Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Input price
—$0.15
Output price
—$0.60
Cached input price
—$0.075
Cheapest input
$0.256DeepInfra$0.15Azure
Cheapest output
$0.712DeepInfra$0.60Azure
$103StreamLake$60.00OpenAI list price
Benchmarks
GPQA Diamond
59.1%40.2%
MMLU
88.5%82%
Overview
CompanyDeepSeekOpenAI
Release dateDec 26 2024Jul 18 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads GPT-4o mini on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). Only GPT-4o mini has a verified first-party price for an available API: $0.15 per million input tokens and $0.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. GPT-4o mini shipped 161 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 128k (GPT-4o mini). DeepSeek V3 is open weight, while GPT-4o mini is closed.

On GPQA Diamond, DeepSeek V3 leads at 59.1% vs GPT-4o mini at 40.2%. On MMLU, DeepSeek V3 leads at 88.5% vs GPT-4o mini at 82%.