xAI
The xAI provider uses provider key xai and the HPD-Agent.Providers.Xai package. It is backed by the shared OpenAI-compatible chat-completions client, so ModelName is an xAI chat model id such as grok-4.3.
Set an API key:
export XAI_API_KEY="..."The default endpoint is https://api.x.ai/v1/. Pass endpoint to WithXai(...), set Endpoint in ChatClientConfig, or use XAI_ENDPOINT/XAI_BASE_URL when you need a compatible proxy or custom xAI base URL.
Use fluent chat setup first:
using HPD.Agent;
using HPD.Agent.Providers.Xai;
var agent = await new AgentBuilder()
.WithXai(model: "grok-4.3")
.BuildAsync();
var result = await agent.RunAsync("Write one sentence about xAI setup.");
Console.WriteLine(result.Text);The equivalent Clients.Chat shape is:
{
"Clients": {
"Chat": {
"ProviderKey": "xai",
"ModelName": "grok-4.3"
}
}
}Runtime Chat Options
Use ChatClientConfig 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 AgentConfig.Clients.Chat; use AgentRunConfig.Clients.Chat for complete per-run replacements.
ResponseFormat accepts text or json_object. Per-run HPD chat options can supply JSON schema response format and tool declarations where the model supports them.
Caveats
This package currently registers only the chat family. xAI image generation, image editing, embeddings, audio, realtime voice, files, batches, and deferred completions are deferred until those families have dedicated HPD provider support.
Runtime validation checks model and endpoint configuration. Runtime chat options are applied through Clients.Chat and AgentRunConfig.Clients.Chat. Credentials are resolved lazily when a run first acquires this provider client; a missing credential fails that run, not BuildAsync().