Nemotron 3 Super

Mar 2026
Nemotron 3 Super
Compare in
—per task?
$0.085 / $0.40per 1M in / out?
—output speed?
1Mcontext

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✓ 80 GB GPU · compressed
Licencenvidia-nemotron-open-model-licensecommercial use with conditions

Benchmarks

all categories
No benchmark results yet.

FAQ

How much does Nemotron 3 Super cost?›

$0.085 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: DeepInfra).

Is Nemotron 3 Super free to use?›

There is no free API; the cheapest paid price is $0.085 per 1M input tokens. The weights are open, so you can run it yourself.

How can I use Nemotron 3 Super?›

Through the API of Crusoe, DeepInfra, DekaLLM.

What is the context window of Nemotron 3 Super?›

1M tokens, with up to 236K output tokens.

When was Nemotron 3 Super released? Is there a newer version?›

Released 2026-03-10. It has been superseded by Nemotron 3.5 Super VL.

Is Nemotron 3 Super open source?›

Yes, the weights are open (nvidia-nemotron-open-model-license licence).

Can I run Nemotron 3 Super locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Nemotron 3 Super read images?›

No, it accepts text only.

What is Nemotron 3 Super?›

Nemotron 3 Super is an open-weights language model from NVIDIA, released Mar 2026, the successor to Llama Nemotron Super 49B v1.5.