Nemotron 3 Ultra
NVIDIA
A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
- Language
- Reasoning
- Tool use
- Implicit caching
- Context
- 1M
- Max output
- 65K
- Input / 1M
- $0.600
- Output / 1M
- $2.40
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass nvidia/nemotron-3-ultra-550b-a55b as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$0.600
Output
Per 1M completion tokens
$2.40
Cache read
Per 1M cached prompt tokens
$0.120
A 1M-token prompt with 250K tokens of output costs about $1.20.
Rates for this model vary by upstream provider; Maxynetic Systems routes to the cheapest healthy one by default.