Model Maker · Amazon Bedrock
NVIDIA AI Model Pricing
Complete pricing datasheet and token cost estimator for 4 NVIDIA foundation models available on Amazon Bedrock. Normalized to USD per 1 Million Tokens ($/1M) with on-demand, prompt caching, and batch rates.
Compare Models →Model Makers:
Organization ProfileNVIDIA Corporation
About NVIDIA
Founded in 1993 and headquartered in Santa Clara, California, NVIDIA produces the accelerated computing platforms powering modern AI. Its AI software team trains the Nemotron family of open-weight models, engineered specifically to generate high-quality synthetic data, train reward models, and streamline model distillation pipelines.
HeadquartersSanta Clara, California, USA
Founded1993
OwnershipPublic (NASDAQ: NVDA)
Flagship LineageNemotron, NeMo
Model Ecosystem & LicensingOpen weights (NVIDIA Open Model License)
NVIDIA Token Cost Estimator
Calculate estimated monthly inference spend for NVIDIA foundation models.
Estimated Monthly Spend
$0.00
Prompt (Input):$0.00
Prompt Cache Read:$0.00
Completion (Output):$0.00
—
All NVIDIA Models (4)
| Model Name | Tier | Modality | Input $/1M | Output $/1M | Batch In $/1M | Batch Out $/1M | Cache Read $/1M | Regions |
|---|---|---|---|---|---|---|---|---|
| Lightweight | Text | $0.06 | $0.24 | $0.03 | $0.12 | — | 15 | |
| General | Text | $0.15 | $0.65 | $0.07 | $0.33 | — | 15 | |
| Lightweight | Text | $0.06 | $0.23 | $0.03 | $0.12 | — | 15 | |
| Lightweight | Multimodal | $0.20 | $0.60 | $0.10 | $0.30 | — | 15 |