DeepSeek-V4-Pro-0813 is live on CoreWeave Serverless Inference. 1.6T parameters. 1M context. Built for long-horizon agent work, and priced for it: cache reads run $0.044/M for all the context your agent re-sends every step. Start here: ▻ ↧ Model on Serverless Inference Pricing, context window, capabilities, and usage examples for Model hosted on Serverless Inference.