# NVIDIA Nemotron Nano 9B V2: AI model fact sheet

- **Provider:** nvidia
- **Released:** 2025-09-05
- **Context window:** 131,072 tokens
- **API pricing:** $0.04 / 1M input, $0.16 / 1M output
- **OpenRouter ID:** nvidia/nemotron-nano-9b-v2
- **Capabilities:** conversation, reasoning, code-generation, analysis

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, designed as a unified model for reasoning and non-reasoning tasks. It can expose an internal reasoning trace and then produce a final answer, or be configured via system prompt to only provide final answers without intermediate traces.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| LiveCodeBench | 71.1% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/nemotron-nano-9b-v2