AI Hub
← All models

DeepSeek-V4-Flash vs MiniMax M2.7

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 87.4)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.28 per 1M input)
  • DeepSeek-V4-Flash is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashMiniMax M2.7
Intelligence index89.487.4
DeveloperDeepSeekMiniMax
TypeLLMLLM
AccessOpen weightsOpen weights
Context window1,048,576 tokens204,800 tokens
Input price$0.10 / 1M$0.28 / 1M
Output price$0.20 / 1M$1.20 / 1M
Speed109 tok/s50 tok/s
ReleasedApril 24, 2026March 18, 2026
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
MiniMax M2.7
GPQA Diamond
89.4
87.4
Humanity’s Last Exam
32.1
28.1