Nemotron 3 Super

Name: Nemotron 3 Super
Author: NVIDIA

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 Mam

by NVIDIA(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Reference model card from the OpenRouter listing - model nvidia/nemotron-3-super-120b-a12b. Prices are per million tokens as listed; ratings and installs below are from this marketplace.

Nemotron 3 Super

Facts


Vendor	NVIDIA
Context window	262,144 tokens
Max output	235,929 tokens
Input price	$0.08 / 1M tokens
Output price	$0.45 / 1M tokens
Input	text
Output	text
Tool calling	yes
Structured outputs	yes
Reasoning	yes
Open weights	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8

Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model nvidia/nemotron-3-super-120b-a12b

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-nvidia-nemotron-3-super-120b-a12b", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

model-nvidia-nemotron-3-super-120b-a12b.ocm.jsonjson

{
  "ocm": "1",
  "id": "model-nvidia-nemotron-3-super-120b-a12b",
  "kind": "llm",
  "name": "Nemotron 3 Super",
  "description": "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...",
  "publisher": "NVIDIA",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "llm",
      "nvidia",
      "openrouter",
      "open-weights",
      "reasoning",
      "tool-calling",
      "models"
    ],
    "languages": [
      "en"
    ],
    "modalities": [
      "text"
    ],
    "supports_tools": true,
    "supports_streaming": true,
    "context_window": 262144
  },
  "quality_prior": 0.136,
  "examples": [
    "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..."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "models",
      "ref": "1773245239",
      "url": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b",
      "key": "nvidia/nemotron-3-super-120b-a12b",
      "catalogue": "https://openrouter.ai/api/v1"
    },
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "pricing": {
      "input_usd_per_1m": 0.08,
      "output_usd_per_1m": 0.45
    },
    "max_output_tokens": 235929,
    "output_modalities": [
      "text"
    ],
    "hugging_face_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
    "reasoning": true,
    "created": 1773245239,
    "benchmarks": {
      "intelligence_index": 13.6,
      "coding_index": 37.7,
      "agentic_index": 4.1,
      "hub_downloads": 72728,
      "hub_downloads_total": 2593309,
      "hub_likes": 279,
      "hub_trending": 0,
      "osr_index": 28,
      "osr_coverage": 0.4
    }
  },
  "cost": {
    "usd_per_1k_tokens": 0.000265
  },
  "endpoints": [
    {
      "protocol": "openai",
      "url": "https://openrouter.ai/api/v1"
    }
  ]
}

Fetch it by URL: GET /api/v1/registry/model-nvidia-nemotron-3-super-120b-a12b/manifest?version=1.0.0

About

Nemotron 3 Super

Facts

Use it

Manifest

Reviews