Z.ai GLM
Use GLM in your coding tools
Step-by-step setup for GLM in 11 coding tools: Aider, Claude Code, Cline, Codex CLI, Continue, Cursor, Goose, Kilo Code, OpenCode, Roo Code and Zed. Every step comes from official docs, read on .
GLM setup guides
- From GLM and Aider docsUse GLM in AiderAider documents connecting to any OpenAI-compatible endpoint via OPENAI_API_BASE and OPENAI_API_KEY with an openai/ model prefix; combined with Z.ai's documented standard API endpoint https://api.z.ai/api/paas/v4 and model id glm-5.3.api.z.ai4 steps
- Documented by GLMUse GLM in Claude CodeZ.ai documents pointing Claude Code at its Anthropic-compatible endpoint (https://api.z.ai/api/anthropic) by setting env vars in ~/.claude/settings.json, and mapping Claude Code's Opus/Sonnet/Haiku slots to GLM-5.3 and GLM-5.3-Flash with a [1m] suffix for 1M context.api.z.ai6 steps
- Documented by GLMUse GLM in ClineZ.ai documents using GLM in Cline through the OpenAI Compatible provider with base URL https://api.z.ai/api/coding/paas/v4 and a custom model id such as glm-5.3 or glm-5.3-flash.api.z.ai5 steps
- Documented by GLMUse GLM in Codex CLIZ.ai documents running Codex CLI (and the Codex app) on GLM-5.3 via its dedicated OpenAI Responses endpoint https://api.z.ai/api/v1, using a ~/.codex/models.json model catalog plus a custom model_providers.ZAI block in ~/.codex/config.toml.api.z.ai6 steps
- Documented by ContinueUse GLM in ContinueContinue's docs document a built-in zAI provider in config.yaml, defaulting to Z.ai's standard API base https://api.z.ai/api/paas/v4/, with an optional apiBase override for the Coding Plan endpoint.api.z.ai3 steps
- Documented by GLMUse GLM in CursorZ.ai documents adding GLM to Cursor as a custom OpenAI-protocol model by overriding the OpenAI Base URL with https://api.z.ai/api/coding/paas/v4 and entering the model name in uppercase.api.z.ai4 steps
- From GLM and Goose docsUse GLM in GooseGoose's docs document a built-in Z.AI Coding Plan provider (zai_coding_plan, OpenAI-compatible endpoint), and Z.ai's docs document an Anthropic Compatible custom provider pointed at https://api.z.ai/api/anthropic.api.z.ai4 steps
- Documented by GLMUse GLM in Kilo CodeZ.ai documents using Kilo Code's built-in Z AI provider with the International Coding Plan entrypoint and your Z.AI API key.api.z.ai4 steps
- From GLM and OpenCode docsUse GLM in OpenCodeOpenCode ships built-in Z.AI and Z.AI Coding Plan providers. Both Z.ai's docs and OpenCode's provider docs document selecting Z.AI Coding Plan, pasting the API key, and picking a GLM model with /models.api.z.ai4 steps
- From GLM and Roo Code docsUse GLM in Roo CodeRoo Code has a built-in Z AI provider. Z.ai documents selecting it with the International Coding Plan entrypoint; Roo Code's docs document the Z AI provider with region-based endpoints and an auto-fetched model list.api.z.ai4 steps
- From GLM and Zed docsUse GLM in ZedZed documents custom OpenAI-compatible providers under language_models.openai_compatible (with a key read from <PROVIDER_ID>_API_KEY); combined with Z.ai's documented standard endpoint https://api.z.ai/api/paas/v4 and GLM-5.3 (1M context, 128K max output).api.z.ai3 steps
No verified GLM guide yet for GitHub Copilot. We only publish a pairing once official docs cover it.
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.