GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

azure_ai/deepseek-v4-flash

Modello IA

Modalità API: Chat^*
Output massimo: 384.000 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

azure_ai/deepseek-v4-flash

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

Capacità

Input massimo: 1.000.000 tokens^*
Output massimo: 384.000 tokens^*
Ragionamento: Sì^*
Uso di strumenti: Sì^*
Modalità API: Chat^*
Cache dei prompt: Sì^*
Scelta degli strumenti: Sì^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 13 campi

cache read input token cost

2,8e-8^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

2028-02-20^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

1,9e-7^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

azure_ai^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

1.000.000^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

384.000^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

384.000^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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

5,1e-7^*

Ambito e condizioni

native_context

provider: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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: azure_ai^*
mode: chat^*
full_native_model_id: azure_ai/deepseek-v4-flash^*
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