Nemotron 3.5 Lightning API Pricing
Nvidia · Open Weights · CC-BY-NC-4.0 · released 2026-08. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.
- Input: $0.10 per 1M tokens
- Output: $0.25 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.05
- Context window: 1M
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 | $0.000275 | $0.000230 | $23 |
| Knowledge Q&A | 2,000 / 800 | $0.000400 | $0.000330 | $33 |
| Meeting Summary | 10,000 / 1,200 | $0.0013 | $0.0013 | $125 |
| Marketing Content | 2,500 / 1,800 | $0.000700 | $0.000675 | $68 |
| Coding Task | 3,000 / 2,000 | $0.000800 | $0.000725 | $73 |
| Invoice Processing | 1,500 / 600 | $0.000300 | $0.000277 | $28 |
| Call Summary | 2,000 / 700 | $0.000375 | $0.000365 | $37 |
| Agent Workflow | 6,000 / 3,000 | $0.0014 | $0.0011 | $114 |
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.