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.
Modalities
Price
Free
Context
131K
Weekly Tokens
4.17B
Released
Feb 25, 2026
Create an API key from your OpenRouter dashboard and set it as an environment variable:
Use nvidia/llama-nemotron-embed-vl-1b-v2:free with the OpenRouter API:
OpenRouter supports image input embeddings for models that can generate embeddings from both text and images. Pass multimodal content using the content array format with text and image_url components. Learn more about image embeddings.
In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.
For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.
https://openrouter.ai/api/v1/embeddingsBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsnvidia/llama-nemotron-embed-vl-1b-v2:free| Name | Type | Default | Description |
|---|---|---|---|
temperature | float | 1 | This setting influences the variety in the model's responses. |
max_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |
seed | integer | — | If specified, the inferencing will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. |
top_p | float | 1 | This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. |