This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Tim Duffy
timfduffy.com
did:plc:mk7qlghvwdjjayu5x3bo3lx2
The very low cached token cost might be mostly about the KV cache size relative to V3, it uses almost an order of magnitude less per token. https://vllm.ai/blog/2026-04-24-deepseek-v4
2026-05-22T17:33:58.175Z