Nemotron 3 Super
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
- Context
- 262K
- Released
- 7mo ago
- Parameters
- 120B
- Input / 1M tokens
- $0.08
- Output / 1M tokens
- $0.45
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- NVIDIA
- Model family
- Nemotron
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- March 11, 2026
- Model ID
nvidia/nemotron-3-super-120b-a12b- Openness
- Open weights
- License
- —
- Parameters
- 120B
- Architecture
- nemotron_h_moe
- Families
- nemotron_h_moe
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Native context
- 262K
- Tokenizer
- Other
- Max output tokens
- 236K
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- nvidia/nemotron-3-super-120b-a12b
- Source family
- nemotron
- Last updated
- 2026-03-11
- Model context
- 262K
- Model output limit
- 262K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Complete source record (JSON)
{
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super 120B A12B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"family": "nemotron",
"last_updated": "2026-03-11",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"release_date": "2026-03-11",
"open_weights": true
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| dekallm/fp8 | 262K | $0.08 | $0.45 | — | — | 99.58% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| deepinfra/bf16 | 262K | $0.08 | $0.40 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.