DeepSeek launches V4.1-Flash with native multimodal support, phasing out V4-Pro

Key Info

DeepSeek has released V4.1-Flash on its API with native multimodal support, replacing V4-Flash models and positioned ahead of V4-Pro on performance, cost, speed and total runtime.

Highlights

• Set your API model to deepseek-flash to use V4.1-Flash; the legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily route to the new model for compatibility.
• V4-Flash and V4-Flash-Vision-Exp are retired, and V4-Pro is being phased out: from Sept 14, 2026 at 04:00 UTC, all deepseek-v4-pro requests will route to V4.1-Flash.