AI Hub
← All models

DeepSeek-V2 vs DeepSeek-V4-Flash

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

  • DeepSeek-V4-Flash has a larger context window (1M)
DeepSeek-V2DeepSeek-V4-Flash
Intelligence index89.4
DeveloperDeepSeekDeepSeek
TypeLLMLLM
AccessOpen weightsOpen weights
Context window128,000 tokens1,048,576 tokens
Input price$0.10 / 1M
Output price$0.20 / 1M
Speed109 tok/s
ReleasedMay 6, 2024April 24, 2026
Parameters236B total / 21B active (MoE)284B (13B active)
Input modalitiesTextText
Output modalitiesTextText