GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

azure/gpt-4o-transcribe

Modello IA

Modalità API: Trascrizione audio^*
Output massimo: 2.000 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

azure/gpt-4o-transcribe

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

Capacità

Input massimo: 16.000 tokens^*
Output massimo: 2.000 tokens^*
Modalità API: Trascrizione audio^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 9 campi

deprecation date

2026-10-15^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

6,0e-6^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

2,5e-6^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

16.000^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

2.000^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

audio_transcription^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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

1,0e-5^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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/audio/transcriptions^*

Ambito e condizioni

native_context

provider: azure^*
mode: audio_transcription^*
full_native_model_id: azure/gpt-4o-transcribe^*
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