OpenAI 1.11.0

There is a newer prerelease version of this package available.
See the version list below for details.
dotnet add package OpenAI --version 1.11.0
NuGet\Install-Package OpenAI -Version 1.11.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="OpenAI" Version="1.11.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add OpenAI --version 1.11.0
#r "nuget: OpenAI, 1.11.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
// Install OpenAI as a Cake Addin
#addin nuget:?package=OpenAI&version=1.11.0

// Install OpenAI as a Cake Tool
#tool nuget:?package=OpenAI&version=1.11.0

C#/.NET SDK for accessing the OpenAI APIs, including GPT-3.5/4, GPT-3.5/4-Turbo, and DALL-E 2/3

A simple C# .NET wrapper library to use with OpenAI's API. More context on my blog. This is an unofficial wrapper library around the OpenAI API. I am not affiliated with OpenAI and this library is not endorsed or supported by them.

Quick Example

var api = new OpenAI_API.OpenAIAPI("YOUR_API_KEY");
var result = await api.Chat.CreateChatCompletionAsync("Hello!");
// should print something like "Hi! How can I help you?"




Adds new embedding models as of March 2024.


This library is based on .NET Standard 2.0, so it should work across all versions of .Net, from the traditional .NET Framework >=4.7.2 to .NET (Core) >= 3.0. It should work across console apps, winforms, wpf,, unity, Xamarin, etc. It should work across Windows, Linux, and Mac, and possibly even mobile. There are minimal dependencies, and it's licensed in the public domain.

Getting started

Install from NuGet

Install package OpenAI from Nuget. Here's how via commandline:

Install-Package OpenAI


There are 3 ways to provide your API keys, in order of precedence:

  1. Pass keys directly to APIAuthentication(string key) constructor
  2. Set environment var for OPENAI_API_KEY (or OPENAI_KEY for backwards compatibility)
  3. Include a config file in the local directory or in your user directory named .openai and containing the line:

You use the APIAuthentication when you initialize the API as shown:

// for example
OpenAIAPI api = new OpenAIAPI("YOUR_API_KEY"); // shorthand
// or
OpenAIAPI api = new OpenAIAPI(new APIAuthentication("YOUR_API_KEY")); // create object manually
// or
OpenAIAPI api = new OpenAIAPI(APIAuthentication LoadFromEnv()); // use env vars
// or
OpenAIAPI api = new OpenAIAPI(APIAuthentication LoadFromPath()); // use config file (can optionally specify where to look)
// or
OpenAIAPI api = new OpenAIAPI(); // uses default, env, or config file

You may optionally include an openAIOrganization (OPENAI_ORGANIZATION in env or config file) specifying which organization is used for an API request. Usage from these API requests will count against the specified organization's subscription quota. Organization IDs can be found on your Organization settings page.

// for example
OpenAIAPI api = new OpenAIAPI(new APIAuthentication("YOUR_API_KEY","org-yourOrgHere"));

Chat API

The Chat API is accessed via OpenAIAPI.Chat. There are two ways to use the Chat Endpoint, either via simplified conversations or with the full Request/Response methods.

Chat Conversations

The Conversation Class allows you to easily interact with ChatGPT by adding messages to a chat and asking ChatGPT to reply.

var chat = api.Chat.CreateConversation();
chat.Model = Model.GPT4_Turbo;
chat.RequestParameters.Temperature = 0;

/// give instruction as System
chat.AppendSystemMessage("You are a teacher who helps children understand if things are animals or not.  If the user tells you an animal, you say \"yes\".  If the user tells you something that is not an animal, you say \"no\".  You only ever respond with \"yes\" or \"no\".  You do not say anything else.");

// give a few examples as user and assistant
chat.AppendUserInput("Is this an animal? Cat");
chat.AppendUserInput("Is this an animal? House");

// now let's ask it a question
chat.AppendUserInput("Is this an animal? Dog");
// and get the response
string response = await chat.GetResponseFromChatbotAsync();
Console.WriteLine(response); // "Yes"

// and continue the conversation by asking another
chat.AppendUserInput("Is this an animal? Chair");
// and get another response
response = await chat.GetResponseFromChatbotAsync();
Console.WriteLine(response); // "No"

// the entire chat history is available in chat.Messages
foreach (ChatMessage msg in chat.Messages)
	Console.WriteLine($"{msg.Role}: {msg.Content}");
Chat Streaming

Streaming allows you to get results are they are generated, which can help your application feel more responsive.

