DeepSeek-V4-Pro launches on CoreWeave with 1.6T params, 1M context

wandb · x · 2026-09-02

DeepSeek-V4-Pro-0813 is live on CoreWeave Serverless Inference. Featuring 1.6T parameters and a 1M context window, it is built for long-horizon agent work. Cache reads are priced at $0.044/M, optimizing for the context agents resend at every step.

Original post →

More from Infra

Infra channel →