DeepSeek-V4.1-Flash launches on SiliconFlow, with 552B MoE and support for a 1M context window
@deepseek_ai just made Flash the new Pro. 🤯 DeepSeek-V4.1-Flash is live on SiliconFlow — Day 0. 55...
AI BriefingSiliconFlow announced that DeepSeek-V4.1-Flash went live on its platform on Day 0. The model is a 552B MoE with approximately 8B active parameters during prefill and approximately 16B during decode, native vision, a 1M context window, and KV cache usage of approximately one-quarter that of V4 Flash. It uses the MIT License.
Also reported by 2 other sources
- DeepSeek releases open-source model DeepSeek-V4.1-Flash, optimizing prefill efficiency for coding agentsBaseten Engineering Blog · September 12
- DeepSeek announces that the V4 Pro API will continue to be available, canceling its originally scheduled shutdown on September 14IT Home: Artificial Intelligence · September 11
Source: SiliconFlow · x.com
Event follow-up1
View all event coverage- DeepSeek releases open-source model DeepSeek-V4.1-Flash, optimizing prefill efficiency for coding agentsBaseten Engineering Blog · September 12