Using the new C# 8.0 async iterators:

var chat = api.Chat.CreateConversation();
chat.AppendUserInput("How to make a hamburger?");

await foreach (var res in chat.StreamResponseEnumerableFromChatbotAsync())

Or if using classic .NET Framework or C# <8.0:

var chat = api.Chat.CreateConversation();
chat.AppendUserInput("How to make a hamburger?");

await chat.StreamResponseFromChatbotAsync(res =>
GPT Vision

You can send images to the chat to use the new GPT-4 Vision model. This only works with the Model.GPT4_Vision model. Please see for more information and limitations.

// the simplest form
var result = await api.Chat.CreateChatCompletionAsync("What is the primary non-white color in this logo?", ImageInput.FromFile("path/to/logo.png"));

// or in a conversation
var chat = api.Chat.CreateConversation();
chat.Model = Model.GPT4_Vision;
chat.AppendSystemMessage("You are a graphic design assistant who helps identify colors.");
chat.AppendUserInput("What are the primary non-white colors in this logo?", ImageInput.FromFile("path/to/logo.png"));
string response = await chat.GetResponseFromChatbotAsync();
Console.WriteLine(response); // "Blue and purple"
chat.AppendUserInput("What are the primary non-white colors in this logo?", ImageInput.FromImageUrl(""));
response = await chat.GetResponseFromChatbotAsync();
Console.WriteLine(response); // "Blue, red, and yellow"

// or when manually creating the ChatMessage
messageWithImage = new ChatMessage(ChatMessageRole.User, "What colors do these logos have in common?");

// you can specify multiple images at once
chat.AppendUserInput("What colors do these logos have in common?", ImageInput.FromFile("path/to/logo.png"), ImageInput.FromImageUrl(""));
Conversation History Context Length Management

If the chat conversation history gets too long, it may not fit into the context length of the model. By default, the earliest non-system message(s) will be removed from the chat history and the API call will be retried. You may disable this by setting chat.AutoTruncateOnContextLengthExceeded = false, or you can override the truncation algorithm like this:

chat.OnTruncationNeeded += (sender, args) =>
	// args is a List<ChatMessage> with the current chat history.  Remove or edit as nessisary.
	// replace this with more sophisticated logic for your use-case, such as summarizing the chat history
	for (int i = 0; i < args.Count; i++)
		if (args[i].Role != ChatMessageRole.System)

You may also wish to use a new model with a larger context length. You can do this by setting chat.Model = Model.GPT4_Turbo or chat.Model = Model.ChatGPTTurbo_16k, etc.

You can see token usage via chat.MostRecentApiResult.Usage.PromptTokens and related properties.

Chat Endpoint Requests

You can access full control of the Chat API by using the OpenAIAPI.Chat.CreateChatCompletionAsync() and related methods.

async Task<ChatResult> CreateChatCompletionAsync(ChatRequest request);

// for example
var result = await api.Chat.CreateChatCompletionAsync(new ChatRequest()
		Model = Model.ChatGPTTurbo,
		Temperature = 0.1,
		MaxTokens = 50,
		Messages = new ChatMessage[] {
			new ChatMessage(ChatMessageRole.User, "Hello!")
// or
var result = api.Chat.CreateChatCompletionAsync("Hello!");

var reply = results.Choices[0].Message;
Console.WriteLine($"{reply.Role}: {reply.Content.Trim()}");
// or

It returns a ChatResult which is mostly metadata, so use its .ToString() method to get the text if all you want is assistant's reply text.

There's also an async streaming API which works similarly to the Completions endpoint streaming results.


With the new Model.GPT4_Turbo or gpt-3.5-turbo-1106 models, you can set the ChatRequest.ResponseFormat to ChatRequest.ResponseFormats.JsonObject to enable JSON mode. When JSON mode is enabled, the model is constrained to only generate strings that parse into valid JSON object. See for more details.

