Nemotron 3 Ultra (NVIDIA) API

NVIDIA · serves nemotron-3-ultra-550b-a55b

Call it

OpenAI-compatible endpoint — set NVIDIA_API_KEY.

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI  # pip install openai

client = OpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key="...",  # NVIDIA_API_KEY
)
resp = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Use this data

Raw JSON for this page: nemotron-3-ultra-550b-a55b.json. Free to reuse under CC BY 4.0 with attribution to apipriceindex.com.