Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Input massimo
262.000 tokens*
Ragionamento
Sì*
Modalità API
Chat*
Input immagini
No*
Cache dei prompt
Sì*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 10 campi
cache read input token cost
1,0e-7*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
5,0e-7*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
wandb*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
262.000*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
262.144*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
2,15e-6*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Sì*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Sì*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
No*Ambito e condizioni
native_context
provider
wandb*
mode
chat*
full_native_model_id
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*