DeepSeek V4.1 Flash Begins Internal Testing, Directly Usable by Changing Model ID

DeepSeek has begun internal testing of the V4.1 Flash intermediate version. An official WeChat group notice stated that the new model adopts a new architecture, natively supports multimodal capabilities, and offers stronger performance, faster speed, and lower cost.

Current billing is the same as V4 Flash, with a maximum of 20 concurrent requests per account. Users can already call it directly. The base_url remains unchanged; only the original model ID needs to be replaced with deepseek-v4.1-flash-expires-on-0910.

[BlockBeats]