Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
together_ai/nvidia/nemotron-3-ultra-550b-a55b
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Input massimo
512.288 tokens*
Modalità API
Chat*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 8 campi
cache read input token cost
2,0e-7*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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.*
deprecation date
2026-08-27*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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
6,0e-7*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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
together_ai*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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
512.288*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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
512.288*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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
together_ai*
mode
chat*
full_native_model_id
together_ai/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
3,6e-6*Ambito e condizioni
native_context
provider
together_ai*
mode
chat*
full_native_model_id
together_ai/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.*