Z.ai GLM Coding Plan

What the harness already knows

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:

Keys are issued by Z.ai GLM Coding Plan — where to get one.

Models on Z.ai GLM Coding Plan

The newest models Z.ai GLM Coding Plan serves that can call tools, from the models.dev snapshot OHarness ships.

List prices in USD per million tokens, read from models.dev on 2026-09-19. Z.ai GLM Coding Plan changes its prices and models; its own pricing page is the authority. Start a session on the newest:

Worth knowing

The GLM Coding Plan endpoint. A plan key is not accepted on the pay-as-you-go host zai uses, and a pay-as-you-go key is not billed against a plan here, so the two are separate entries with separate env vars — sharing ZAI_API_KEY would send one kind of key to the other's endpoint. pi-ai's zai roster is this endpoint's, so it seeds both.

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": {
    "zai-coding": {
      "baseUrl": "https://api.z.ai/api/coding/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.

All 34 providers · Install OHarness