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
—$0.15Azure
Cheapest output
—$0.60Azure
—$60.00OpenAI list price
Benchmarks
DROP
92.279.7
GPQA Diamond
71.5%40.2%
MMLU
90.8%82%
Overview
CompanyDeepSeekOpenAI
Release dateJan 20 2025Jul 18 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads GPT-4o mini on 3 of the 3 benchmarks they both report (DROP, 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 R1. GPT-4o mini shipped 186 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 128k (GPT-4o mini). DeepSeek R1 is open weight, while GPT-4o mini is closed.

On DROP, DeepSeek R1 leads at 92.2 vs GPT-4o mini at 79.7. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs GPT-4o mini at 40.2%. On MMLU, DeepSeek R1 leads at 90.8% vs GPT-4o mini at 82%.