Zhipu (GLM)
Zhipu GLM official API. Bring your own key; nothing is billed by us.
Ta strona jest napisana po angielsku. Terminy, które wyjaśnia, są tymi, których szuka się po angielsku, a przetłumaczony termin fachowy to już inny termin.
What the harness already knows
| Provider id | zhipu |
| Base URL | https://open.bigmodel.cn/api/paas/v4 |
| Protocol | OpenAI-compatible chat completions |
| API key | ZHIPU_API_KEY or GLM_API_KEY |
| Model discovery | Yes — the model list is asked of the endpoint rather than shipped. |
Connecting it
The endpoint above is built in, so there is nothing to configure. Put the key in the environment and the provider appears in the model picker:
export ZHIPU_API_KEY="..."Keys are issued by Zhipu (GLM) — where to get one.
Worth knowing
pi-ai files the mainland GLM models under zai-coding-cn; the model ids are the same ones open.bigmodel.cn serves, so only the name needs reconciling — the endpoint above stays this entry's.
Pointing it somewhere else
A regional host, a gateway, or a server of your own. Overrides in ~/.oharness/config.json are field level, so changing the endpoint does not mean restating the rest of the provider — this is the whole block, shown holding the default so the shape is clear:
{
"providers": {
"zhipu": {
"baseUrl": "https://open.bigmodel.cn/api/paas/v4"
}
}
}What you get either way
The same agent loop, the same tools, the same MCP servers and the same permission rules, whichever provider is underneath — and switching between them mid-session converts nothing, because history is never stored in a vendor’s shape. What an agent harness is covers why that is the hard part, and the providers reference covers the catalogue itself.