Nemotron Embed VL 1B v2
Nemotron Embed VL 1B v2 is NVIDIA’s open-weight embedding model from its Llama Nemotron family, trained for retrieval over visually rich documents such as reports, slides and scanned pages. Through the API it embeds text into 2,048-dimensional vectors.
Per 1M tokens
$0.0125
Dimensions
2,048
Max input
32K
tokens per item
1M docs × 500 tokens
$6.25
to embed once
Pricing
USD per 1M input tokensInput
$0.0125
1M documents
$6.25
500 tokens each, embedded once
Specs
- Model ID
text-embedding-nemotron-embed-vl-1b-v2- Endpoint
POST /api/v1/embeddings- Dimensions
- 2,048
- Max input
- 32,768 tokens per item
- Added
- Apr 17, 2026
- Weights
- Open
POST
/api/v1/embeddingscurl 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."
}'Privacy
Tier 1
Anonymized
Included
Tier 2 · this model
Private
Zero data retention, enforced by contract. Prompts and outputs aren’t stored.
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available