InferenceHunt / Explore
NVIDIA AI model pricing
Compare live API pricing for NVIDIA models across tracked inference venues. Prices show the lowest currently observed input and output rate for each model.
2 models with current data
Which NVIDIA model has the lowest API price?
Nemotron 3 Ultra has the lowest observed input price on this page at $0 per 1M tokens. Nemotron 3 Ultra has the lowest observed output price at $0 per 1M tokens. Prices reflect the latest successful collection.
| Model | Input / 1M | Output / 1M | Context | Venues |
|---|---|---|---|---|
 Nemotron 3 UltraNVIDIA | $0 | $0 | 1M | OpenRouterOpenCode ZenSurplus Intelligence |
| Nemotron 3.5 LightningNVIDIA | $0 | $0 | 1M | OpenRouterOpenCode Zen |