Models

← All models

DeepSeek V4.1 Flash

DeepSeek · 2026-09-10

DeepSeek V4.1 Flash is DeepSeek's September 2026 multimodal mixture-of-experts model, using a causal encoder-decoder architecture and compressed sparse attention. It natively accepts text and images, generates text, and supports numeric reasoning effort from 1 to 100; the API serves it through deepseek-flash.

Benchmark scores