DeepSeek V4-Flash-0731 Goes Live on CoreWeave's Serverless Inference

_ScottCondron · x · 2026-08-06

CoreWeave officially announced that the DeepSeek V4-Flash-0731 model is now live on its Serverless Inference platform. A developer reported that the model performs exceptionally well for extraction tasks, offering a great balance of speed and cost-efficiency, and works perfectly with NousResearch's Hermes.

Related event: DeepSeek V4 Flash API Public Beta Launches with Enhanced Agent Capabilities(8 posts)→

Original post →

More from Models

Models channel →