GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

azure/eu/gpt-5.4-pro

Modello IA

Modalità API: API Responses^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

azure/eu/gpt-5.4-pro

Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.

Capacità

Modalità API: API Responses^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 11 campi

deprecation date

2027-09-07^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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

3,3e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 above 272k tokens

6,6e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 above 272k tokens batches

3,3e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 batches

1,65e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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

responses^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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

0,000198^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 above 272k tokens

0,000297^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 above 272k tokens batches

0,0001485^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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 batches

9,9e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: responses^*
full_native_model_id: azure/eu/gpt-5.4-pro^*
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.^*

* Dati provvisori