Nemotron API pricing
NVIDIA's open-weight Nemotron models, including hybrid mixture-of-experts designs with small active parameter counts.
Nemotron 3 Super
What it costs in practice
Nemotron 3 Super at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $0.26 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $0.20 |
| A month of a coding agent400 tasks, 85% of input cached | $63.60 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Model your own workload
Details
nemotron-3-super-120b-a12bCheapest host listed on OpenRouter. Prices vary by host.
Checked 27 Sep 2026 against OpenRouter listing .
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 |
$0.080 | $0.20 | — | 1M | 11 Aug 2026 |
Nemotron 3.5 Lightning details
Nemotron 3.5 Lightning
$0.080 / $0.20 per 1M tokens1M context
Cheapest host listed on OpenRouter. Prices vary by host.
Checked 27 Sep 2026 against OpenRouter listing .
Compare Nemotron 3 Super
No ready-made comparisons for this family yet.
Price history
All changesNo price changes recorded since we began tracking in June 2026.
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 27 Sep 2026, Nemotron 3 Super costs $0.08 per million input tokens and $0.45 per million output tokens. Prices checked 27 Sep 2026.
What is the cheapest Nemotron model?
Nemotron 3.5 Lightning, at $0.08 / $0.20 per million input / output tokens.
What is Nemotron 3 Super's context window?
256K tokens.