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.
- Input: $0.60 per 1M tokens
- Output: $3.60 per 1M tokens
- Batch API (input/output): $0.30 / $1.80
- Prompt-cache read: $0.20
- Context window: 512K
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 case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0027 | $0.0023 | $234 |
| Knowledge Q&A | 2,000 / 800 | $0.0041 | $0.0035 | $352 |
| Meeting Summary | 10,000 / 1,200 | $0.010 | $0.0051 | $506 |
| Marketing Content | 2,500 / 1,800 | $0.0080 | $0.0078 | $778 |
| Coding Task | 3,000 / 2,000 | $0.0090 | $0.0084 | $840 |
| Invoice Processing | 1,500 / 600 | $0.0031 | $0.0015 | $149 |
| Call Summary | 2,000 / 700 | $0.0037 | $0.0018 | $184 |
| Agent Workflow | 6,000 / 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.