← model directory
nvidia
NVIDIA: Nemotron Nano 9B V2
nvidia/nemotron-nano-9b-v2
↓ runs free on your own hardwareNVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
specs & pricing
- Type
- text
- Provider
- nvidia
- Model ID
- nvidia/nemotron-nano-9b-v2
- Capabilities
- tools, reasoning
- Context window
- 131K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.044 / 1M tokens
- Output price
- $0.18 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.