ModelInfo
English
All models

Llama Nemotron Rerank VL 1B v2

Multimodal cross-encoder reranker that scores how relevant a document page (image, text, or both) is to a text query.

NVIDIAllama-nemotron-rerank-vl-1b-v22026-03-13Report incorrect data

Specs

Context
—
Max output
—
Input price
—
Output price
—
Released
2026-03-13

Context

Not published

Pricing

Not published

Modalities

Input
TextImage
Output
Score

API

API types
rerank

Reasoning

Not published

Info

Status
Active
Released
2026-03-13
Knowledge cutoff
—

Features

Not published
Source · official docsVerified 2026-10-11

How to call

1 provider

nvidiamodel = nvidia/llama-nemotron-rerank-vl-1b-v2

rerank
POSThttps://ai.api.nvidia.com/v1/retrieval/nvidia/llama-nemotron-rerank-vl-1b-v2/reranking

JSON

Standard format
llama-nemotron-rerank-vl-1b-v2.json
{
  "id": "llama-nemotron-rerank-vl-1b-v2",
  "object": "model",
  "created": 1773360000,
  "owned_by": "nvidia",
  "name": "Llama Nemotron Rerank VL 1B v2",
  "api": {
    "types": [
      "rerank"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "score"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": null,
  "features": [],
  "info": {
    "status": "active",
    "release_date": "2026-03-13",
    "knowledge_cutoff": null,
    "description": "Multimodal cross-encoder reranker that scores how relevant a document page (image, text, or both) is to a text query.",
    "docs": "https://build.nvidia.com/nvidia/llama-nemotron-rerank-vl-1b-v2/modelcard",
    "verified_at": "2026-10-11"
  }
}

Official sources

3
llama-nemotron-rerank-vl-1b-v2 Model Card | NVIDIA NIMbuild.nvidia.com2026-10-11nvidia / llama-nemotron-rerank-vl-1b-v2 | NVIDIA NIM API Referencedocs.api.nvidia.com2026-10-11Reranking (nvidia/llama-nemotron-rerank-vl-1b-v2) | NVIDIA NIM API Referencedocs.api.nvidia.com2026-10-11