Llama 3.2 NeMo Retriever 1B VLM Embed v1
Multimodal embedding model optimized for question-answering retrieval over image, text, or combined image-and-text documents.
Specs
- Context
- 8.2K
- Max output
- —
- Input price
- —
- Output price
- —
- Released
- 2025-05-20
Context
- Context window
- 8.2K
- Max input
- —
- Max output
- —
Pricing
- Not published
Modalities
- Input
- TextImage
- Output
- Embedding
API
- API types
Reasoning
- Not published
Info
- Status
- Active
- Released
- 2025-05-20
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
nvidiamodel = nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1
JSON
Standard format
{
"id": "llama-3.2-nemoretriever-1b-vlm-embed-v1",
"object": "model",
"created": 1747699200,
"owned_by": "nvidia",
"name": "Llama 3.2 NeMo Retriever 1B VLM Embed v1",
"api": {
"types": [
"embeddings"
]
},
"limits": {
"context": 8192,
"input": null,
"output": null
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"embedding"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "active",
"release_date": "2025-05-20",
"knowledge_cutoff": null,
"description": "Multimodal embedding model optimized for question-answering retrieval over image, text, or combined image-and-text documents.",
"docs": "https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_2-nemoretriever-1b-vlm-embed-v1",
"verified_at": "2026-10-11"
}
}Official sources
1