NVIDIA
Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
At a glance
- Input / 1M
- $0.50
- Output / 1M
- $2.20
- Context
- 262K
- Max output
- 16K
- Intelligence
- 22.9
- Released
- Jun 2026
Pricing
Nemotron 3 Ultra API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.50 |
|---|---|
| Output tokensPer 1M tokens | $2.20 |
| Cached input (read)Per 1M tokens | $0.10 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$2.10
per 1,000 requests
Coding task
30K in, 4K out
$23.80
per 1,000 requests
Long document summary
150K in, 2K out
$79.40
per 1,000 requests
Benchmarks
Nemotron 3 Ultra benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
22.9
Coding index
49.3
Agentic index
20.1
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 262K tokens
- Max output
- 16K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- High, Medium
- Release date
- June 4, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Nemotron 3 Ultra vs other models
See how Nemotron 3 Ultra stacks up head to head on price, benchmarks, and features.
Nemotron 3 Ultra vs DeepSeek V4 Flash 0423
NVIDIA vs DeepSeek
See comparison
Nemotron 3 Ultra vs Gemini 3 Flash Preview
NVIDIA vs Google
See comparisonNemotron 3 Ultra vs Grok 4.3
NVIDIA vs xAI
See comparison
Nemotron 3 Ultra vs GPT-5.4 Mini
NVIDIA vs OpenAI
See comparisonNemotron 3 Ultra vs Kimi K2.5
NVIDIA vs Moonshot AI
See comparison
Nemotron 3 Ultra vs Qwen3.5-27B
NVIDIA vs Qwen
See comparisonAlternatives
Nemotron 3 Ultra alternatives
Similar models worth considering, and where each one has the edge.
Gemini 3 Flash Preview
xAI
Grok 4.3
DeepSeek
DeepSeek V4 Flash 0423
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Nemotron 3 Ultra cost?
Nemotron 3 Ultra costs $0.50 per 1M input tokens and $2.20 per 1M output tokens through the API. A typical chat message costs about $2.10 per 1,000 messages.
What is the context window of Nemotron 3 Ultra?
Nemotron 3 Ultra accepts up to 262K tokens of input and can write up to 16K tokens in a single response.
What is the best alternative to Nemotron 3 Ultra?
Gemini 3 Flash Preview from Google is a strong alternative. It offers: higher intelligence score, larger 1.05m context, accepts image and file and audio and video.
Can I use Nemotron 3 Ultra alongside other models?
Yes. Shortcut Chat sends one prompt to Nemotron 3 Ultra and any other models you pick at the same time, so you can compare answers side by side.
Try Nemotron 3 Ultra next to every other model.
Use Nemotron 3 Ultra alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.