Compare AI models

Specifications
Parameters
4B—
Context window
256k1M
API pricing
Input price
—$0.40
Output price
—$1.60
Cached input price
—$0.10
Cheapest input
—$0.40Azure
Cheapest output
—$1.60Azure
—$160OpenAI list price
Benchmarks
MATH-500
95.4%81.4%
GPQA Diamond
53.2%65%
Overview
CompanyNVIDIAOpenAI
Release dateMar 16 2026Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Nano 4B and GPT-4.1 mini are evenly matched across the 2 benchmarks they both report (MATH-500, GPQA Diamond). Only GPT-4.1 mini has a verified first-party price for an available API: $0.40 per million input tokens and $1.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Nemotron 3 Nano 4B. GPT-4.1 mini shipped 336 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Nemotron 3 Nano 4B) vs 1M (GPT-4.1 mini). Nemotron 3 Nano 4B is open weight, while GPT-4.1 mini is closed.

On MATH-500, Nemotron 3 Nano 4B leads at 95.4% vs GPT-4.1 mini at 81.4%. On GPQA Diamond, GPT-4.1 mini leads at 65% vs Nemotron 3 Nano 4B at 53.2%.