Llama Nemotron Embed VL 1B V2 (free)

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

import os
from openai import OpenAI
client = OpenAI(base_url="https://deference.si/v1", api_key=os.environ["DEFERENCE_API_KEY"])
result = client.embeddings.create(model="nvidia/llama-nemotron-embed-vl-1b-v2:free", input="The quick brown fox")
print(len(result.data[0].embedding))

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://deference.si/v1", apiKey: process.env.DEFERENCE_API_KEY });
const result = await client.embeddings.create({ model: "nvidia/llama-nemotron-embed-vl-1b-v2:free", input: "The quick brown fox" });
console.log(result.data[0].embedding.length);