AI Hub
← All models

DeepSeek-V4-Flash vs DeepSeek-V4-Pro

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 88.2)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.44 per 1M input)
  • DeepSeek-V4-Flash is faster
DeepSeek-V4-FlashDeepSeek-V4-Pro
Intelligence index89.488.2
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens1,048,576 tokens
Input price$0.10 / 1M$0.44 / 1M
Output price$0.20 / 1M$0.87 / 1M
Speed109 tok/s30 tok/s
ReleasedApril 24, 2026April 24, 2026
Parameters284B (13B active)1.6T (49B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
DeepSeek-V4-Pro
GPQA Diamond
89.4
90.1
Humanity’s Last Exam
32.1
35.9