DeepseekDeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.
QwenQwen3-Embedding-8B belongs to the proprietary Qwen3 Embedding series from Qwen, built for text embedding and ranking. It draws on the multilingual abilities, long-context comprehension, and reasoning of its base model, and improves on a range of embedding and ranking tasks, including text retrieval, code search, text classification, clustering, and bitext mining.