DeepSeek-V4-Flash-0731vsGPT-5 nano

DeepSeek-V4-Flash-0731
GPT-5 nano
API pricing
Input price
$0.22$0.05
Output price
$0.66$0.40
Cached input price
$0.007$0.005
Cheapest input
$0.04OpenInference$0.05Azure
Cheapest output
$0.08Relace$0.40Azure
Benchmarks
BullshitBench v2
38%
Terminal-Bench 2.1
82.7%
Toolathlon-Verified
70.3%
CyberGym
76.7%
AutomationBench
25.1%
Overview
CompanyDeepSeekOpenAI
Release dateJul 31 2026Aug 7 2025
AccessProprietaryProprietary

Other comparisons

DeepSeek-V4-Flash-0731vsClaude Opus 5GPT-5 nanovsClaude Opus 5DeepSeek-V4-Flash-0731vsGemini 3.7 FlashGPT-5 nanovsGemini 3.7 FlashDeepSeek-V4-Flash-0731vsMuse GlimmerGPT-5 nanovsMuse GlimmerDeepSeek-V4-Flash-0731vsGrok 4.6GPT-5 nanovsGrok 4.6DeepSeek-V4-Flash-0731vsMistral Medium 3.5GPT-5 nanovsMistral Medium 3.5DeepSeek-V4-Flash-0731vsKimi K3GPT-5 nanovsKimi K3

Frequently asked questions

DeepSeek-V4-Flash-0731 and GPT-5 nano don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5 nano is cheaper on both input and output: $0.05 vs $0.22 per million input tokens, and $0.40 vs $0.66 per million output tokens. Figures are base-tier rates. GPT-5 nano shipped 358 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.

Direct benchmark comparisons are unavailable — DeepSeek-V4-Flash-0731 and GPT-5 nano don't publish scores on any of the same benchmarks.

DeepSeek-V4-Flash-0731 was released by DeepSeek on Jul 31 2026.

GPT-5 nano was released by OpenAI on Aug 7 2025.

GPT-5 nano is cheaper on both input and output: $0.05 vs $0.22 per million input tokens, and $0.40 vs $0.66 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.