diff --git a/app/MindWork AI Studio/Provider/OpenAI/ChatRequest.cs b/app/MindWork AI Studio/Provider/OpenAI/ChatRequest.cs
new file mode 100644
index 0000000..79f89fd
--- /dev/null
+++ b/app/MindWork AI Studio/Provider/OpenAI/ChatRequest.cs	
@@ -0,0 +1,21 @@
+using System.ComponentModel.DataAnnotations;
+
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// The OpenAI chat request model.
+/// </summary>
+/// <param name="Model">Which model to use for chat completion.</param>
+/// <param name="Messages">The chat messages.</param>
+/// <param name="Stream">Whether to stream the chat completion.</param>
+/// <param name="Seed">The seed for the chat completion.</param>
+/// <param name="FrequencyPenalty">The frequency penalty for the chat completion.</param>
+public readonly record struct ChatRequest(
+    string Model,
+    IList<Message> Messages,
+    bool Stream,
+    int Seed,
+    
+    [Range(-2.0f, 2.0f)]
+    float FrequencyPenalty
+);
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/OpenAI/Message.cs b/app/MindWork AI Studio/Provider/OpenAI/Message.cs
new file mode 100644
index 0000000..508645b
--- /dev/null
+++ b/app/MindWork AI Studio/Provider/OpenAI/Message.cs	
@@ -0,0 +1,8 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Chat message model.
+/// </summary>
+/// <param name="Content">The text content of the message.</param>
+/// <param name="Role">The role of the message.</param>
+public readonly record struct Message(string Content, string Role);
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/OpenAI/ModelResponse.cs b/app/MindWork AI Studio/Provider/OpenAI/ModelResponse.cs
new file mode 100644
index 0000000..6abf39d
--- /dev/null
+++ b/app/MindWork AI Studio/Provider/OpenAI/ModelResponse.cs	
@@ -0,0 +1,7 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// A data model for the response from the model endpoint.
+/// </summary>
+/// <param name="Data"></param>
+public readonly record struct ModelsResponse(IList<Model> Data);
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs b/app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs
new file mode 100644
index 0000000..ed5abfe
--- /dev/null
+++ b/app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs	
@@ -0,0 +1,188 @@
+using System.Net.Http.Headers;
+using System.Runtime.CompilerServices;
+using System.Text;
+using System.Text.Json;
+
+using AIStudio.Chat;
+using AIStudio.Settings;
+
+using Microsoft.JSInterop;
+
+using MudBlazor;
+
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// The OpenAI provider.
+/// </summary>
+public sealed class ProviderOpenAI() : BaseProvider("https://api.openai.com/v1/"), IProvider
+{
+    private static readonly JsonSerializerOptions JSON_SERIALIZER_OPTIONS = new()
+    {
+        PropertyNamingPolicy = JsonNamingPolicy.SnakeCaseLower,
+    };
+    
+    #region Implementation of IProvider
+
+    /// <inheritdoc />
+    public string Id => "OpenAI";
+
+    /// <inheritdoc />
+    public string InstanceName { get; set; } = "OpenAI";
+
+    /// <inheritdoc />
+    public async IAsyncEnumerable<string> StreamChatCompletion(IJSRuntime jsRuntime, SettingsManager settings, Model chatModel, ChatThread chatThread, [EnumeratorCancellation] CancellationToken token = default)
+    {
+        // Get the API key:
+        var requestedSecret = await settings.GetAPIKey(jsRuntime, this);
+        if(!requestedSecret.Success)
+            yield break;
+
+        // Prepare the system prompt:
+        var systemPrompt = new Message
+        {
+            Role = "system",
+            Content = chatThread.SystemPrompt,
+        };
+        
+        // Prepare the OpenAI HTTP chat request:
+        var openAIChatRequest = JsonSerializer.Serialize(new ChatRequest
+        {
+            Model = chatModel.Id,
+            
+            // Build the messages:
+            // - First of all the system prompt
+            // - Then none-empty user and AI messages
+            Messages = [systemPrompt, ..chatThread.Blocks.Where(n => n.ContentType is ContentType.TEXT && !string.IsNullOrWhiteSpace((n.Content as ContentText)?.Text)).Select(n => new Message
+            {
+                Role = n.Role switch
+                {
+                    ChatRole.USER => "user",
+                    ChatRole.AI => "assistant",
+                    ChatRole.SYSTEM => "system",
+
+                    _ => "user",
+                },
+
+                Content = n.Content switch
+                {
+                    ContentText text => text.Text,
+                    _ => string.Empty,
+                }
+            }).ToList()],
+
+            Seed = chatThread.Seed,
+            
+            // Right now, we only support streaming completions:
+            Stream = true,
+            FrequencyPenalty = 0f,
+        }, JSON_SERIALIZER_OPTIONS);
+
+        // Build the HTTP post request:
+        var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+        
+        // Set the authorization header:
+        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", requestedSecret.Secret);
+        
+        // Set the content:
+        request.Content = new StringContent(openAIChatRequest, Encoding.UTF8, "application/json");
+        
+        // Send the request with the ResponseHeadersRead option.
