← Back to Directory

NVIDIA: Nemotron Nano 9B V2

NVIDIA Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1052Chatbot Arena Verified
Max Context131,072Tokens
API Cost / 1M$0.20Blended Prompt + Completion

Model Capabilities

    NVIDIA-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...

    Granular Pricing Matrix

    Input Tokens (Prompt)$0.04 / 1M
    Output Tokens (Completion)$0.16 / 1M

    Pricing data via OpenRouter. Sync: 4/30/2026

    Evaluate Competitors

    VS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs Qwen: Qwen3 235B A22B Instruct 2507VS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs Google: Gemma 3n 4BVS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs Mistral: Mistral Small 3VS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs Reka EdgeVS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs LiquidAI: LFM2.5-1.2B-Instruct (free)VS Engine MatchupNVIDIA: Nemotron Nano 9B V2 vs Qwen: Qwen3 14B