DeepSeek V4 in the wild, and how to run it on Runpod | Runpod Blog

DeepSeek's V4 preview landed on April 24, 2026 with two MoE models: V4-Pro (1.6T total / 49B active) and V4-Flash (284B / 13B active), with both shippingunder MIT license with a 1M-token context window, with real-world inference costs that pound for pound undercut every frontier lab by roughly an order of magnitude. Two days in, the practitioner verdict is more interesting than the marketing: V4 is not the "Sputnik moment" R1 was, but it is the cheapest credible alternative to Claude Opus and GPT-5.5 that anyone has shipped thus far, and a specific set of use cases is already making it indispensable. This guide walks through what people are actually doing with it, where it falls down, and exactly how to stand it up on Runpod with vLLM or SGLang.