ZMIME
NVIDIA · Released Aug 18, 2025

Nemotron Nano 9B v2

Compact Nemotron model for efficient reasoning and deployable AI agents.

  • Open weights
  • Reasoning
  • Tool calling
  • Deprecated
Capability
—No ECI score yet
Input
$0.06per 1M tokens
Output
$0.23per 1M tokens
Context
131K131K max output
Pricing

What it costs

Input
$0.06per million tokens
Output
$0.23per million tokens
Blended (3:1)
$0.102cheaper than 91% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.235
Team assistant25M input + 5M output tokens$2.65
Production app250M input + 50M output tokens$26.50

Median of 3 paid API providers on models.dev; NVIDIA also offers it free on Nvidia.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Nemotron Nano 9B v2 yet.

Specifications

The details

Lab
NVIDIA
Released
Aug 18, 2025
Context window
131,072 tokens
Max output
131,072 tokens
Inputs
Text
Output
Text
Reasoning
Can be switched on or off
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
nvidia/nvidia-nemotron-nano-9b-v2on Nvidia
Availability
4 API providerslisted on models.dev
Status
Deprecated by the provider

Nvidia model documentation

Same lab

More from NVIDIA

Questions

About Nemotron Nano 9B v2

How much does Nemotron Nano 9B v2 cost?

Nemotron Nano 9B v2 costs $0.06 input / $0.23 output per million tokens (median across 3 API providers; free on Nvidia). At a 3:1 input-to-output mix that is $0.102 per million tokens, cheaper than 91% of the 360 priced models we track.

What is the context window of Nemotron Nano 9B v2?

Nemotron Nano 9B v2 accepts up to 131,072 tokens per request and can write up to 131,072 tokens in one response.

How good is Nemotron Nano 9B v2?

Epoch AI has not published a Capabilities Index score for Nemotron Nano 9B v2 yet.

Is Nemotron Nano 9B v2 open source?

Yes. NVIDIA publishes the weights, so it can be downloaded and self-hosted.

What inputs does Nemotron Nano 9B v2 support?

Nemotron Nano 9B v2 accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Nemotron Nano 9B v2 released?

NVIDIA released Nemotron Nano 9B v2 on Aug 18, 2025.

What are the best alternatives to Nemotron Nano 9B v2?

The closest current models from other labs on capability, price and release date are Apertus 8B (Swiss AI, $0.10 / $0.20), Granite-4.0-H-Small (IBM, $0.064 / $0.265), Sarvam 105B (Sarvam AI, $0.047 / $0.186) and Qwen Flash (Alibaba (Qwen), $0.05 / $0.40).