AI Hub
← All models

DeepSeek-V4-Flash vs GPT-5.4 nano

DeepSeek vs OpenAI — benchmarks, pricing, and capabilities side by side.

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 81.7)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.20 per 1M input)
  • GPT-5.4 nano is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashGPT-5.4 nano
Intelligence index89.481.7
DeveloperDeepSeekOpenAI
TypeLLMLLM
AccessOpen weightsAPI only
Context window1,048,576 tokens400,000 tokens
Input price$0.10 / 1M$0.20 / 1M
Output price$0.20 / 1M$1.25 / 1M
Speed109 tok/s157 tok/s
ReleasedApril 24, 2026March 17, 2026
Parameters284B (13B active)
Input modalitiesTextText, Image
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
GPT-5.4 nano
GPQA Diamond
89.4
81.7
Humanity’s Last Exam
32.1
26.5