Compare AI models

Specifications
Parameters
4B—
Context window
256k1M
API pricing
Input price
—$2.00
Output price
—$8.00
Cached input price
—$0.50
Cheapest input
—$2.00Azure
Cheapest output
—$8.00Azure
—$800OpenAI list price
Benchmarks
MATH-500
95.4%82.1%
GPQA Diamond
53.2%66.3%
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 are evenly matched across the 2 benchmarks they both report (MATH-500, GPQA Diamond). Only GPT-4.1 has a verified first-party price for an available API: $2.00 per million input tokens and $8.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Nemotron 3 Nano 4B. GPT-4.1 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). Nemotron 3 Nano 4B is open weight, while GPT-4.1 is closed.

On MATH-500, Nemotron 3 Nano 4B leads at 95.4% vs GPT-4.1 at 82.1%. On GPQA Diamond, GPT-4.1 leads at 66.3% vs Nemotron 3 Nano 4B at 53.2%.