GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

deepseek/deepseek-coder

Modello IA

Modalità API: Chat^*
Output massimo: 4.096 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

deepseek/deepseek-coder

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

Capacità

Input massimo: 128.000 tokens^*
Output massimo: 4.096 tokens^*
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

1,4e-8^*

Ambito e condizioni

native_context

provider: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-coder^*
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: deepseek^*
mode: chat^*
full_native_model_id: deepseek/deepseek-coder^*
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 cache hit

1,4e-8^*

Ambito e condizioni

native_context

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

deepseek^*

Ambito e condizioni

native_context

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

4.096^*

Ambito e condizioni

native_context

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

4.096^*

Ambito e condizioni

native_context

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

Sì^*

Ambito e condizioni

native_context

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