Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
fireworks_ai/accounts/fireworks/routers/rune
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 · 6 campi
cache read input token cost
8,4e-9*Ambito e condizioni
native_context
provider
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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
4,2e-8*Ambito e condizioni
native_context
provider
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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
fireworks_ai*Ambito e condizioni
native_context
provider
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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
fireworks_ai*
mode
evaluation*
full_native_model_id
fireworks_ai/accounts/fireworks/routers/rune*
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.*