New Feature: docs example for PZERO OpenAI-compatible endpoint

[cursor]

Semantic Kernel's OpenAI connector already talks to any OpenAI-compatible host by passing a custom endpoint. People looking for prepaid, privacy-first inference still have to guess the host, key format, and that the endpoint is the /v1 root.

A named PZERO example in the OpenAI connector docs would let users paste and run. No first-party SK connector required. Search for pzero returned none.

using Microsoft.SemanticKernel;

var builder = Kernel.CreateBuilder();
builder.AddOpenAIChatCompletion(
    modelId: "deepseek-v4-flash",
    endpoint: new Uri("https://api.pzero.studio/v1"),
    apiKey: Environment.GetEnvironmentVariable("PZERO_API_KEY")!
);
var kernel = builder.Build();

Endpoint is the /v1 root, not /v1/chat/completions. Pass the catalog id as-is.

Get a key: https://pzero.studio/agents (sign-in free; min top-up 1 USDC on Base; no starter credits). Live text ids: GET https://api.pzero.studio/v1/models (public, no key). Default landing model: deepseek-v4-flash.

Smoke against the same host SK will call:

curl -sS -X POST "https://api.pzero.studio/v1/chat/completions" \
  -H "Authorization: Bearer $PZERO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello from PZERO"}],"stream":false}'

I am not asking for a bundled AddPzeroChatCompletion. The existing OpenAI connector seam is enough. Do not start implementation on my behalf until the board says Ready; the snippet is for users today.

Every AI Credit is at least 20% off $1 list. Usage is paid.