Nemotron 3 Super API Pricing
NVIDIA · context window 262K · prices updated 2026-09-09
Where Nemotron 3 Super sits on price
At $0.4 per million output tokens, Nemotron 3 Super is a budget tier model — 5.5× cheaper than the median output price of $2.20, which puts it cheaper than 85% and pricier than 15% of the models we track. It sits 4th cheapest of the 5 NVIDIA models we track. Output costs 4.7× input, the usual spread — trim both, starting with the answer length.
What real workloads cost on Nemotron 3 Super
These three workloads are the ones teams actually run on a budget-priced model — a $0.4/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. | $0 | $252 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0001 | $3.07 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0005 | $137 |
Model your exact traffic in the API cost calculator — it preloads Nemotron 3 Super with caching and batch options.
Nemotron 3 Super price history
NVIDIA last cut Nemotron 3 Super's output price on Aug 10, 2026 (-56% per output token), from $0.3/$0.9 to $0.085/$0.4 per 1M in/out. That is one of 4 repricings in the 38 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $0.085 | $0.4 | — |
| Aug 7, 2026 | $0.3 | $0.9 | +125% |
| Aug 8, 2026 | $0.085 | $0.4 | -56% |
| Aug 9, 2026 | $0.3 | $0.9 | +125% |
| Aug 10, 2026 | $0.085 | $0.4 | -56% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Nemotron 3 Super vs Qwen2.5 72B Instruct
The closest-priced alternative from another vendor is Qwen2.5 72B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.275 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen2.5 72B Instruct pricing →Cheaper alternatives
More NVIDIA models
Frequently asked questions
› How much does the Nemotron 3 Super API cost?
Nemotron 3 Super costs $0.085 per million input tokens and $0.4 per million output tokens and no discounted cached-input tier. That works out to roughly 2,500,000 output tokens per dollar.
› What does the high-volume classification workload cost on Nemotron 3 Super?
High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $252 per month on Nemotron 3 Super. Short output, huge volume: the input price dominates the bill.
› What does it cost to fill Nemotron 3 Super's 262K context window?
Sending 262K of input in a single request costs $0.0223 at $0.085 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Nemotron 3 Super worth the price?
Nemotron 3 Super is in the cheapest end of the market — cheaper than 85% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.