ChatRequest chatRequest = new ChatRequest()
	Model = model,
	Temperature = 0.0,
	MaxTokens = 500,
	ResponseFormat = ChatRequest.ResponseFormats.JsonObject,
	Messages = new ChatMessage[] {
		new ChatMessage(ChatMessageRole.System, "You are a helpful assistant designed to output JSON."),
		new ChatMessage(ChatMessageRole.User, "Who won the world series in 2020?  Return JSON of a 'wins' dictionary with the year as the numeric key and the winning team as the string value.")

var results = await api.Chat.CreateChatCompletionAsync(chatRequest);
/* prints:
  "wins": {
	2020: "Los Angeles Dodgers"

Completions API

Completions are considered legacy by OpenAI. The Completion API is accessed via OpenAIAPI.Completions:

async Task<CompletionResult> CreateCompletionAsync(CompletionRequest request);

// for example
var result = await api.Completions.CreateCompletionAsync(new CompletionRequest("One Two Three One Two", model: Model.CurieText, temperature: 0.1));
// or
var result = await api.Completions.CreateCompletionAsync("One Two Three One Two", temperature: 0.1);
// or other convenience overloads

You can create your CompletionRequest ahead of time or use one of the helper overloads for convenience. It returns a CompletionResult which is mostly metadata, so use its .ToString() method to get the text if all you want is the completion.


Streaming allows you to get results are they are generated, which can help your application feel more responsive, especially on slow models like Davinci.

Using the new C# 8.0 async iterators:

IAsyncEnumerable<CompletionResult> StreamCompletionEnumerableAsync(CompletionRequest request);

// for example
await foreach (var token in api.Completions.StreamCompletionEnumerableAsync(new CompletionRequest("My name is Roger and I am a principal software engineer at Salesforce.  This is my resume:", Model.DavinciText, 200, 0.5, presencePenalty: 0.1, frequencyPenalty: 0.1)))

Or if using classic .NET framework or C# <8.0:

async Task StreamCompletionAsync(CompletionRequest request, Action<CompletionResult> resultHandler);

// for example
await api.Completions.StreamCompletionAsync(
	new CompletionRequest("My name is Roger and I am a principal software engineer at Salesforce.  This is my resume:", Model.DavinciText, 200, 0.5, presencePenalty: 0.1, frequencyPenalty: 0.1),
	res => ResumeTextbox.Text += res.ToString());


The Audio API's are Text to Speech, Transcription (speech to text), and Translation (non-English speech to English text).

Text to Speech (TTS)

The TTS API is accessed via OpenAIAPI.TextToSpeech:

await api.TextToSpeech.SaveSpeechToFileAsync("Hello, brave new world!  This is a test.", outputPath);
// You can open it in the defaul audio player like this:

You can also specify all of the request parameters with a TextToSpeechRequest object:

var request = new TextToSpeechRequest()
	Input = "Hello, brave new world!  This is a test.",
	ResponseFormat = ResponseFormats.AAC,
	Model = Model.TTS_HD,
	Voice = Voices.Nova,
	Speed = 0.9
await api.TextToSpeech.SaveSpeechToFileAsync(request, "test.aac");

Instead of saving to a file, you can get audio byte stream with api.TextToSpeech.GetSpeechAsStreamAsync(request):

using (Stream result = await api.TextToSpeech.GetSpeechAsStreamAsync("Hello, brave new world!", Voices.Fable))
using (StreamReader reader = new StreamReader(result))
	// do something with the audio stream here
Transcription (Speech to Text)

The Audio Transcription API allows you to generate text from audio, in any of the supported languages. It is accessed via OpenAIAPI.Transcriptions:

string resultText = await api.Transcriptions.GetTextAsync("path/to/file.mp3");

You can ask for verbose results, which will give you segment and token-level information, as well as the standard OpenAI metadata such as processing time:

AudioResultVerbose result = await api.Transcriptions.GetWithDetailsAsync("path/to/file.m4a");
Console.WriteLine(result.ProcessingTime.TotalMilliseconds); // 496ms
Console.WriteLine(result.text); // "Hello, this is a test of the transcription function."
Console.WriteLine(result.language); // "english"
Console.WriteLine(result.segments[0].no_speech_prob); // 0.03712
// etc

