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 Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 262K token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere, from workstation to cloud.
$0.0375market price $0.075
$0.20market price $0.40
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
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.
On NagaAI, Nemotron 3 Super costs $0.0375 per 1M input tokens and $0.20 per 1M output tokens. You pay only for what you use, with no subscription.
Nemotron 3 Super reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Nemotron 3 Super can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Nemotron 3.5 Super VLNvidiaNemotron 3.5 LightningNvidiaNemotron 3.5 Content SafetyNvidia$0.10 / $0.10 per 1MNemotron 3 UltraNvidiaNemotron 3 Nano 30B A3BNvidia$0.03 / $0.12 per 1M
LFM3-1.7BLiquid AI$0.04 / $0.10 per 1M