NVIDIA: Llama Nemotron Embed VL 1B V2

nvidia/llama-nemotron-embed-vl-1b-v2

Released Feb 25, 2026131,072 context

The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text combined. Documents can be retrieved given a user query in text form. The model supports images containing text, tables, charts, and infographics.

Recent activity on Llama Nemotron Embed VL 1B V2

Total usage per day on OpenRouter

Prompt

3.04B

Completion

0

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

NVIDIA: Llama Nemotron Embed VL 1B V2