# DeepSeek AI

## Models

- [deepseek-v4.1-flash](/qc69jvmznzxy/deepseek-v4.1-flash.md) — 552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache
- [deepseek-v4.1-flash](/qc69jvmznzxy/deepseek-v4.1-flash.md) — 552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache