings
Input: FreeOutput: Freeper 1M tokens
Ver detalhes do modelo →