Using Nemotron 3 Ultra on DeepInfra
Implementation guide · Nemotron 3 · NVIDIA AI
DeepInfra exposes Nemotron 3 Ultra through model ID nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-17. Next refresh: weekly.
Quick Start
- 1
- 2Use the DeepInfra SDK or REST API to call
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B— see the documentation for request format. - 3
Code Examples
pip install openaiDEEPINFRA_API_KEYnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra uses "organization/model-name" format, e.g. "meta-llama/Meta-Llama-3-8B-Instruct" or "mistralai/Mistral-7B-Instruct-v0.3". See the DeepInfra model catalog for exact IDs.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["DEEPINFRA_API_KEY"],
base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
model="nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on DeepInfra
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.50 |
| Output tokens | $2.20 |
Capabilities
About Nemotron 3 Ultra
NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). Highest Artificial Analysis Intelligence Index for any US open model (score: 48). 300+ tokens/second. 1M-token context. Announced at Computex 2026. Pricing: ~$0.60/$2.60 per 1M tokens (provider median); free tier on some providers.