← all releases
DeepSeek AI·Apr 24, 2026·V4-Flash·paid
DeepSeek-V4-Flash
DeepSeek-V4-Flash is a Mixture-of-Experts (MoE) language model developed by DeepSeek-AI, featuring 284 billion total parameters with 13 billion activated, and supporting a context length of one million tokens. It offers advanced capabilities in text generation and conversational AI, optimized for efficiency and scalability.
DeepSeek-V4-FlashDeepSeek-AIlanguage modelAI researchDeepSeek FlashDeepSeekDeepseek AI
overview
DeepSeek-V4-Flash is a Mixture-of-Experts (MoE) language model developed by DeepSeek-AI, featuring 284 billion total parameters with 13 billion activated, and supporting a context length of one million tokens. It offers advanced capabilities in text generation and conversational AI, optimized for efficiency and scalability.
key features
- 01284 billion total parameters with 13 billion activated
- 02Supports a context length of one million tokens
- 03Optimized for efficiency and scalability
- 04Advanced capabilities in text generation and conversational AI
- 05Innovative Mixture-of-Experts (MoE) architecture
related productsbrowse all →