Nemotron Embed VL 1B v2 API: Pricing and Specs

Nemotron Embed VL 1B v2 API

Nemotron Embed VL 1B v2 is an embedding model by NVIDIA, available on the Venice API as text-embedding-nemotron-embed-vl-1b-v2. It runs privately, with zero data retention.

Nemotron Embed VL 1B v2 API pricing

Model ID	Variant	Privacy	Price
`text-embedding-nemotron-embed-vl-1b-v2`	Standard	Private	$0.0125 / 1M tok

Nemotron Embed VL 1B v2 specifications

Spec	Value
Provider	NVIDIA
Released	Apr 17, 2026
Privacy	Private
Status	Stable
Open weights	Yes
Dimensions	2,048
Max input	32K tokens

How to use the Nemotron Embed VL 1B v2 API

Send requests to POST https://api.venice.ai/api/v1/embeddings with "model": "text-embedding-nemotron-embed-vl-1b-v2" and your API key.

curl https://api.venice.ai/api/v1/embeddings \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-nemotron-embed-vl-1b-v2",
    "input": "Private AI for everyone."
  }'

Related models

BGE-EN-ICL API: $0.0125 / 1M tok
Multilingual E5 Large Instruct API: $0.0125 / 1M tok
Qwen3 Embedding 0.6B API: $0.0125 / 1M tok
Qwen3 Embedding 8B API: $0.0125 / 1M tok

Explore

By modality

Nemotron Embed VL 1B v2 API

Nemotron Embed VL 1B v2 API pricing

Nemotron Embed VL 1B v2 specifications

How to use the Nemotron Embed VL 1B v2 API

Related models