vertex_ai/gemma-4-26b-a4b-it

Modello IA

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

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

Specifiche · 5 campi

cache read input token cost

1,5e-8^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: chat^*
full_native_model_id: vertex_ai/gemma-4-26b-a4b-it^*
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

1,5e-7^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: chat^*
full_native_model_id: vertex_ai/gemma-4-26b-a4b-it^*
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^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: chat^*
full_native_model_id: vertex_ai/gemma-4-26b-a4b-it^*
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^*
mode: chat^*
full_native_model_id: vertex_ai/gemma-4-26b-a4b-it^*
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

6,0e-7^*

Ambito e condizioni

native_context

provider: vertex_ai^*
mode: chat^*
full_native_model_id: vertex_ai/gemma-4-26b-a4b-it^*
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