You can also ask for results in SRT or VTT format, which is useful for generating subtitles for videos:

string result = await api.Transcriptions.GetAsFormatAsync("path/to/file.m4a", AudioRequest.ResponseFormats.SRT);

Additional parameters such as temperature, prompt, language, etc can be specified either per-request or as a default:

// inline
result = await api.Transcriptions.GetTextAsync("conversation.mp3", "en", "This is a transcript of a conversation between a medical doctor and her patient: ", 0.3);

// set defaults
api.Transcriptions.DefaultTranscriptionRequestArgs.Language = "en";

Instead of providing a local file on disk, you can provide a stream of audio bytes. This can be useful for streaming audio from the microphone or another source without having to first write to disk. Please not you must specify a filename, which does not have to exist, but which must have an accurate extension for the type of audio that you are sending. OpenAI uses the filename extension to determine what format your audio stream is in.

using (var audioStream = File.OpenRead("path-here.mp3"))
	return await api.Transcriptions.GetTextAsync(audioStream, "file.mp3");
Translations (Non-English Speech to English Text)

Translations allow you to transcribe text from any of the supported languages to English. OpenAI does not support translating into any other language, only English. It is accessed via OpenAIAPI.Translations. It supports all of the same functionality as the Transcriptions.

string result = await api.Translations.GetTextAsync("chinese-example.m4a");


The Embedding API is accessed via OpenAIAPI.Embeddings:

async Task<EmbeddingResult> CreateEmbeddingAsync(EmbeddingRequest request);

// for example
var result = await api.Embeddings.CreateEmbeddingAsync(new EmbeddingRequest("A test text for embedding", model: Model.AdaTextEmbedding));
// or
var result = await api.Embeddings.CreateEmbeddingAsync("A test text for embedding");

The embedding result contains a lot of metadata, the actual vector of floats is in result.Data[].Embedding.

For simplicity, you can directly ask for the vector of floats and disgard the extra metadata with api.Embeddings.GetEmbeddingsAsync("test text here")


The Moderation API is accessed via OpenAIAPI.Moderation:

async Task<ModerationResult> CreateEmbeddingAsync(ModerationRequest request);

// for example
var result = await api.Moderation.CallModerationAsync(new ModerationRequest("A test text for moderating", Model.TextModerationLatest));
// or
var result = await api.Moderation.CallModerationAsync("A test text for moderating");


The results are in .results[0] and have nice helper methods like FlaggedCategories and MainContentFlag.

Files (for fine-tuning)

The Files API endpoint is accessed via OpenAIAPI.Files:

// uploading
async Task<File> UploadFileAsync(string filePath, string purpose = "fine-tune");

// for example
var response = await api.Files.UploadFileAsync("fine-tuning-data.jsonl");
Console.Write(response.Id); //the id of the uploaded file

// listing
async Task<List<File>> GetFilesAsync();

// for example
var response = await api.Files.GetFilesAsync();
foreach (var file in response)

There are also methods to get file contents, delete a file, etc.

The fine-tuning endpoint itself has not yet been implemented, but will be added soon.


The DALL-E Image Generation API is accessed via OpenAIAPI.ImageGenerations:

async Task<ImageResult> CreateImageAsync(ImageGenerationRequest request);

// for example
var result = await api.ImageGenerations.CreateImageAsync(new ImageGenerationRequest("A drawing of a computer writing a test", 1, ImageSize._512));
// or
var result = await api.ImageGenerations.CreateImageAsync("A drawing of a computer writing a test");


The image result contains a URL for an online image or a base64-encoded image, depending on the ImageGenerationRequest.ResponseFormat (url is the default).


Use DALL-E 3 like this:

async Task<ImageResult> CreateImageAsync(ImageGenerationRequest request);

// for example
var result = await api.ImageGenerations.CreateImageAsync(new ImageGenerationRequest("A drawing of a computer writing a test", OpenAI_API.Models.Model.DALLE3, ImageSize._1024x1792, "hd"));
// or
var result = await api.ImageGenerations.CreateImageAsync("A drawing of a computer writing a test", OpenAI_API.Models.Model.DALLE3);



For using the Azure OpenAI Service, you need to specify the name of your Azure OpenAI resource as well as your model deployment id.

