NVIDIA/ Nemotron
Nemotron Nano 9B v2
nvidia/nemotron/nano-9b-v2
Compact Nemotron model for efficient reasoning and deployable AI agents
Released
2025-08-18
Context window
131K
Max output
131K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- nemotron-nano-9b-v2
- Knowledge cutoff
- 2025-03-31
- Aliases
- Nemotron Nano 9B v2
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Kilo Gateway | nvidia/nemotron-nano-9b-v2 | openai_chat | 131K | 131K | Text | Text | ReasoningTool callTemperatureOpen weight | - | - | Yes |
| Merge Gateway | nvidia/nemotron-nano-9b-v2 | openai_chat | 131K | 131K | Text | Text | ReasoningTool callTemperatureOpen weight | - | input $0.06/M output $0.23/M | Yes |
| Vercel AI Gateway | nvidia/nemotron-nano-9b-v2 | openai_chat | 131K | 131K | Text | Text | ReasoningTool callTemperatureOpen weight | - | input $0.06/M output $0.23/M | Yes |
| OpenRouter | nvidia/nemotron-nano-9b-v2:free | openai_chat | 131K | 131K | Text | Text | ReasoningTool callTemperatureOpen weight | Hugging Face: nvidia/NVIDIA-Nemotron-Nano-9B-v2 | input $0/M output $0/M | Yes |
Capabilities
ReasoningTool callTemperatureOpen weight