Nemotron-3.5-Rerank-8B-BF16

Name: Nemotron-3.5-Rerank-8B-BF16
Author: DeepInfra

rerank

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.

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Details

Model IDnvidia/Nemotron-3.5-Rerank-8B-BF16

ProviderDeepInfra

CreatorNVIDIA

Family—

License—

Statusactive

Typererank

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date—

Sourceofficial

Endpoints

rerankPOST

https://api.deepinfra.com/v1/openai/rerank

API

GET/v1/models/deepinfra/nvidia/Nemotron-3.5-Rerank-8B-BF16