Inference
EN
NVIDIA

Nemotron 3 Super 120B A12B

Nemotron 3 Super 120B A12B is a standard model from NVIDIA. It has no scored result.

  • Open weights
  • Standard
  • Input: text
  • Released 2026-03
No resultsEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.0%
SpeedOutput tokens per second.134/sMedian 67/s
First tokenSeconds to the first output token.0.7 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.075Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.40Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
nvidia/nemotron-3-super-120b-a12b
Max outputMaximum output tokens per request.
16K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
5 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$0.075$0.40262K
Amazon BedrockCloud$0.15$0.65262K
NebiusHost$0.30$0.90262K
Cloudflare Workers AIDeprecatedCloud$0.50$1.50256K
CrusoeHost$0.30$2.40262K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

0 counted
This model has no scored result.

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reusemodels.devMIT

History

5 releases
Output / 1M$0.45 → $0.40
23 Oct 202612 Nov 2026

Questions

How much does Nemotron 3 Super 120B A12B cost?
$0.075 per 1M input tokens, $0.40 per 1M output tokens.
How fast is Nemotron 3 Super 120B A12B?
134 output tokens per second, 0.7 s to the first token.
What is the context window of Nemotron 3 Super 120B A12B?
262K tokens.
Is Nemotron 3 Super 120B A12B open source?
Yes. Its weights are published.
When was Nemotron 3 Super 120B A12B released?
March 2026.

More from NVIDIA

All models
Nemotron 3 Super 100BUnrankedNemotron 3 Nano Omni 30B A3B38.6Cosmos3-NanoUnrankedCosmos3-SuperUnrankedNemotron 3 Ultra50.8