Models›NVIDIA
NVIDIA
NVIDIA's Nemotron family: open models tuned for enterprise agentic work on NVIDIA hardware.
Models
7
on Gizmo
Free
2
plan limits apply
Open weights
7
downloadable
Largest context
1.05M
tokens
Models · 7
Compare Fast and Cheap modes, see the percentage saved, or filter to models with a verified discount. Select any model for its full pricing and API options.
Fast mode prioritizes response speed. Cheap mode uses lower-cost capacity and may be a little slower. Compare the same model’s input and output rates below.
| Model | Fast mode Input / output per 1M tokens | Cheap mode Input / output per 1M tokens | Discount | Run model |
|---|---|---|---|---|
| Nemotron 3.5 Super VLNVIDIA · 1.05M context | $0.1575 / $0.525 | $0.0945 / $0.315 | 40% off | |
| Nemotron 3.5 LightningNVIDIA · 262K context | $0.0735 / $0.21 | $0.0263 / $0.126 | 40–64.3% off | |
| Nemotron 3.5 Lightning (free)NVIDIA · 1M context | $0 / $0 | Already free | — | |
| Nemotron 3 UltraNVIDIA · 262K context | $0.63 / $2.52 | $0.42 / $1.848 | 26.7–33.3% off | |
| Nemotron 3 Ultra (free)NVIDIA · 1M context | $0 / $0 | Already free | — | |
| Nemotron 3 SuperNVIDIA · 1.05M context | $0.0788 / $0.42 | No verified discount | — | |
| Nemotron 3 Nano 30B A3BNVIDIA · 262K context | $0.063 / $0.252 | No verified discount | — |
7 of 7 models · Prices include your 5% platform fee.
Discounts compare current uncached input and output rates. Different percentages mean savings depend on your token mix. Fast rates are routing ceilings; actual charges and capacity may vary. No discount is shown without a verified quote.