Nemotron 3 Super 120B A12B
Nemotron 3 Super 120B A12BAlternatives?
CheaperDeepSeek V4 Pro 0813maxOpen×2.1-59%$0.67Memory (4-bit): 74 GB → 990 GB+5
BetterMuse Glimmer 30BhighOpen+48%-96%$0.058Context: 1M → 131K
OpenQwen3.8 27Bxhigh+88%-39%$1.01Context: 1M → 262K+5
CheaperGrok 4.6high×2.1-9%$1.48Context: 1M → 500KCheaperMuse Spark 1.2xhigh×2-41%$0.97Only auto tool_choice is supported+1DeepSeek V4 Pro 0813maxOpen×2.1-59%$0.67Memory (4-bit): 74 GB → 990 GB+5Grok 4.6high×2.1-9%$1.48Context: 1M → 500KMuse Spark 1.2xhigh×2-41%$0.97Only auto tool_choice is supported+1
Step 5 PreviewthinkingOpen×2-37%$1.03Memory (4-bit): 74 GB → 363 GB+3Qwen3.7 Maxthinking+91%-30%$1.15Muse Glimmer 30BhighOpen+48%-96%$0.058Context: 1M → 131K
Gemini 3.1 Flash Litehigh+19%-96%$0.06TInkling SmallthinkingOpen+81%-95%$0.089Context: 1M → 256K+2
GPT-5.6 Lunamax+73%-89%$0.18GPT-5.4 Nanoxhigh+34%-89%$0.18Context: 1M → 400KQwen3.8 27BxhighOpen+88%-39%$1.01Context: 1M → 262K+5TInkling SmallthinkingOpen+81%-95%$0.089Context: 1M → 256K+2Muse Glimmer 30BhighOpen+48%-96%$0.058Context: 1M → 131K
Mistral Medium 3.5highOpen+43%-69%$0.50Context: 1M → 262K+1Step 3.7 FlashhighOpen+23%+15%$0.20 / $1.15Context: 1M → 256K+1Nemotron 3 UltrathinkingOpen+23%-65%$0.58Memory (4-bit): 74 GB → 336 GBNemotron 3.5 LightningthinkingOpen-22%-95%$0.079Nemotron 3.5 Super VLOpenn/a—$0.19Memory (4-bit): 74 GB → 75 GBNemotron 3.5 Bolt 74B-A9BOpenn/a——Context: 1M → 256KNemotron 3 Nano Omni 30B A3B ReasoningOpenn/a—$0 / $0Context: 1M → 256KNemotron Cascade 2 30B A3BOpenn/a——NVIDIA Nemotron 3 Nano 4BOpenn/a——Context: 1M → 262KNemotron 3 SuperOpenn/a—$0.085 / $0.40All NVIDIA models →Run it yourself
estimateBenchmarks
in Agents & Tool UseFAQ
How much does Nemotron 3 Super 120B A12B cost?›
$0.13 per 1M input tokens and $1.15 per 1M output tokens (cheapest host: Featherless). A typical benchmark task costs about $1.64 at default effort.
Is Nemotron 3 Super 120B A12B free to use?›
There is no free API; the cheapest paid price is $0.13 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Nemotron 3 Super 120B A12B, and what is it best at?›
#121 of 334 in Chat & Knowledge, #75 of 132 in Coding, #89 of 133 in Agents & Tool Use, #41 of 245 in Writing & Language, #104 of 133 in Vision & Documents. Strongest at: Instructions.
Is Nemotron 3 Super 120B A12B better than GPT OSS 120B?›
On EnterpriseOps-Gym-AA, Nemotron 3 Super 120B A12B scores 23.5 vs 25.5 — lower. It is 1,678% more expensive per task.
How can I use Nemotron 3 Super 120B A12B?›
Through the API of Featherless.
What is the context window of Nemotron 3 Super 120B A12B?›
1M tokens.
When was Nemotron 3 Super 120B A12B released? Is there a newer version?›
Released 2026-03-11. It is the current version in its line.
Is Nemotron 3 Super 120B A12B open source?›
Yes, the weights are open (nvidia-nemotron-open-model-license licence).
Can I run Nemotron 3 Super 120B A12B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Nemotron 3 Super 120B A12B read images?›
No, it accepts text only.
What is Nemotron 3 Super 120B A12B?›
Nemotron 3 Super 120B A12B is an open-weights language model from NVIDIA, released Mar 2026.
What are the best alternatives to Nemotron 3 Super 120B A12B?›
DeepSeek V4 Pro 0813 (cheaper), Muse Glimmer 30B (better), Qwen3.8 27B (open weights).