Nemotron API pricing
NVIDIA's open-weight Nemotron models, including hybrid mixture-of-experts designs with small active parameter counts.
Nemotron 3 Super
Repriced 13 OctWhat it costs in practice
Nemotron 3 Super at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $0.25 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $0.20 |
| A month of a coding agent400 tasks, 85% of input cached | $66.95 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Work out AI agent cost on Nemotron 3 Super
Details
nemotron-3-super-120b-a12bCheapest host listed on OpenRouter (DeepInfra).
Checked 13 Oct 2026 against OpenRouter listing .
Estimate your monthly cost
List prices, no batch discount
| Model | Input / output per 1M | Per month |
|---|---|---|
| Nemotron 3 Super | $0.085 / $0.40 | $1.65 |
| Nemotron 3.5 Lightning | $0.025 / $0.12 | $0.49 |
Type amounts like 500K, 25M or 2B.
Price Nemotron 3 Super in: Token cost calculator · AI agent cost · Token counter
Cheapest in its class
No current general-purpose workhorse model from another family costs meaningfully less than Nemotron 3 Super.
Compare Nemotron 3 Super with
Side by side: prices, cached and batch rates, and the cost of the same workload.
Other Nemotron models
Prices are the cheapest listed on OpenRouter; hosts vary.
| Model | Input / 1M | Output / 1M | Cached input | Context | Released |
|---|---|---|---|---|---|
Open weights · via OpenRouter · Source: OpenRouter listing (opens in a new tab) |
$0.025 | $0.12 | — | 1M | 11 Aug 2026 |
Nemotron 3.5 Lightning details
Nemotron 3.5 Lightning
▼ 40% on 13 Oct$0.025 / $0.12 per 1M tokens1M context
Cheapest host listed on OpenRouter (Darkbloom). DeepInfra charges $0.06 / $0.16.
Checked 13 Oct 2026 against OpenRouter listing .
Compare Nemotron 3 Super
No ready-made comparisons for this family yet.
Price history
All changes
The cheapest OpenRouter hosts repriced 6 open-weight models, mostly downwards, including gpt-oss-120b (now $0.03 / $0.15) and Qwen3.8 27B (now $0.039 / $1.25). Source
Every dated price: price records · CSV. Cite as: AI Token Price, Nemotron pricing, https://aitokenprice.com/pricing/nemotron#price-history
NVIDIA pricing rules
- Nemotron models are open weights; prices shown are from third-party hosts.
Questions
How much does Nemotron 3 Super cost?
As of 13 Oct 2026, Nemotron 3 Super costs $0.085 per million input tokens and $0.40 per million output tokens. Prices checked 13 Oct 2026.
What is the cheapest Nemotron model?
Nemotron 3.5 Lightning, at $0.025 / $0.12 per million input / output tokens.
What is Nemotron 3 Super's context window?
256K tokens.