LLM Gateway
DeepSeek announced DeepSeek-V4.1-Flash, the smallest model in its new architecture family, with native visual understanding and a 552B-parameter mixture-of-experts design using a new causal encoder-decoder architecture with 8B active parameters for input and 16B for output. New pretraining methods and larger-scale RL post-training deliver benchmark results ahead of flagship models including DeepSeek-V4-Pro, and the KV cache needs only one quarter the HBM and one eighth the SSD storage of the previous generation. The model is live on the DeepSeek API as deepseek-flash with native multimodal support, and DeepSeek states that V4-Flash and V4-Flash-Vision-Exp are retired, with deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily routing to V4.1-Flash. From 04:00 UTC on September 14, 2026, all deepseek-v4-pro requests route to V4.1-Flash at V4.1-Flash rates until V4.1-Pro launches, and off-peak pricing runs at 50% of peak rates.