flagship · Jun 2026
Nemotron 3 Ultra 550B
NVIDIA’s flagship open model optimized for enterprise reasoning workloads.
By NVIDIA · Text · NVIDIA Open Model License
Model details
Specs & substance
Spec sheet
Developed byNVIDIA
Model familyNemotron
Categoryflagship
ModalityText
Context window128K tokens
ArchitectureMoE NVFP4
Version3 Ultra
LicenseNVIDIA Open Model License
Pricing$0.50 in$2.50 out · $0.10 cache
ReleasedJun 2026
Endpointparasail-nemotron-3-ultra-550b-nvfp4
NVIDIA’s flagship open model optimized for enterprise reasoning workloads.
Nemotron 3 Ultra 550B is part of the Nemotron family by NVIDIA, categorized as a flagship model. It supports a 128K tokens context window and is built on a MoE NVFP4 architecture.
Key strengths: reasoning, enterprise. Parasail serves Nemotron 3 Ultra 550B on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.
Integrate
Drop-in via the OpenAI SDK
Point any OpenAI-compatible chat client at Parasail and change the model name. That's it.
pythonparasail · Nemotron 3 Ultra 550B
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.parasail.io/v1"
)
response = client.chat.completions.create(
model="parasail-nemotron-3-ultra-550b-nvfp4",
messages=[
{"role": "user", "content": "Hello, what can you do?"}
],
stream=True,
stream_options={"include_usage": True},
top_p=1,
max_tokens=1000,
temperature=1
)
for chunk in response:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)bashparasail · Nemotron 3 Ultra 550B
curl https://api.parasail.io/v1/chat/completions \
-H "Authorization: Bearer $PARASAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "parasail-nemotron-3-ultra-550b-nvfp4",
"messages": [{"role": "user", "content": "Hello, what can you do?"}],
"stream": true,
"max_tokens": 1000
}'More models