azure/gpt-35-turbo-instruct
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
GeekRadar / Il banco di confronto
CONFRONTA.
Modelli IAazure/gpt-35-turbo-instruct
Modello IA
- Modalità API
- Completamento testo*
Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Capacità
- Input massimo
- 4.097 tokens*
- Modalità API
- Completamento testo*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 6 campi
- input cost per token
- 1,65e-6*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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
- azure_text*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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
- 4.097*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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
- 4.097*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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
- completion*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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
- 2,2e-6*
Ambito e condizioni
- native_context
- provider
- azure_text*
- mode
- completion*
- full_native_model_id
- azure/gpt-35-turbo-instruct*
- 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.*
0 selezionati Confronta 0
* Dati provvisori