Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
$0.256DeepInfra$0.10Azure
Cheapest output
$0.712DeepInfra$0.40Azure
$103StreamLake$40.00Azure
Benchmarks
GPQA Diamond
59.1%50.3%
MMLU
88.5%80.1%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads GPT-4.1 nano on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). DeepSeek V3 shipped 109 days before GPT-4.1 nano, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 1M (GPT-4.1 nano). DeepSeek V3 is open weight, while GPT-4.1 nano is closed.

On GPQA Diamond, DeepSeek V3 leads at 59.1% vs GPT-4.1 nano at 50.3%. On MMLU, DeepSeek V3 leads at 88.5% vs GPT-4.1 nano at 80.1%.