nvidia
NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Type
- text
- Provider
- nvidia
- Model ID
- nvidia/nemotron-3-super-120b-a12b
- Capabilities
- tools, reasoning
- Context window
- 262K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.088 / 1M tokens
- Output price
- $0.50 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.
What it costs to run
cloud · 1M in + 1M out
$0.58
$0.088 for a million input tokens plus $0.50 for a million output tokens, billed from credits only when a request fails over to the cloud.
your hardware
$0 / token
Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.
Run it on your own hardware
Estimated GPU memory for NVIDIA: Nemotron 3 Super (120B parameters), for the weights alone — add room for the context cache.
- Q4_K_M
- ~68.9 GBfits a 80 GB card
- Q8_0
- ~119.2 GBmulti-GPU or large unified memory
- FP16 / BF16
- ~224.3 GBmulti-GPU or large unified memory
Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.
/// initialize
Call NVIDIA: Nemotron 3 Super through one OpenAI-compatible endpoint.
Serve it from hardware you own, with cloud failover when your nodes are busy or offline.
no credit card · 2 nodes free · openai-compatible
Frequently asked questions
- What is the context window of NVIDIA: Nemotron 3 Super?
- NVIDIA: Nemotron 3 Super accepts up to 262,144 tokens (262K) of context per request.
- How much does NVIDIA: Nemotron 3 Super cost per million tokens?
- Through Wide Area Intelligence, NVIDIA: Nemotron 3 Super costs $0.088 per 1M input tokens and $0.50 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.58.
- Can I run NVIDIA: Nemotron 3 Super on my own hardware?
- Yes — NVIDIA: Nemotron 3 Super is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 68.9 GB of GPU memory, plus room for the context cache — it fits a single 80 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.