Nemotron 3 Super 120B
Nemotron 3 Super 120B is NVIDIA's language model. A 120B-parameter super-tier hybrid MoE LLM from NVIDIA's Nemotron 3 series, targeting maximum accuracy in multi-agent and enterprise reasoning tasks.
NVIDIA's language model. A 120B-parameter super-tier hybrid MoE LLM from NVIDIA's Nemotron 3 series, targeting maximum accuracy in multi-agent and enterprise reasoning tasks.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | Flex | Priority | ||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Amazon Bedrock | $0.150 | $0.650 | $0.075 | $0.325 | $0.075 | $0.325 | $0.263 | $1.14 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Nemotron 3 Super 120B | — | — | — | — | Current |
| Nemotron 3 Super | — | — | — | — | Available |
| Nemotron 3 Super 120B A12B | — | — | — | — | Available |
| Llama Nemotron Super 49B v1.5 | — | — | — | — | Available |
| Nemotron 1.5 Super 49B | — | — | — | — | Available |
| Llama 3.3 Nemotron Super 49B v1 | — | — | — | — | Available |
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Nemotron 4 15B | — | — | — | — | — |
| Nemotron Super 3 120B | — | 256K | $0.150 | $0.650 | |
| Nemotron Super 3 120B A12B | — | 262K | $0.090 | $0.450 | |
| Nemotron Nano 3 30B | — | 262K | $0.060 | $0.240 | |
| Nemotron 3 Nano 30B A3B | — | 262K | $0.050 | $0.200 | |
| Nemotron 3 | — | — | — | — | — |
| Nemotron 2 Nano 12B VL | Nano | 131K | — | — | |
| Nemotron Cascade 2 30B A3B | — | — | — | — | — |
| ProteinMPNN 1.0 2 | — | — | — | — | — |
| Nemotron 3 Nano 30B | Nano | 262K | — | — |