Nemotron 3 Ultra API Pricing

Nvidia · Open Weights · CC-BY-NC-4.0 · released 2026-06. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.

Cost per request by business use case

List price vs optimized (prompt caching on the cached input share, batch API for async workloads — only where the provider publishes those rates).

Use caseTokens (in/out)Cost/req (list)Cost/req (optimized)Monthly @100K req
Support Ticket1,500 / 500$0.0027$0.0023$234
Knowledge Q&A2,000 / 800$0.0041$0.0035$352
Meeting Summary10,000 / 1,200$0.010$0.0051$506
Marketing Content2,500 / 1,800$0.0080$0.0078$778
Coding Task3,000 / 2,000$0.0090$0.0084$840
Invoice Processing1,500 / 600$0.0031$0.0015$149
Call Summary2,000 / 700$0.0037$0.0018$184
Agent Workflow6,000 / 3,000$0.014$0.013$1.3K

These are list prices — real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.