Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Input price
—$0.40
Output price
—$1.60
Cached input price
—$0.10
Cheapest input
$0.256DeepInfra$0.40Azure
Cheapest output
$0.712DeepInfra$1.60Azure
$103StreamLake$160OpenAI list price
Benchmarks
SWE-Bench Verified
42%23.6%
GPQA Diamond
59.1%65%
MMLU
88.5%87.5%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads GPT-4.1 mini on 2 of the 3 benchmarks they both report (SWE-Bench Verified, GPQA Diamond, MMLU). 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 DeepSeek V3. DeepSeek V3 shipped 109 days before GPT-4.1 mini, so benchmark comparisons should account for the intervening progress.

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

On SWE-Bench Verified, DeepSeek V3 leads at 42% vs GPT-4.1 mini at 23.6%. On GPQA Diamond, GPT-4.1 mini leads at 65% vs DeepSeek V3 at 59.1%. On MMLU, DeepSeek V3 leads at 88.5% vs GPT-4.1 mini at 87.5%.