NVIDIA API Models & Pricing
19 NVIDIA models tracked with official API pricing and benchmark scores, refreshed daily.
| Model | Released | In $/1M | Out $/1M | Blended | Intelligence | Coding | Tok/s |
|---|---|---|---|---|---|---|---|
| Nemotron 3 Ultra 550B A55B (Reasoning) | 2026-06-04 | 0.60 | 2.75 | 1.14 | 38.3 | 49.3 | 169 |
| Nemotron 3 Super 120B A12B (Reasoning) | 2026-03-11 | 0.20 | 0.80 | 0.35 | 25.7 | 37.7 | 143 |
| Nemotron 3.5 LightningNEW | 2026-08-11 | 0.07 | 0.22 | 0.11 | 23.6 | 26.8 | 308 |
| Nemotron Cascade 2 30B A3B | 2026-03-19 | 0.00 | 0.00 | 0.00 | 17.8 | 25.3 | 0 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 2026-04-29 | 0.07 | 0.30 | 0.13 | 15.0 | 13.8 | 330 |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 2025-12-15 | 0.05 | 0.20 | 0.09 | 14.5 | 14.4 | 298 |
| Llama Nemotron Super 49B v1.5 (Reasoning) | 2025-07-25 | 0.40 | 0.40 | 0.40 | 12.4 | — | 122 |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning) | 2025-03-18 | 0.00 | 0.00 | 0.00 | 12.2 | — | 0 |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | 2025-04-07 | 0.60 | 1.80 | 0.90 | 8.9 | — | 53 |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | 2025-10-28 | 0.20 | 0.60 | 0.30 | 8.8 | — | 83 |
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | 2025-08-18 | 0.04 | 0.16 | 0.07 | 8.7 | — | 228 |
| NVIDIA Nemotron 3 Nano 4B | 2026-03-16 | 0.00 | 0.00 | 0.00 | 8.6 | 8.0 | 0 |
| Llama Nemotron Super 49B v1.5 (Non-reasoning) | 2025-07-25 | 0.40 | 0.40 | 0.40 | 8.5 | — | 118 |
| Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | 2025-05-20 | 0.00 | 0.00 | 0.00 | 8.4 | — | 0 |
| Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | 2025-03-18 | 0.00 | 0.00 | 0.00 | 8.3 | — | 0 |
| Llama 3.1 Nemotron Instruct 70B | 2024-10-15 | 1.20 | 1.20 | 1.20 | 7.4 | — | 95 |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | 2025-12-15 | 0.05 | 0.20 | 0.09 | 7.2 | — | 257 |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | 2025-08-18 | 0.05 | 0.20 | 0.09 | 7.2 | — | 174 |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 2025-10-28 | 0.20 | 0.60 | 0.30 | 4.2 | — | 164 |
Prices are NVIDIA's official list prices in USD per 1M tokens. Multi-gateway price comparison (OpenRouter, Together, etc.) is coming soon. See the full model directory to compare across all providers.