Why can't I use GLM with Codex?

Codex CLI now requires the OpenAI Responses API; GLM doesn't offer that endpoint yet. Claude Code with GLM is unaffected.

SETUP GUIDE

How to run Claude Code with GLM 智谱

GLM (Zhipu AI) is a Tsinghua-rooted LLM family with balanced Chinese/English capability and a mature ecosystem. GLM provides an Anthropic-compatible endpoint and works with Claude Code directly.

Engine support (probe-verified, 2026-07-10)

Engine	GLM 智谱 support
Claude Code	✅ Supported (Anthropic-compatible endpoint)
Codex	— Not yet

Step 1 — Get a GLM 智谱 API key

Open open.bigmodel.cn → sign up / log in → “API Keys” under your account → create and copy.

Console: https://open.bigmodel.cn/usercenter/apikeys

Step 2 — Configure the Snail launcher (3 steps)

Download the launcher for Mac / Windows from justalittlesnail.ai;
Paste the API key on the GLM 智谱 card (the launcher validates connectivity immediately);
Pick a model and click Launch Claude Code — a dedicated terminal window opens.

Recommended models

Main: glm-5.2 (complex tasks) · Fast: glm-5-turbo (subtasks / summaries). After saving the key, click “Refresh” on the card to pull the live model list.

FAQ

Why can't I use GLM with Codex?: Codex CLI now requires the OpenAI Responses API; GLM doesn't offer that endpoint yet. Claude Code with GLM is unaffected.

Multi-window sessions, a different model in each window

Download the Snail launcher

Other guides: DeepSeek · Qwen 通义千问 · Kimi · MiMo · MiniMax · StepFun 阶跃星辰 · 百度千帆 ERNIE · Anthropic Claude 官方
 All guides (EN) · 中文版 · Home