token.app › NVIDIA › Nemotron 3 Nano 30B A3B (free)

Nemotron 3 Nano 30B A3B (free) pricing & benchmarks

Nemotron 3 Nano 30B A3B (free) is available from NVIDIA at Free per million input tokens and Free per million output tokens (Free blended at 3:1). It accepts up to 256,000 tokens of context. 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...

Pricing

Per million tokens · OpenRouter

InputFree

OutputFree

Blended (3:1)Free

Specification

nvidia/nemotron-3-nano-30b-a3b:free

Context window256K

Max output—

ReleasedDec 2025

LicenceOpen weights

Modalitiesin:text, out:text

No independently-run benchmark scores are published for Nemotron 3 Nano 30B A3B (free) yet. We show nothing rather than reprinting an unverified figure.

Compare Nemotron 3 Nano 30B A3B (free)

Nemotron 3 Nano 30B A3B (free) vs Qwen3.8 Max Nemotron 3 Nano 30B A3B (free) vs DeepSeek V4 Flash 0731 Nemotron 3 Nano 30B A3B (free) vs Claude Opus 5 Nemotron 3 Nano 30B A3B (free) vs Gemini 3.6 Flash Nemotron 3 Nano 30B A3B (free) vs Kimi K3 Nemotron 3 Nano 30B A3B (free) vs GPT-5.6 Luna Nemotron 3 Nano 30B A3B (free) vs GPT-5.6 Terra Nemotron 3 Nano 30B A3B (free) vs GPT-5.6 Sol

FAQ

How much does Nemotron 3 Nano 30B A3B (free) cost?

Nemotron 3 Nano 30B A3B (free) costs Free per million input tokens and Free per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to Free per million tokens.

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

Nemotron 3 Nano 30B A3B (free) accepts up to 256,000 tokens of context.