GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

azure/gpt-realtime

Modello IA

Modalità API: API in tempo reale^*
Output massimo: 4.096 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

azure/gpt-realtime

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

Capacità

Input massimo: 32.000 tokens^*
Output massimo: 4.096 tokens^*
Uso di strumenti: Sì^*
Modalità API: API in tempo reale^*
Input audio: Sì^*
Output audio: Sì^*
Chiamate parallele agli strumenti: Sì^*
Messaggi di sistema: Sì^*
Scelta degli strumenti: Sì^*

Modalità di input

text^*
image^*
audio^*

Modalità di output

text^*
audio^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 23 campi

cache creation input audio token cost

4,0e-6^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

cache read input audio token cost

4,0e-7^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

cache read input token cost

4,0e-7^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

2027-03-02^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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 audio token

3,2e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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 image token

5,0e-6^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

4,0e-6^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

32.000^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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 output tokens

4.096^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

4.096^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

realtime^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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 audio token

6,4e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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

1,6e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supported endpoints

/v1/realtime^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supported modalities

text^*
image^*
audio^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supported output modalities

text^*
audio^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports audio input

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports audio output

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports function calling

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports parallel function calling

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports system messages

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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.^*

supports tool choice

Sì^*

Ambito e condizioni

native_context

provider: azure^*
mode: realtime^*
full_native_model_id: azure/gpt-realtime^*
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