Modal(@modal):DeepSeek v4.1-Flash, a new multimodal model from @deepseek_ai, is now available on Modal. v4.1-Flash uses DeepSeek's Causal Encoder-Decoder architecture, activating 16B parameters for input and 8B parameters for output to improve cost efficiency for input-heavy agentic workloads.

2026.09.11 18:43

DeepSeek v4.1-Flash, a new multimodal model from @deepseek_ai, is now available on Modal. v4.1-Flash uses DeepSeek's Causal Encoder-Decoder architecture, activating 16B parameters for input and 8B parameters for output to improve cost efficiency for input-heavy agentic workloads.