Provider pricing
NVIDIA Nemotron API pricing: every model, cheapest provider
4 NVIDIA Nemotron models are offered by 5 providers we track. The lowest listed rate is nvidia-nemotron-nano-9b-v2 at $0.04 input and $0.16 output per 1M tokens from DeepInfra.
Standard list prices in USD. Last price change Oct 17, 2026. How we collect and rank prices.
Open a model to compare every provider
NVIDIA Nemotron models and lowest prices
| Model | Providers | Cheapest provider | Input / 1M | Output / 1M | Max context |
|---|---|---|---|---|---|
| Nemotron Ultra | 3 | W&B Inference (CoreWeave) | $0.50 | $2.15 | 262K |
| Nemotron 3 Nano 30B A3B | 2 | DeepInfra | $0.05 | $0.20 | 262K |
| Nemotron 3.5 Super VL | 2 | Baseten | $0.20 | $0.50 | 1M |
| nvidia-nemotron-nano-9b-v2 | 2 | DeepInfra | $0.04 | $0.16 | 131K |
Only models listed by at least three providers are shown. Prices are per 1M tokens at the cheapest provider for each model.
Compare more
Other model developers
Alibaba Qwen, Anthropic Claude, DeepSeek, Google Gemini and Gemma, Meta Llama, MiniMax, Mistral AI, Moonshot AI Kimi, OpenAI, xAI Grok, Z.ai GLM