GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

google

Gemini Embedding 2

Modello IA Uscita Apr 22, 2026

Modalità API: Embedding^*
Finestra di contesto: 8.192 tokens
Output massimo: 3.072 tokens
Pesi aperti: No

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

Gemini Embedding 2

Pesi chiusi. Non sono pubblicati un impiego locale supportato o requisiti GPU.

Costo API

USD / mese

Token di input / meseToken di output / mese

Stima per token di testo standard. Esclude imposte, cache, sconti batch e costi aggiuntivi per ragionamento e modalità multimediali. Limiti e disponibilità possono variare per provider.

Gemini Embedding 2

Offerta del provider

Gemini Embedding 2 / Fasce di prezzo 1

Provider / condizioni	Tariffa	Valuta	Importo / unità
GoogleGemini Embedding 2Standard	Token audio	USD	6.5 / 1M tokens
	Token immagine	USD	0.45 / 1M tokens
	Input	USD	0.2 / 1M tokens
	Token video	USD	12 / 1M tokens

Capacità

Finestra di contesto: 8.192 tokens
Input massimo: 8.192 tokens^*
Output massimo: 3.072 tokens
Ragionamento: No
Uso di strumenti: No
Pesi aperti: No
Dati di addestramento fino a: 2025-11
Modalità API: Embedding^*

Modalità di input

text
image
audio
video
pdf

Modalità di output

text

Configurazione di sistema

Specifiche dettagliate

Specifiche · 16 campi

input cost per audio token

6,5e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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 batches

3,25e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

4,5e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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 batches

2,25e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

2,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

1,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

1,2e-5^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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 batches

6,0e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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-embedding-models^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

8.192^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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

embedding^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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 vector size

3.072^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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 multimodal

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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.^*

uses embed content

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
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