AI Hub
← All models

DeepSeek-V4-Flash vs Mercury 2

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 77)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.25 per 1M input)
  • Mercury 2 is faster
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V4-FlashMercury 2
Intelligence index89.477
DeveloperDeepSeekInception
TypeLLMLLM
AccessOpen weightsAPI only
Context window1,048,576 tokens128,000 tokens
Input price$0.10 / 1M$0.25 / 1M
Output price$0.20 / 1M$0.75 / 1M
Speed109 tok/s790 tok/s
ReleasedApril 24, 2026March 4, 2026
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek-V4-Flash
Mercury 2
GPQA Diamond
89.4
77
Humanity’s Last Exam
32.1
15.5