I do not have access to the Microsoft Azure OpenAI service, so I am unable to test this functionality. If you have access and can test, please submit an issue describing your results. A PR with integration tests would also be greatly appreciated. Specifically, it is unclear to me that specifying models works the same way with Azure.

Refer the Azure OpenAI documentation and detailed screenshots in #64 for further information.

Configuration should look something like this for the Azure service:

OpenAIAPI api = OpenAIAPI.ForAzure("YourResourceName", "deploymentId", "api-key");
api.ApiVersion = "2023-03-15-preview"; // needed to access chat endpoint on Azure

You may then use the api object like normal. You may also specify the APIAuthentication is any of the other ways listed in the Authentication section above. Currently this library only supports the api-key flow, not the AD-Flow.

As of April 2, 2023, you need to manually select api version 2023-03-15-preview as shown above to access the chat endpoint on Azure. Once this is out of preview I will update the default.


You may specify an IHttpClientFactory to be used for HTTP requests, which allows for tweaking http request properties, connection pooling, and mocking. Details in #103.

OpenAIAPI api = new OpenAIAPI();
api.HttpClientFactory = myIHttpClientFactoryObject;


Every single class, method, and property has extensive XML documentation, so it should show up automatically in IntelliSense. That combined with the official OpenAI documentation should be enough to get started. Feel free to open an issue here if you have any questions. Better documentation may come later.


CC-0 Public Domain

This library is licensed CC-0, in the public domain. You can use it for whatever you want, publicly or privately, without worrying about permission or licensing or whatever. It's just a wrapper around the OpenAI API, so you still need to get access to OpenAI from them directly. I am not affiliated with OpenAI and this library is not endorsed by them, I just have beta access and wanted to make a C# library to access it more easily. Hopefully others find this useful as well. Feel free to open a PR if there's anything you want to contribute.

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 was computed.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 was computed.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
.NET Core netcoreapp2.0 was computed.  netcoreapp2.1 was computed.  netcoreapp2.2 was computed.  netcoreapp3.0 was computed.  netcoreapp3.1 was computed. 
.NET Standard netstandard2.0 is compatible.  netstandard2.1 was computed. 
.NET Framework net461 was computed.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
MonoAndroid monoandroid was computed. 
MonoMac monomac was computed. 
MonoTouch monotouch was computed. 
Tizen tizen40 was computed.  tizen60 was computed. 
Xamarin.iOS xamarinios was computed. 
Xamarin.Mac xamarinmac was computed. 
Xamarin.TVOS xamarintvos was computed. 
Xamarin.WatchOS xamarinwatchos was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (26)

Showing the top 5 NuGet packages that depend on OpenAI:

Package Downloads
Azure.AI.OpenAI The ID prefix of this package has been reserved for one of the owners of this package by

Azure OpenAI's official extension package for using OpenAI's .NET library with the Azure OpenAI Service.


Package Description


Available soon


VL/vvvv gamma nodeset wrapping the library, enabling access to OpenAI APIs from vvvv gamma


Package Description

GitHub repositories (5)

Showing the top 5 popular GitHub repositories that depend on OpenAI:

Repository Stars
.NET MAUI Samples
📖简易日语学习 / 视觉小说阅读辅助工具
All in one .wz file/map editor for MapleStory game files
Add chatGPT functionalities directly on Visual Studio
Hexagonal architecture showcase
Version Downloads Last updated
2.0.0-beta.4 1,551 6/10/2024
2.0.0-beta.3 3,111 6/7/2024
2.0.0-beta.2 348 6/6/2024
2.0.0-beta.1 279 6/6/2024
1.11.0 79,749 3/13/2024
1.10.0 144,528 12/14/2023
1.9.0 11,939 12/12/2023
1.8.0 9,231 12/6/2023
1.7.2 502,959 4/2/2023
1.7.1 1,281 4/2/2023
1.7.0 1,032 4/2/2023
1.6.0 51,919 3/9/2023
1.5.0 21,193 2/16/2023
1.4.0 11,273 2/3/2023
1.3.0 12,866 1/12/2023
1.2.0 39,019 12/22/2020
1.1.0 1,684 7/28/2020
1.0.0 2,304 7/23/2020

Adds new embedding models as of March 2024