GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

vertex_ai/meta/llama-3.1-8b-instruct-maas

Modello IA

Modalità API: Chat^*
Output massimo: 2.048 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

vertex_ai/meta/llama-3.1-8b-instruct-maas

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

Capacità

Input massimo: 128.000 tokens^*
Output massimo: 2.048 tokens^*
Modalità API: Chat^*
Input immagini: Sì^*
Messaggi di sistema: Sì^*
Scelta degli strumenti: Sì^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 11 campi

input cost per token

0,0^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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-llama_models^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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

128.000^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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

2.048^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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.^*

metadata

notes: VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost.^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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

chat^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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

0,0^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.1-8b-instruct-maas^*
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