Skip to content
CostPerPrompt

Nemotron 3 Super API Pricing

NVIDIA · context window 262K · prices updated 2026-09-20

Input per 1M tokens
$0.08
Output per 1M tokens
$0.45
Cached input per 1M
No discounted cached tier on this model

Where Nemotron 3 Super sits on price

At $0.45 per million output tokens, Nemotron 3 Super is a budget tier model — 4.4× cheaper than the median output price of $2.00, which puts it cheaper than 82% and pricier than 18% of the models we track. It sits 4th cheapest of the 5 NVIDIA models we track. Output costs 5.6× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
2,222,222
One full context fill
$0.021
Cheaper than
82% of tracked models

What real workloads cost on Nemotron 3 Super

These three workloads are the ones teams actually run on a budget-priced model — a $0.45/1M 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 $246
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0001 $3.23
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0005 $140

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 raised Nemotron 3 Super's output price on Sep 15, 2026 (+12% per output token), from $0.085/$0.4 to $0.08/$0.45 per 1M in/out. That is one of 5 repricings in the 49 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%
Sep 15, 2026 $0.08 $0.45 +12%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Nemotron 3 Super vs Gemma 3 27B

The closest-priced alternative from another vendor is Gemma 3 27B (Google) — priced within a rounding error on output, with identical input pricing. 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 Gemma 3 27B pricing →

Cheaper alternatives

More NVIDIA models

Frequently asked questions

How much does the Nemotron 3 Super API cost?

Nemotron 3 Super costs $0.08 per million input tokens and $0.45 per million output tokens and no discounted cached-input tier. That works out to roughly 2,222,222 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 $246 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 $0.021 at $0.08 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 82% 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.