Llama-Nemotron-Embed-1B-v2

curl

curl https://integrate.api.nvidia.com/v1/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/llama-nemotron-embed-1b-v2",
    "messages": [{"role": "user", "content": "你好，介绍一下你自己"}]
  }'

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://integrate.api.nvidia.com/v1/v1")
response = client.chat.completions.create(
    model="nvidia/llama-nemotron-embed-1b-v2",
    messages=[{"role": "user", "content": "你好，介绍一下你自己"}],
)
print(response.choices[0].message.content)