Skip to content

Z.AI

The Z.AI provider uses provider key zai and the HPD-Agent.Providers.Zai package. It is backed by HPD's shared OpenAI-compatible chat-completions client, so ModelName is a Z.AI chat model id.

Set an API key:

bash
export ZAI_API_KEY="..."

The default endpoint is https://api.z.ai/api/paas/v4/, which sends chat requests to chat/completions. Pass endpoint to WithZai(...), set Endpoint in ClientProviderConfig, or use ZAI_ENDPOINT / ZAI_BASE_URL / Z_AI_ENDPOINT / Z_AI_BASE_URL / BIGMODEL_ENDPOINT / BIGMODEL_BASE_URL when you need a compatible proxy or custom base URL.

Use fluent chat setup first:

csharp
using HPD.Agent;
using HPD.Agent.Providers.Zai;

var agent = await new AgentBuilder()
    .WithZai(model: "glm-4.7")
    .BuildAsync();

var result = await agent.RunAsync("Write one sentence about Z.AI setup.");
Console.WriteLine(result.Text);

The equivalent Clients.Chat shape is:

json
{
  "Clients": {
    "Chat": {
      "ProviderKey": "zai",
      "ModelName": "glm-4.7"
    }
  }
}

Runtime Chat Options

Use ChatRunConfig for shared model-call behavior such as temperature, top-p, max output tokens, stop sequences, response format, tools, tool mode, seed, and generic reasoning options. Put agent-level defaults in ClientProviderConfig.ChatDefaults or .WithChatDefaults(...); use AgentRunConfig.Chat for per-run or per-session overrides.

Caveats

This provider targets Z.AI OpenAI-compatible APIs. BIGMODEL_API_KEY is accepted as an alias for older Zhipu/BigModel naming.

This provider currently registers the chat family only. Other endpoint families, if the upstream service exposes them, are deferred until HPD has dedicated provider-family support for that surface.

Chat uses HPD's shared OpenAI-compatible chat-completions client. It supports token streaming, function tools, response format and tool mode, seed, max output tokens, top-p, temperature, and stop sequences where the selected model supports them.

Validation checks model and endpoint configuration. Runtime chat options are applied through ChatDefaults and AgentRunConfig.Chat. Missing credentials fail at BuildAsync() before a live provider call.

Built for production .NET agent applications.