KUAE Cloud Coding Plan API
An LLM inference endpoint operated on Moore Threads MTT S5000 GPUs and sold as a subscription for AI coding tools. It speaks two wire protocols from one host — the Anthropic Messages protocol at the root (used by Claude Code) and the OpenAI Chat Completions protocol at /v1 (used by Cline, Cursor, Roo Code, Kilo Code and OpenCode) — serving the GLM-4.7 model. Authenticated with an API key created in the KUAE Cloud console.