Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
perplexity/pplx-decider-flash-v1.2
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Input massimo
262.144 tokens*
Modalità API
Servizio di valutazione*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 5 campi
input cost per token
1,0e-8*Ambito e condizioni
native_context
provider
perplexity*
mode
evaluation*
full_native_model_id
perplexity/pplx-decider-flash-v1.2*
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
perplexity*Ambito e condizioni
native_context
provider
perplexity*
mode
evaluation*
full_native_model_id
perplexity/pplx-decider-flash-v1.2*
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
262.144*Ambito e condizioni
native_context
provider
perplexity*
mode
evaluation*
full_native_model_id
perplexity/pplx-decider-flash-v1.2*
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
evaluation*Ambito e condizioni
native_context
provider
perplexity*
mode
evaluation*
full_native_model_id
perplexity/pplx-decider-flash-v1.2*
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
0,0*Ambito e condizioni
native_context
provider
perplexity*
mode
evaluation*
full_native_model_id
perplexity/pplx-decider-flash-v1.2*
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.*