Model information
Released
2026-03-11
Context window
262K
Max output
262K
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- nemotron-3-super-120b-a12b
- Aliases
- Nemotron 3 Super 120B A12B
Resources
Capabilities
Open weightReasoningTemperatureTool call
Official price
input $0.2/M · output $0.8/M
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Nvidia | nvidia/nemotron-3-super-120b-a12b | custom | 262K | 262K | ReasoningTool callTemperature | - | input $0.2/M · output $0.8/M | Yes | ||
| Nebius Token Factory | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callStructuredTemperature | - | input $0.3/M · output $0.9/M | Yes | ||
| NanoGPT | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0.05/M · output $0.25/M cache read $0.025/M | Yes | ||
| Kenari | nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0/M · output $0/M | Yes | ||
| Kenari | nemotron-3-super-120b-a12b:free | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0/M · output $0/M | Yes | ||
| TensorX | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0.3/M · output $0.9/M cache read $0.075/M · cache write $0.375/M | Yes | ||
| Kilo Gateway | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callStructuredTemperature | - | input $0.085/M · output $0.4/M | Yes | ||
| Kilo Gateway | nvidia/nemotron-3-super-120b-a12b:free | openai_chat | 262K | 262K | ReasoningTool callStructuredTemperature | - | input $0/M · output $0/M | Yes | ||
| Vercel AI Gateway | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTemperature | - | input $0.15/M · output $0.65/M | Yes | ||
| OpenRouter | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callStructuredTemperature | Reasoning levels: medium, low, Default reasoning: medium, Reasoning supports token budgets, Hugging Face: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | input $0.085/M · output $0.4/M | Yes | ||
| OpenRouter | nvidia/nemotron-3-super-120b-a12b:free | openai_chat | 262K | 262K | ReasoningTool callStructuredTemperature | Reasoning levels: medium, low, Default reasoning: medium, Reasoning supports token budgets, Hugging Face: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | input $0/M · output $0/M | Yes | ||
| Perplexity Agent | nvidia/nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0.25/M · output $2.5/M | Yes | ||
| Cortecs | nemotron-3-super-120b-a12b | openai_chat | 262K | 262K | ReasoningTool callTemperature | - | input $0.266/M · output $0.799/M | Yes |