GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

wandb/deepseek-ai/DeepSeek-V4-Flash

Modello IA

Modalità API: Chat^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

wandb/deepseek-ai/DeepSeek-V4-Flash

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

Capacità

Input massimo: 1.049.000 tokens^*
Ragionamento: Sì^*
Modalità API: Chat^*
Input immagini: No^*
Cache dei prompt: Sì^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 11 campi

cache read input token cost

7,0e-8^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

2026-10-05^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

1,4e-7^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

wandb^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

1.049.000^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

1.048.576^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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

2,8e-7^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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 vision

No^*

Ambito e condizioni

native_context

provider: wandb^*
mode: chat^*
full_native_model_id: wandb/deepseek-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