Nvidia · nemotron family
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| Cortecs | nemotron-3-super-120b-a12b | $0.266 / 1M | $0.799 / 1M | 262,144 | 262,144 |
| NanoGPT | nvidia/nemotron-3-super-120b-a12b | $0.05 / 1M | $0.25 / 1M | 262,144 | 16,384 |
| Nvidia | nvidia/nemotron-3-super-120b-a12b | $0.2 / 1M | $0.8 / 1M | 262,144 | 262,144 |
| Perplexity Agent | nvidia/nemotron-3-super-120b-a12b | $0.25 / 1M | $2.5 / 1M | 1,000,000 | 32,000 |
| Nebius Token Factory | nvidia/nemotron-3-super-120b-a12b | $0.3 / 1M | $0.9 / 1M | 256,000 | 32,768 |
| Kilo Gateway | nvidia/nemotron-3-super-120b-a12b | $0.1 / 1M | $0.5 / 1M | 262,144 | 262,144 |
| OpenRouter | nvidia/nemotron-3-super-120b-a12b | $0.21 / 1M | $0.455 / 1M | 1,000,000 | 16,384 |
| Vercel AI Gateway | nvidia/nemotron-3-super-120b-a12b | $0.15 / 1M | $0.65 / 1M | 256,000 | 32,000 |
Attachments
No
Reasoning
Yes
Tool calling
Yes
Structured output
Unknown
Temperature
Yes