GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

multimodalembedding

Modello IA

Modalità API: Embedding^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

multimodalembedding

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

Capacità

Input massimo: 2.048 tokens^*
Modalità API: Embedding^*

Modalità di input

text^*
image^*
video^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 14 campi

input cost per character

2,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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

0,0001^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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

8,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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 per second

0,0005^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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 per second above 15s interval

0,002^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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 per second above 8s interval

0,001^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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: multimodalembedding^*
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

2.048^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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

2.048^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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: multimodalembedding^*
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: multimodalembedding^*
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

768^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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/embeddings^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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^*
video^*

Ambito e condizioni

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: multimodalembedding^*
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