We got DeepSeek-V4-Pro serving in 20 seconds

Inferize announced DeepSeek-V4-Pro, claiming it can serve the model in 20 seconds with highly optimized, elastic AI inference. The company is building fast, efficient LLM serving that scales with demand and has opened a waitlist for early access.

Inferize: Highly Optimized, Elastic AI Inference Inferize is building highly optimized, elastic inference for AI workloads. Ridiculously fast, efficient LLM serving that scales with demand. Join the waitlist to be first to know when we launch. Inferize on X @InferizeAI