# Llama Nemotron Embed VL 1B v2

> NVIDIA Llama-Nemotron-Embed-VL-1B-v2 is a vision-language embedding model for multimodal question-answering and retrieval over text, images, or combined image-text documents. A transformer encoder fine-tuned from Llama 3.2 1B with SigLip2 400M, it uses a tiling-based VLM architecture (Eagle 2 + nemoretriever-parse) for high-resolution image and complex visual-document understanding. Served via NVIDIA NIM.

**ID**: `nvidia/llama-nemotron-embed-vl-1b-v2`  
**Creator**: nvidia  
**Category**: embedding  
**Context**: 8K tokens  
**Status**: Removed (since 2026-09-17) — this listing is no longer sold; requests that still use `nvidia/llama-nemotron-embed-vl-1b-v2` are routed to [`nvidia/nemotron-3-embed-1b`](https://anyrouter.dev/model/nvidia/nemotron-3-embed-1b).  
**Reason**: NVIDIA's hosted NIM API returns 404 for this catalog id. The model is downloadable self-host NIM only. The live NVIDIA embedding SKU is nvidia/nemotron-3-embed-1b.  
**Input**: $0  
**Output**: $0  
**Released**: 2026-06-01  
**Web page**: https://anyrouter.dev/model/nvidia/llama-nemotron-embed-vl-1b-v2

**Input modalities**: text, image  
**Output modalities**: embeddings  

**Tokenizer**: Llama

**Capabilities**: embedding, vision

**Supported parameters**: input, model, encoding_format, input_type

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/embeddings`

```bash
curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/llama-nemotron-embed-vl-1b-v2",
  "input": "The quick brown fox jumps over the lazy dog"
}'
```

Pass `input` as a string or an array of strings to embed a batch in one call.

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| nvidia | $0 | $0 |
| nvidia-byok | $0 | $0 |

## Source

- Upstream docs: https://build.nvidia.com/nvidia/llama-nemotron-embed-vl-1b-v2