GeekRadar / Il banco di confronto

CONFRONTA.

Modelli IA

Unspecified

gradient_ai/deepseek-r1-distill-llama-70b

Modello IA

Modalità API: Chat^*
Output massimo: 8.000 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

gradient_ai/deepseek-r1-distill-llama-70b

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

Capacità

Input massimo: 32.768 tokens^*
Output massimo: 8.000 tokens^*
Modalità API: Chat^*
Scelta degli strumenti: No^*

Modalità di input

text^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 10 campi

input cost per token

9,9e-7^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

gradient_ai^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

32.768^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

8.000^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

8.000^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

9,9e-7^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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 endpoints

/v1/chat/completions^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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

No^*

Ambito e condizioni

native_context

provider: gradient_ai^*
mode: chat^*
full_native_model_id: gradient_ai/deepseek-r1-distill-llama-70b^*
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