NVIDIA Nemotron 3 Ultra 550B A55B API

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")

response = client.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

curl https://api.fastinfra.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How much does the nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B API cost?

On FastInfra, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B costs $0.525/1M input, $2.31/1M output tokens. Billing is per token used, with no subscription.

Is nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B compatible with the OpenAI SDK?

Yes. FastInfra exposes nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.

How does routing work for nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B?

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B is available on 1 route(s): route-21. Requests use route-21 by default (lowest cost). FastInfra fails over automatically if a route is unavailable.