GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

gemini-live-2.5-flash-native-audio

Modello IA

Modalità API: API in tempo reale^*
Output massimo: 65.536 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

gemini-live-2.5-flash-native-audio

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

Capacità

Input massimo: 131.072 tokens^*
Output massimo: 65.536 tokens^*
Uso di strumenti: Sì^*
Output strutturato: No^*
Modalità API: API in tempo reale^*
Input immagini: Sì^*
Input PDF: No^*
Input audio: Sì^*
Output audio: Sì^*
Chiamate parallele agli strumenti: Sì^*
Cache dei prompt: No^*
Messaggi di sistema: Sì^*
Scelta degli strumenti: Sì^*
Ricerca sul web: Sì^*

Modalità di input

text^*
image^*
audio^*
video^*

Modalità di output

text^*
audio^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 29 campi

deprecation date

2026-12-13^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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.^*

gemini native audio

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

3,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

3,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

5,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 video token

3,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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-language-models^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

131.072^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

65.536^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

65.536^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

1,2e-5^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

2,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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.^*

search context cost per query

search_context_size_low: 0,035^*
search_context_size_medium: 0,035^*
search_context_size_high: 0,035^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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

/vertex_ai/live^*
/v1/realtime^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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^*
video^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 pdf input

No^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 prompt caching

No^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 response schema

No^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 url context

No^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 vision

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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 web search

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-language-models^*
mode: realtime^*
full_native_model_id: gemini-live-2.5-flash-native-audio^*
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