Nemotron 3 Super Pricing
FastNVIDIA · 1M tokens context
Nemotron 3 Super from NVIDIA costs $0.085 per 1 million input tokens and $0.400 per 1 million output tokens as of July 2026 (live OpenRouter data). The model supports a 1,000,000-token context window (approximately 750,000 words) with a 16K-token maximum output. A typical 1,000-token request costs $0.0001 in input charges; a 10,000-token request costs $0.0008.
| Input price | $0.085 / 1M tokens |
|---|---|
| Output price | $0.400 / 1M tokens |
| Output / input ratio | 4.7× |
| Context window | 1,000,000 tokens (~750,000 words) |
| Maximum output | 16,384 tokens |
| Cost per 1K tokens (input) | $0.0001 |
| Tier | Fast |
| Last verified |
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.
Input Price
$0.085
per 1 million tokens
Output Price
$0.400
per 1 million tokens
Context Window
1M tokens
max 16K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.000113 | $0.00016 |
| 10-page document (2,500 words) | 3,333 | $0.000283 | $0.0004 |
| 1,000 lines of code | 5,000 | $0.000425 | $0.0006 |
| 100K token document | 100,000 | $0.0085 | $0.012 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Extremely cheap at $0.085/1M input tokens
- ✓Massive 1M-token context window
- ✓Low latency for high-throughput workloads
Limitations
- –Less capable than flagship models on complex reasoning
- –Quality and availability can vary by hosting provider
Best Use Cases
Calculate Nemotron 3 Super Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact Nemotron 3 Super costs — and compare across all models.
Open Calculator →Nemotron 3 Super — FAQ
Related Models
Related Guides