Frameworks & Platforms
Semantic Kernel
Connect Microsoft Semantic Kernel to TokenLab with a custom OpenAI-compatible endpoint
Overview
Semantic Kernel can call TokenLab through its OpenAI custom endpoint chat completion service.
Environment
export TOKENLAB_API_KEY="sk-your-tokenlab-key".NET Kernel Builder
Semantic Kernel's custom endpoint should point to the root OpenAI-compatible /v1 endpoint, not /v1/chat/completions.
using Microsoft.SemanticKernel;
#pragma warning disable SKEXP0010
var builder = Kernel.CreateBuilder();
builder.AddOpenAIChatCompletion(
modelId: "gpt-5.6-luna",
endpoint: new Uri("https://api.tokenlab.sh/v1"),
apiKey: Environment.GetEnvironmentVariable("TOKENLAB_API_KEY"));
var kernel = builder.Build();Basic Prompt
var result = await kernel.InvokePromptAsync(
"Give me a concise checklist for evaluating an LLM gateway.");
Console.WriteLine(result);Endpoint Notes
Use:
https://api.tokenlab.sh/v1Do not use:
https://api.tokenlab.sh/v1/chat/completionsSemantic Kernel adds the chat completions path automatically for this connector.