Question 1

What is Nemotron 3 Nano 30B A3B?

Accepted Answer

Nemotron 3 Nano 30B A3B is a model from NVIDIA, released on Dec 15, 2025. NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Question 2

How much does Nemotron 3 Nano 30B A3B cost?

Accepted Answer

On the Respan gateway, input starts at $0.05 per 1M tokens on Novita, and output starts at $0.18 per 1M tokens on Novita, after gateway discounts. Averaged across 4 providers, it costs $0.05 per 1M input tokens and $0.21 per 1M output tokens.

Question 3

Which providers serve Nemotron 3 Nano 30B A3B on Respan?

Accepted Answer

4 providers serve Nemotron 3 Nano 30B A3B: Novita, DeepInfra, OpenRouter, and Nebius.

Question 4

What is Nemotron 3 Nano 30B A3B's context window?

Accepted Answer

Nemotron 3 Nano 30B A3B accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Nemotron 3 Nano 30B A3B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "nemotron-3-nano-30b-a3b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Nemotron 3 Nano 30B A3B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 108 tokens per second, and the lowest response latency was 0.3 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Nemotron 3 Nano 30B A3B rank on the Respan Index?

Accepted Answer

Nemotron 3 Nano 30B A3B scores 14.9 out of 100 on the Respan Index v1.1, ranking #121 of 138 models. By category: Coding 4.6 (estimated), Agents 16.3 (estimated), Reasoning 12.5, Knowledge & language 8.5, and Human preference 37.7. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Nemotron 3 Nano 30B A3B score on benchmarks?

Accepted Answer

Nemotron 3 Nano 30B A3B has 10 published benchmark scores, including LiveCodeBench 68.3%, GPQA (with tools) 75%, and AIME 2025 (with tools) 99.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
NovitaSave 10%`novita/nvidia/nemotron-3-nano-30b-a3b`	262K	$0.05/M	$0.18/M
DeepInfra`deepinfra/nvidia/Nemotron-3-Nano-30B-A3B`	262K	$0.05/M	$0.20/M
OpenRouter`openrouter/nvidia/nemotron-3-nano-30b-a3b`	262K	$0.05/M	$0.20/M
Nebius`nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B`	262K	$0.06/M	$0.24/M

Nemotron 3 Nano 30B A3B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding2

Reasoning

Apps