Model pricing

NVIDIA: Nemotron 3 Ultra API Pricing

NVIDIA · 1M context

toolsstructured-outputreasoninglong-context
Provider prices

Pricing across providers

Prices are shown per 1M tokens with cache pricing, source links, observation dates, and confidence labels.

ProviderInput / OutputCachedSource typeSourceObservedConfidence
DeepInfradeepinfra · endpoint$0.50 / $2.20$0.10OpenRouter endpointSource2026-07-17high
OpenRouteropenrouter · aggregator$0.60 / $3.60$0.20OpenRouter aggregateSource2026-07-17high
Together AItogether · aggregator$0.60 / $3.60$0.20OpenRouter endpointSource2026-07-17high
Venicevenice · endpoint$0.63 / $3.13$0.19OpenRouter endpointSource2026-07-17high
Same organization

Related models

Other tracked models from NVIDIA.