llama-nemotron-rerank-vl-1b-v2

deepinfra/nvidia/llama-nemotron-rerank-vl-1b-v2

NVIDIA cross-encoder reranker (about 1.7B parameters, December 2025) that scores how relevant a document page, given as an image, text or both, is to a text query; the second stage for visual-document RAG alongside llama-nemotron-embed-vl.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/rerank" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Idempotency-Key: $AUDIOLAB_REQUEST_ID" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/nvidia/llama-nemotron-rerank-vl-1b-v2",
  "query": "Voice agents",
  "documents": [
    "Build a realtime voice agent.",
    "A guide to gardening."
  ],
  "top_n": 1
}'

Input Price: $0.0085 / 1M tokens
Output Price: —
Input: Text
Output: Score

Capabilities

Explore what llama-nemotron-rerank-vl-1b-v2 supports, then use the API section for a request tailored to this model.

Model Information

Provider: DeepInfra
Product: Reranking
Release Date: Dec 18, 2025
Data Policy: Not specified
Region: US
Input: Text
Output: Score

Provider Documentation

Playground

Try llama-nemotron-rerank-vl-1b-v2 by DeepInfra. Requests use the selected workspace’s credits and API pricing.

llama-nemotron-rerank-vl-1b-v2

This model uses a dedicated input format. Explore its API example or open the supported playground.

View API reference

Providers

Compare available endpoints, pricing, and context limits for llama-nemotron-rerank-vl-1b-v2.

Provider	Context	Output	Input Price	Output Price	Endpoint
DeepInfra	Not specified	Score	$0.0085 / 1M tokens	—	`nvidia/llama-nemotron-rerank-vl-1b-v2`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max units	81920

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/rerank" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Idempotency-Key: $AUDIOLAB_REQUEST_ID" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/nvidia/llama-nemotron-rerank-vl-1b-v2",
  "query": "Voice agents",
  "documents": [
    "Build a realtime voice agent.",
    "A guide to gardening."
  ],
  "top_n": 1
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepinfra/nvidia/llama-nemotron-rerank-vl-1b-v2` — Required model identifier.
`query`	View Accepted Values
`documents`	View Accepted Values
`top_n`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max units	81920

Similar Models

Explore more reranking and compare their capabilities.

Model	Context	Input Price	Output Price
Qwen3-Reranker-0.6BDeepInfra	Not specified	$0.0085 / 1M tokens	—
Qwen3-Reranker-4BDeepInfra	Not specified	$0.0212 / 1M tokens	—
Qwen3-Reranker-8BDeepInfra	Not specified	$0.0425 / 1M tokens	—
Qwen3 RerankAlibaba Cloud Model Studio	Not specified	$0.085 / 1M tokens	—

View All Reranking