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 / $2.50$0.15OpenRouter endpointSource2026-06-08high
OpenRouteropenrouter · aggregator$0.50 / $2.50$0.15OpenRouter aggregateSource2026-06-08high
Same organization

Related models

Other tracked models from NVIDIA.

NVIDIA: Nemotron 3.5 Content Safety (free)↗128K contextOpenRouter $0 inputNVIDIA: Nemotron 3 Ultra (free)↗1M contextOpenRouter $0 inputNVIDIA: Nemotron 3 Nano Omni (free)↗256K contextOpenRouter $0 inputNVIDIA: Nemotron 3 Super (free)↗1M contextOpenRouter $0 inputNVIDIA: Nemotron 3 Super↗1M contextOpenRouter $0.090 inputNVIDIA: Nemotron 3 Nano 30B A3B (free)↗256K contextOpenRouter $0 input