Nemotron 3 Super 120B A12B (Reasoning) API Pricing
NVIDIA · released 2026-03-11
Pricing
0.030¢ / 1K
0.090¢ / 1K
0.045¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.042¢ |
| RAG query | 4,000 in / 500 out | 0.165¢ |
| Long document summary | 50,000 in / 1,000 out | $0.0159 |
| Code review of a 2k-line file | 30,000 in / 2,000 out | $0.0108 |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $12.60 |
Cost = (input tokens ÷ 1,000,000 × $0.30) + (output tokens ÷ 1,000,000 × $0.90).
Benchmarks
#206 of 533
#98 of 197
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Qwen3.5 4B (Reasoning) | 13.1 | $0.06 |
| Nemotron 3.5 Lightning | 12.9 | $0.095 |
| gpt-oss-20b (low) | 10.0 | $0.103 |
| Granite 4.2 8B | 11.1 | $0.107 |
| GPT-5 nano (high) | 13.0 | $0.138 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| GPT-5 nano (high) | 13.0 | $0.138 |
| Nemotron 3.5 Lightning | 12.9 | $0.095 |
| GLM-4.5 (Reasoning) | 12.8 | — |
| Nemotron 3 Super 120B A12B (Reasoning) | 12.8 | $0.45 |
| GPT-4.1 | 12.7 | $3.50 |
| Kimi K2 | 12.7 | $1.002 |
| Qwen3 235B A22B 2507 (Reasoning) | 12.7 | $0.747 |
More from NVIDIA
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Nemotron 3 Ultra 550B A55B (Reasoning) | 22.9 | $1.05 |
| Nemotron 3.5 Lightning | 12.9 | $0.095 |
| Nemotron Cascade 2 30B A3B | 11.7 | — |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 10.3 | $0.42 |
| Llama Nemotron Super 49B v1.5 (Reasoning) | 9.0 | $0.40 |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning) | 8.9 | — |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 8.9 | $0.088 |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | 7.5 | — |
Count tokens & estimate cost for Nemotron 3 Super 120B A12B (Reasoning) See Nemotron 3 Super 120B A12B (Reasoning) on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Nemotron 3 Super 120B A12B (Reasoning)?
Nemotron 3 Super 120B A12B (Reasoning) is developed by NVIDIA, released 2026-03-11.
How much does Nemotron 3 Super 120B A12B (Reasoning) cost per million tokens?
Nemotron 3 Super 120B A12B (Reasoning) costs $0.30 per 1M input tokens and $0.90 per 1M output tokens ($0.45 blended), per Artificial Analysis's official pricing data.
How does Nemotron 3 Super 120B A12B (Reasoning) rank on benchmarks?
Nemotron 3 Super 120B A12B (Reasoning) scores 12.8 on the Artificial Analysis Intelligence Index, ranking #206 of 533 models we track.
Is there a cheaper model with similar intelligence to Nemotron 3 Super 120B A12B (Reasoning)?
Yes — Qwen3.5 4B (Reasoning) scores similar intelligence (13.1) at $0.06/1M blended, versus $0.45/1M for Nemotron 3 Super 120B A12B (Reasoning).
Where does this data come from?
Pricing and benchmark data for Nemotron 3 Super 120B A12B (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.