Home › Providers › nvidia › NVIDIA: Nemotron 3 Super
NVIDIA: Nemotron 3 Super API Pricing
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...
How much does NVIDIA: Nemotron 3 Super cost for a real workload?
At 10M input + 2M output tokens per month, NVIDIA: Nemotron 3 Super costs about $7.8 ($3 input + $4.8 output). Try your own volumes in the cost calculator.
What are cheaper alternatives to NVIDIA: Nemotron 3 Super?
- DeepSeek: R1 0528 — $0.5 in / $2.15 out per 1M
- DeepSeek: DeepSeek V4 Pro 0813 — $0.66 in / $1.98 out per 1M
- OpenAI: GPT-5.4 Mini (batch) — $0.375 in / $2.25 out per 1M
- Z.ai: GLM 4.7 — $0.54 in / $1.98 out per 1M
- Z.ai: GLM 5.3 (batch) — $0.45 in / $2 out per 1M
- Qwen: Qwen3.5-27B — $0.27 in / $2.16 out per 1M
Where to run NVIDIA: Nemotron 3 Super
AI/ML API: one API key for 400+ models, including most models tracked here · Novita AI: pay-as-you-go APIs for open models (DeepSeek, Qwen, Llama and more) plus GPU cloud. Prices there follow each platform's own catalog and can differ from the list prices tracked here.
Run it on AI/ML API →Run it on Novita AI →
Disclosure: links to these platforms may be affiliate links — if you sign up or buy through them, LLMPrices may earn a commission at no extra cost to you.
Compare NVIDIA: Nemotron 3 Super with other models
NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3.5 Super VL (free)NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3.5 Lightning (free)NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3.5 Content Safety (free)NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3 Ultra (free)NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3 Nano Omni (free)NVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron 3 Super (free)
Frequently asked questions
How much does NVIDIA: Nemotron 3 Super cost?
NVIDIA: Nemotron 3 Super costs $0.3 per 1M input tokens and $2.4 per 1M output tokens (list price, snapshot October 22, 2026). At 10M input + 2M output tokens per month that is about $7.8.
What is the context window of NVIDIA: Nemotron 3 Super?
NVIDIA: Nemotron 3 Super has a context window of 262,144 tokens and can return up to 235,929 output tokens per response.
What are cheaper alternatives to NVIDIA: Nemotron 3 Super?
Cheaper models include DeepSeek: R1 0528 ($0.5 in / $2.15 out), DeepSeek: DeepSeek V4 Pro 0813 ($0.66 in / $1.98 out), OpenAI: GPT-5.4 Mini (batch) ($0.375 in / $2.25 out). See the full list on this page.
Is NVIDIA: Nemotron 3 Super free to use?
No. NVIDIA: Nemotron 3 Super is a paid model at $0.3 input / $2.4 output per 1M tokens. 21 free models are listed on the free models page.
Provider: nvidia · Model ID: nvidia/nemotron-3-super-120b-a12b · Modality: text->text · Price snapshot October 22, 2026, refreshed daily. How we collect prices