Nemotron 3 Super 120B A12B
Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning and tool calling.
Specs
- Context
- 1.05M
- Max output
- 32.8K
- Input price
- —
- Output price
- —
- Released
- 2026-03-11
Context
- Context window
- 1.05M
- Max input
- —
- Max output
- 32.8K
Pricing
- Not published
Modalities
- Input
- Text
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Active
- Released
- 2026-03-11
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
nvidiamodel = nvidia/nemotron-3-super-120b-a12b
chat
POSThttps://integrate.api.nvidia.com/v1/chat/completions
JSON
Standard format
{
"id": "nemotron-3-super-120b-a12b",
"object": "model",
"created": 1773187200,
"owned_by": "nvidia",
"name": "Nemotron 3 Super 120B A12B",
"api": {
"types": [
"chat"
]
},
"limits": {
"context": 1048576,
"input": null,
"output": 32768
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": null,
"features": [
"tools",
"structured_output"
],
"info": {
"status": "active",
"release_date": "2026-03-11",
"knowledge_cutoff": null,
"description": "Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning and tool calling.",
"docs": "https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard",
"verified_at": "2026-10-11"
}
}Official sources
3