GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

vertex_ai/gemini-3.8-flash-tts

Modello IA

Modalità API: Sintesi vocale^*
Output massimo: 16.384 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

vertex_ai/gemini-3.8-flash-tts

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

Capacità

Input massimo: 8.192 tokens^*
Output massimo: 16.384 tokens^*
Modalità API: Sintesi vocale^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 9 campi

input cost per token

5,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

vertex_ai^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

8.192^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

16.384^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

16.384^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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_speech^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

9,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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

9,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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/speech^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: audio_speech^*
full_native_model_id: vertex_ai/gemini-3.8-flash-tts^*
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