NVIDIA: Nemotron Nano 9B V2
Analysis Summary
NVIDIA Nemotron Nano 9B V2 is a small 9B-parameter model priced at just $0.04 input and $0.16 output per million tokens, making it one of the most affordable options in the current field. It supports tool use and function calling, and its 131K context window is adequate for most document tasks.
With a modest intelligence index and limited agentic and coding scores, it is not suited to complex reasoning, autonomous agents, or serious software engineering. It performs best on straightforward content generation, classification, summarisation, and lightweight instruction-following tasks where cost efficiency matters more than depth.
For businesses running high-volume, low-complexity workloads, Nemotron Nano 9B V2 offers a practical cost-saving option. It is not a replacement for mid-tier or flagship models on demanding tasks, but as a budget tier in a tiered deployment strategy it has clear utility.
Assessed June 17, 2026
Editorial notes
NVIDIA Nemotron Nano 9B V2 is a compact, low-cost model with tool use and function calling, suited to lightweight content and classification tasks where budget is the primary constraint.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How NVIDIA: Nemotron Nano 9B V2 compares
NVIDIA: Nemotron Nano 9B V2 ranks #248 of 380 AI models we track for overall intelligence, #258 of 317 for coding, #249 of 292 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.04 per million input tokens it is cheaper than 74% of comparable models.
About NVIDIA: Nemotron Nano 9B V2
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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does NVIDIA: Nemotron Nano 9B V2 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
nvidia/nemotron-nano-9b-v2
|
| Provider | nvidia |
| Release Date | September 5, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.04 | $0.000040 |
| Output | $0.16 | $0.000160 |
Leaderboard Categories
External Resources
Frequently asked questions about NVIDIA: Nemotron Nano 9B V2
How much does NVIDIA: Nemotron Nano 9B V2 cost?
NVIDIA: Nemotron Nano 9B V2 costs $0.04 per million input tokens and $0.16 per million output tokens.
What is the context window of NVIDIA: Nemotron Nano 9B V2?
NVIDIA: Nemotron Nano 9B V2 has a context window of 131,072 tokens (131K).
Is NVIDIA: Nemotron Nano 9B V2 good for coding?
On our coding benchmark index, NVIDIA: Nemotron Nano 9B V2 ranks #258 of 317 models, placing it in the broader range of the field for code generation and debugging.
What can NVIDIA: Nemotron Nano 9B V2 do?
NVIDIA: Nemotron Nano 9B V2 supports tool use and function calling.
Who created NVIDIA: Nemotron Nano 9B V2?
NVIDIA: Nemotron Nano 9B V2 is developed by NVIDIA and was released on September 5, 2025.
