GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

vertex_ai/deepseek-ai/deepseek-v3.2-maas

Modello IA

Modalità API: Chat^*
Output massimo: 32.768 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

vertex_ai/deepseek-ai/deepseek-v3.2-maas

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

Capacità

Input massimo: 163.840 tokens^*
Output massimo: 32.768 tokens^*
Ragionamento: Sì^*
Uso di strumenti: Sì^*
Modalità API: Chat^*
Cache dei prompt: Sì^*
Scelta degli strumenti: Sì^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 17 campi

cache read input token cost

5,6e-8^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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.^*

deprecation date

2026-10-21^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

5,6e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

2,8e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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-deepseek_models^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

163.840^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

32.768^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

32.768^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

1,68e-6^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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

8,4e-7^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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 regions

global^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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 assistant prefill

No^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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 prompt caching

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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 reasoning

Sì^*

Ambito e condizioni

native_context

provider: vertex_ai-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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-deepseek_models^*
mode: chat^*
full_native_model_id: vertex_ai/deepseek-ai/deepseek-v3.2-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