Setup guide - From GLM and Goose docs
Use GLM in Goose
Goose'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.
Last verified 4 steps3 official sources
Steps
- Step 1.
Install Goose Desktop or CLI from the Goose quickstart.
- Step 2.
Option A (Goose docs, built-in provider): in Goose Desktop open Settings > Models, choose Z.AI Coding Plan, and enter your Coding Plan API key. In the CLI, select Z.AI Coding Plan in goose configure, or set these env vars.
TerminalGOOSE_PROVIDER=zai_coding_plan GOOSE_MODEL=glm-5.3 ZAI_CODING_PLAN_API_KEY=<your Coding Plan API key> - Step 3.
Option B (Z.ai docs, custom provider): in Goose Desktop click Create New Provider, select Anthropic Compatible, and set Base URL, API Key (your Z.ai key) and Model (the GLM model code). Save.
Snippethttps://api.z.ai/api/anthropic - Step 4.
Click Switch Models at the bottom of the main screen and select the new provider.
Caveats
- Goose docs: the Z.AI Coding Plan provider uses https://api.z.ai/api/coding/paas/v4 and falls back to GLM-5.3 and GLM-5.3-Flash when model discovery is unsupported; the existing Z.AI provider uses the Anthropic-compatible endpoint.
- Z.ai's Goose page documents the Anthropic Compatible custom-provider route at https://api.z.ai/api/anthropic instead; both are official.
- The value <your Coding Plan API key> is a placeholder; Goose docs do not give a literal example value.
- Coding Plan and Standard keys are separate since 2026-10-16.
More setup guides
Same tool, other providers
Related reading
- Anthropic's GLM-5.3 Cyber Report: The Numbers, the Backlash, and What Developers Should Take From ItAnthropic's GLM-5.3 cyber report: exploit numbers against Claude Mythos Preview, how its safeguards were stripped, the backlash, and the read for developers.
- GLM-5.3 Free and Cheap: Every Route and Price (October 2026)GLM-5.3 has no free hosted tier. Cheapest on October 9: Wafer via OpenRouter at $0.049/$3.39, Flash from $0.075/$0.25. Z.ai's promos ended October 7.
- Prime Agent: A Self-Improving Coding Harness Where Everything Is PythonPrime Agent is Prime Intellect's open-source coding harness with one tool, a persistent IPython kernel. How it works, its benchmarks, and Claude Code compared.
- Cloudflare Runs Kimi and GLM at Scale: FP8 KV Caches, INT4 Weights, and a Cache Safety NetCloudflare runs Kimi K2.6 and GLM 5.2 on Workers AI with FP8 KV caches, INT4 weights and a KV cache integrity check. What each technique buys on GPU fleets.
- Colibri: Run GLM 5.2 on a 32GB Laptop With Disk StreamingA solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.
- GLM 5.2 Matches Human Bookkeeper Accuracy on UK VAT Returns - With Some CaveatsGLM 5.2 UK VAT return benchmark: how the model handled 59 transactions with near-human bookkeeper accuracy, where it erred, and why HN focused on liability.
FAQ
How do I use GLM in Goose?
Goose'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.
Which GLM model ids work in Goose?
The official docs read for this guide list glm-5.3 and glm-5.3-flash. Requests go to https://api.z.ai/api/coding/paas/v4.
Is this an official GLM and Goose setup?
The steps draw on both GLM's and Goose's docs. It was last checked against 3 official pages on October 17, 2026.
Sources
Last verified against 3 official pages.
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.