DeepSeek said the new model is designed for greater capability, faster inference, higher throughput and scaling to larger models.

DeepSeek has begun a limited-time beta of V4.1 Flash, an interim model that uses a new architecture and natively supports multimodal capabilities.

DeepSeek V4.1 Flash: The Native Multimodal Model That's Breaking Speed Records ...

DeepSeek launches V4.1-Flash, its smallest model in a new architecture family, as the Chinese AI startup prepares for a Shanghai STAR Market IPO.