Explore index
DeepSeek-V4-Flash
An efficiency-optimized Mixture-of-Experts (MoE) model by DeepSeek, featuring 284B total and 13B active parameters, supporting a 1M context window, and tailored for high throughput, low latency, and agentic workflows.
Explore index
An efficiency-optimized Mixture-of-Experts (MoE) model by DeepSeek, featuring 284B total and 13B active parameters, supporting a 1M context window, and tailored for high throughput, low latency, and agentic workflows.