Model dossier

NVIDIA: Llama Nemotron Embed VL 1B V2 (free)

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...

ProviderNVIDIA Start comparison

Context131,072

Max outputn/a

Pricing viewTVP price

Identity

NVIDIA: Llama Nemotron Embed VL 1B V2 (free)

Model ID: nvidia/llama-nemotron-embed-vl-1b-v2:free
Canonical slug: nvidia/llama-nemotron-embed-vl-1b-v2-20260224
Knowledge cutoff: n/a
Created: 2/25/2026

Capabilities

textimageembeddings

Modalities

text+image->embeddingsembeddingstextimage

Capacity

Context131,072

Max outputn/a

TokenizerOther