Skip to content

NVIDIA · Rerank

Llama Nemotron Rerank VL 1b V2

NVIDIA 🇺🇸RerankLlama familyOpen weights. One of its sources says the weights are publicly available.
From DeepInfra's listing:
The llama-nemotron-rerank-vl-1b-v2 is a 1.7B parameter multimodal reranking model designed to evaluate and order the relevance of document images and text against specific user queries. It excels at understanding complex visual content like charts, tables, and infographics.
Market median price
$0.01 /1M
Max context
10K
Listings
2
Providers
2

Evidence and sources

All rankings: #349 on OpenRouter this month #440 on OpenRouter this weekSources: DeepInfra data, Models.dev data, Hugging FacePrimary data from DeepInfra from Models.dev: weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 representative rerank models
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 5 maker's prices; 6 market median prices.

Input & output

from the model's type
Text
Text

Capabilities

Supported operations and provider-stated features

Vision

Listings

 DeepInfranvidia/llama-nemotron-rerank-vl-1b-v2Source: DeepInfra data10K$0.01—

1 listing without a price is hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Rerank

Also known as: nvidia/llama-nemotron-rerank-vl-1b-v2

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works