Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
vertex_ai/deepseek-ai/deepseek-r1-0528-maas
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Input massimo
65.336 tokens*
Output massimo
8.192 tokens*
Ragionamento
Sì*
Uso di strumenti
Sì*
Modalità API
Chat*
Cache dei prompt
Sì*
Scelta degli strumenti
Sì*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 16 campi
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-r1-0528-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
1,35e-6*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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
6,75e-7*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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-r1-0528-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
65.336*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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
8.192*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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
8.192*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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-r1-0528-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
5,4e-6*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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
2,7e-6*Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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
us-central1*
Ambito e condizioni
native_context
provider
vertex_ai-deepseek_models*
mode
chat*
full_native_model_id
vertex_ai/deepseek-ai/deepseek-r1-0528-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-r1-0528-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-r1-0528-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-r1-0528-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-r1-0528-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-r1-0528-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.*