Nemotron-3.5-Rerank-8B-BF16 · deepinfra

Nemotron-3.5-Rerank-8B-BF16 is an 8B-parameter reranking model from NVIDIA that scores the relevance of documents to a query, for reordering the candidates retrieved by an embedding model. It supports long inputs up to 32k tokens and pairs naturally with the Nemotron-3.5-Embed models in multilingual RAG pipelines.

Modelo baseTodos los modelos de esta baseTodos los modelos del proveedoral proveedor

Todos los modelos de NVIDIA en todos los proveedores

Entrada, $/1M $0.05

Salida, $/1M —

Contexto 32 768

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —