OpenAI C# SDK

Usage

using var api = new OpenAiApi("API_KEY");
string response = await api.Chat.CreateChatCompletionAsync(
    messages: ["Generate five random words."],
    model: ModelIdsSharedEnum.Gpt4oMini);
Console.WriteLine(response); // "apple, banana, cherry, date, elderberry"

var enumerable = api.Chat.CreateChatCompletionAsStreamAsync(
    messages: ["Generate five random words."],
    model: ModelIdsSharedEnum.Gpt4oMini);

await foreach (string response in enumerable)
{
    Console.WriteLine(response);
}

You still can use the full response objects if you need more information, just replace string response to var response.

Microsoft.Extensions.AI

The client natively implements IChatClient and IEmbeddingGenerator<string, Embedding<float>> from Microsoft.Extensions.AI, providing a unified interface across 40+ providers:

using OpenAI;
using Microsoft.Extensions.AI;

// Works with OpenAI and all CustomProviders (Azure, DeepSeek, Groq, etc.)
using var client = new OpenAiClient("API_KEY");
// or: using var client = CustomProviders.Groq("API_KEY");

// IChatClient
IChatClient chatClient = client;
var response = await chatClient.GetResponseAsync(
    "Say hello!",
    new ChatOptions { ModelId = "gpt-4o-mini" });
Console.WriteLine(response.Messages[0].Text);

// Streaming
await foreach (var update in chatClient.GetStreamingResponseAsync(
    "Count to 5.",
    new ChatOptions { ModelId = "gpt-4o-mini" }))
{
    Console.Write(string.Concat(update.Contents.OfType<TextContent>().Select(c => c.Text)));
}

// IEmbeddingGenerator
IEmbeddingGenerator<string, Embedding<float>> generator = client;
var embeddings = await generator.GenerateAsync(
    ["Hello, world!"],
    new EmbeddingGenerationOptions { ModelId = "text-embedding-3-small" });