AI Hub
← All models

DeepSeek V3.1 Terminus vs DeepSeek-V4-Flash

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

  • DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 83.5)
  • DeepSeek-V4-Flash is cheaper ($0.10 vs $0.27 per 1M input)
  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek V3.1 TerminusDeepSeek-V4-Flash
Intelligence index83.589.4
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window163,840 tokens1,048,576 tokens
Input price$0.27 / 1M$0.10 / 1M
Output price$0.95 / 1M$0.20 / 1M
Speed109 tok/s
ReleasedSeptember 22, 2025April 24, 2026
Parameters284B (13B active)
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

DeepSeek V3.1 Terminus
DeepSeek-V4-Flash
GPQA Diamond
79.2
89.4
Humanity’s Last Exam
15.2
32.1