告诉 HN：使用 Claude Code 搭配 GLM 4.5 出现故障
1 分•作者: prmph•9 个月前
这很奇怪，我用 Claude Code (CC) 搭配 Z.ai 的 GLM 4.5，仅仅是启动 CC 并让它阅读规范和指南文件，就花了 5 美元。而这个 API 的标价是输入 0.6 美元/百万 tokens，输出 2.2 美元/百万 tokens。
然后，我注意到在最初的提示之后，我给 CC 的任何进一步提示（除了批准它的操作）都完全不起作用。是的，任何提示都被完全忽略了。我必须停止 CC 并用新的提示重新启动它才能生效。
这对我来说真的很奇怪。CC 是否有某种方式来检测它是否在与 Anthropic 之外的 API 交互？如此高昂的成本和/或 tokens 使用量以及受限的 agentic 模式，显然不是因为 GLM 4.5 能力不足。要么是 CC 在使用第三方 API 时以某种方式被限制了，要么是 Z.ai 的 API 在某种程度上没有正常工作。
查看原文
It's weird, but using Claude Code (CC) with GLM 4.5 from Z.ai, I spent $5 just starting CC and asking it to read the spec and guideline files. This on an API that advertises $0.6 per million tokens input, and $2.2 per million tokens output.<p>Then, I noticed that after the original prompt, any further prompt I gave CC (other that approving its actions) did not have any effect at all on it. Yes, any prompt is totally ignored. I have to stop CC and restart with the new prompt for it to take effect.<p>This is really strange to me. Does CC have some way of detecting when it is running against an API other than Anthropic's? The massive cost and/or token usage and crippled agentic mode is clearly not due to GLM 4.5 not being capable. Either CC is crippled in some way when using a 3rd party API, or else Z.ai's API is somehow not working properly.