What is Llama Nemotron Embed VL 1B V2 and what is it good for?

It is a multimodal (text + image) embedding model from NVIDIA. It turns visual or text documents into vectors so you can find the most relevant ones for a text query. For question-answering retrieval and semantic search.

What is the context window of Llama Nemotron Embed VL 1B V2?

The model supports up to 131K tokens of input per request.

How do I access Llama Nemotron Embed VL 1B V2 from inside Iran?

Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card required.

Is Llama Nemotron Embed VL 1B V2 compatible with OpenAI embeddings code?

Yes. Hormouz exposes an OpenAI-compatible embeddings API. Point the base URL at Hormouz and swap in your Hormouz key.

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

NVIDIA's Llama Nemotron Embed VL 1B V2 is a multimodal (text + image) embedding model for question-answering retrieval over visual documents, with a 131K-token context. Free, reachable from inside Iran through Hormouz.

Context window:: 131,072 tokens
Pricing:: Free
Type:: embedding

Embeddings
Long context

Llama Nemotron Embed VL 1B V2 is a multimodal embedding model from NVIDIA, optimized for question-answering retrieval. It can turn a 'document'. An image, text, or image and text combined. Into an embedding vector, then retrieve the most relevant documents given a text query. It works well on images that contain text, tables, charts and infographics, making it a good fit for vision RAG pipelines.

The model handles up to 131K tokens of input per request. Through Hormouz it is served behind an OpenAI-compatible embeddings API. Point your base URL at Hormouz and drop in a Hormouz key. This is the free tier, well suited to testing, prototyping and building semantic search over visual documents.

Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

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...

Quickstart

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/llama-nemotron-embed-vl-1b-v2:free","input":"The quick brown fox"}'

Specs

Vendor	NVIDIA
Type	Embedding
Context window	131,072 tokens
Pricing	Free
API	embeddings

Code example

cURL

curl https://api.hormouz.net/v1/embeddings \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/llama-nemotron-embed-vl-1b-v2:free","input":"The quick brown fox"}'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
resp = client.embeddings.create(model="nvidia/llama-nemotron-embed-vl-1b-v2:free", input="The quick brown fox")
print(resp.data[0].embedding)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const resp = await client.embeddings.create({
  model: "nvidia/llama-nemotron-embed-vl-1b-v2:free",
  input: "The quick brown fox",
});
console.log(resp.data[0].embedding);

Buy the NVIDIA: Llama Nemotron Embed VL 1B V2 (free) API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches NVIDIA: Llama Nemotron Embed VL 1B V2 (free) and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

What is Llama Nemotron Embed VL 1B V2 and what is it good for?: It is a multimodal (text + image) embedding model from NVIDIA. It turns visual or text documents into vectors so you can find the most relevant ones for a text query. For question-answering retrieval and semantic search.
How much does Llama Nemotron Embed VL 1B V2 cost?: This is the free tier. It suits testing, prototyping and building semantic search over visual documents, and may be rate-limited.
What is the context window of Llama Nemotron Embed VL 1B V2?: The model supports up to 131K tokens of input per request.
How do I access Llama Nemotron Embed VL 1B V2 from inside Iran?: Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card required.
Is Llama Nemotron Embed VL 1B V2 compatible with OpenAI embeddings code?: Yes. Hormouz exposes an OpenAI-compatible embeddings API. Point the base URL at Hormouz and swap in your Hormouz key.

Updated 2026-10-13