DeepSeek-V4-Flash-0731vsGPT-4o

DeepSeek-V4-Flash-0731
GPT-4o
Specifications
Context window
128k
API pricing
Input price
$0.22$2.50
Output price
$0.66$10.00
Cached input price
$0.007$1.25
Cheapest input
$0.04OpenInference$2.50Azure
Cheapest output
$0.10OpenInference$10.00Azure
Benchmarks
BullshitBench v2
39%12%
Benchmarks
SWE-Bench Verified
79%
Terminal-Bench 2.1
82.7%
Toolathlon-Verified
70.3%
BrowseComp
73.2%
CyberGym
76.7%
Humanity's Last Exam · with tools
34.8%
GPQA Diamond
49.9%
AutomationBench
25.1%
Overview
CompanyDeepSeekOpenAI
Release dateJul 31 2026May 13 2024
AccessProprietaryProprietary

Other comparisons

DeepSeek-V4-Flash-0731vsClaude Fable 5.1GPT-4ovsClaude Fable 5.1DeepSeek-V4-Flash-0731vsGemini 3.8 FlashGPT-4ovsGemini 3.8 FlashDeepSeek-V4-Flash-0731vsMuse Spark 1.3GPT-4ovsMuse Spark 1.3DeepSeek-V4-Flash-0731vsGrok 4.6GPT-4ovsGrok 4.6DeepSeek-V4-Flash-0731vsMistral Medium 3.5GPT-4ovsMistral Medium 3.5DeepSeek-V4-Flash-0731vsKimi K3GPT-4ovsKimi K3

Frequently asked questions

DeepSeek-V4-Flash-0731 leads GPT-4o on 1 of the 1 benchmark they both report (BullshitBench v2). DeepSeek-V4-Flash-0731 is cheaper on both input and output: $0.22 vs $2.50 per million input tokens, and $0.66 vs $10.00 per million output tokens. Figures are base-tier rates. GPT-4o shipped 809 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, DeepSeek-V4-Flash-0731 leads at 39% vs GPT-4o at 12%.