NVIDIA: Nemotron Nano 9B V2
NVIDIA's Nemotron Nano 9B V2 is a compact, very affordable model with surprisingly strong math scores and decent instruction-following for its size, though its reasoning and coding benchmarks are limited — best suited for lightweight, cost-sensitive tasks where the $0.04/$0.16 pricing is the primary draw.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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 tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 9B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.04 | $0.000040 |
| Output | $0.16 | $0.000160 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
