Nemotron 3 Ultra Pricing
FlagshipNVIDIA · 512K tokens context
Nemotron 3 Ultra from NVIDIA costs $0.600 per 1 million input tokens and $3.60 per 1 million output tokens as of August 2026 (live OpenRouter data). The model supports a 512,288-token context window (approximately 384,216 words) with a 32K-token maximum output. A typical 1,000-token request costs $0.0006 in input charges; a 10,000-token request costs $0.0060.
| Input price | $0.600 / 1M tokens |
|---|---|
| Output price | $3.60 / 1M tokens |
| Output / input ratio | 6.0× |
| Context window | 512,288 tokens (~384,216 words) |
| Maximum output | 32,000 tokens |
| Cost per 1K tokens (input) | $0.0006 |
| Tier | Flagship |
| Last verified |
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
Input Price
$0.600
per 1 million tokens
Output Price
$3.60
per 1 million tokens
Context Window
512K tokens
max 32K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.0008 | $0.00144 |
| 10-page document (2,500 words) | 3,333 | $0.002 | $0.0036 |
| 1,000 lines of code | 5,000 | $0.003 | $0.0054 |
| 100K token document | 100,000 | $0.06 | $0.108 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Affordable at $0.60/1M input tokens
- ✓Large 512K-token context window
- ✓Frontier-class quality on complex tasks
Limitations
- –Quality and availability can vary by hosting provider
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate Nemotron 3 Ultra Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Nemotron 3 Ultra costs — and compare across all models.
Open Calculator →Nemotron 3 Ultra — FAQ
Related Models
Related Guides