GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

vertex_ai/meta/llama-3.3-70b-instruct-maas

Modello IA

Modalità API: Chat^*
Output massimo: 8.192 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

vertex_ai/meta/llama-3.3-70b-instruct-maas

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

Capacità

Input massimo: 128.000 tokens^*
Output massimo: 8.192 tokens^*
Uso di strumenti: Sì^*
Modalità API: Chat^*
Scelta degli strumenti: Sì^*

Modalità di input

text^*

Modalità di output

text^*
code^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 14 campi

deprecation date

2026-10-21^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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.^*

input cost per token

7,2e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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.^*

input cost per token batches

3,6e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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-3.3-70b-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-3.3-70b-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

8.192^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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

8.192^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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-3.3-70b-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

7,2e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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 batches

3,6e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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.^*

supported modalities

text^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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.^*

supported output modalities

text^*
code^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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 function calling

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-llama_models^*
mode: chat^*
full_native_model_id: vertex_ai/meta/llama-3.3-70b-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-3.3-70b-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