+        // This allows us to read the stream as soon as the headers are received.
+        // This is important because we want to stream the responses.
+        var response = await this.httpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, token);
+        
+        // Open the response stream:
+        var openAIStream = await response.Content.ReadAsStreamAsync(token);
+        
+        // Add a stream reader to read the stream, line by line:
+        var streamReader = new StreamReader(openAIStream);
+        
+        // Read the stream, line by line:
+        while(!streamReader.EndOfStream)
+        {
+            // Check if the token is cancelled:
+            if(token.IsCancellationRequested)
+                yield break;
+            
+            // Read the next line:
+            var line = await streamReader.ReadLineAsync(token);
+            
+            // Skip empty lines:
+            if(string.IsNullOrWhiteSpace(line))
+                continue;
+            
+            // Skip lines that do not start with "data: ". Regard
+            // to the specification, we only want to read the data lines:
+            if(!line.StartsWith("data: ", StringComparison.InvariantCulture))
+                continue;
+
+            // Check if the line is the end of the stream:
+            if (line.StartsWith("data: [DONE]", StringComparison.InvariantCulture))
+                yield break;
+
+            ResponseStreamLine openAIResponse;
+            try
+            {
+                // We know that the line starts with "data: ". Hence, we can
+                // skip the first 6 characters to get the JSON data after that.
+                var jsonData = line[6..];
+                
+                // Deserialize the JSON data:
+                openAIResponse = JsonSerializer.Deserialize<ResponseStreamLine>(jsonData, JSON_SERIALIZER_OPTIONS);
+            }
+            catch
+            {
+                // Skip invalid JSON data:
+                continue;
+            }    
+            
+            // Skip empty responses:
+            if(openAIResponse == default || openAIResponse.Choices.Count == 0)
+                continue;
+            
+            // Yield the response:
+            yield return openAIResponse.Choices[0].Delta.Content;
+        }
+    }
+
+    #pragma warning disable CS1998 // Async method lacks 'await' operators and will run synchronously
+    /// <inheritdoc />
+    public async IAsyncEnumerable<ImageURL> StreamImageCompletion(IJSRuntime jsRuntime, SettingsManager settings, Model imageModel, string promptPositive, string promptNegative = FilterOperator.String.Empty, ImageURL referenceImageURL = default, [EnumeratorCancellation] CancellationToken token = default)
+    {
+        yield break;
+    }
+    #pragma warning restore CS1998 // Async method lacks 'await' operators and will run synchronously
+
+    /// <inheritdoc />
+    public async Task<IList<Model>> GetTextModels(IJSRuntime jsRuntime, SettingsManager settings, CancellationToken token = default)
+    {
+        return await this.LoadModels(jsRuntime, settings, "gpt-", token);
+    }
+
+    /// <inheritdoc />
+    public async Task<IList<Model>> GetImageModels(IJSRuntime jsRuntime, SettingsManager settings, CancellationToken token = default)
+    {
+        return await this.LoadModels(jsRuntime, settings, "dall-e-", token);
+    }
+
+    #endregion
+
+    private async Task<IList<Model>> LoadModels(IJSRuntime jsRuntime, SettingsManager settings, string prefix, CancellationToken token)
+    {
+        var requestedSecret = await settings.GetAPIKey(jsRuntime, this);
+        if(!requestedSecret.Success)
+            return new List<Model>();
+        
+        var request = new HttpRequestMessage(HttpMethod.Get, "models");
+        request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", requestedSecret.Secret);
+        
+        var emptyList = new List<Model>();
+        var response = await this.httpClient.SendAsync(request, token);
+        if(!response.IsSuccessStatusCode)
+            return emptyList;
+
+        var modelResponse = await response.Content.ReadFromJsonAsync<ModelsResponse>(token);
+        return modelResponse.Data.Where(n => n.Id.StartsWith(prefix, StringComparison.InvariantCulture)).ToList();
+    }
+}
\ No newline at end of file
diff --git a/app/MindWork AI Studio/Provider/OpenAI/ResponseStreamLine.cs b/app/MindWork AI Studio/Provider/OpenAI/ResponseStreamLine.cs
new file mode 100644
index 0000000..0e938fd
--- /dev/null
+++ b/app/MindWork AI Studio/Provider/OpenAI/ResponseStreamLine.cs	
@@ -0,0 +1,25 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data model for a line in the response stream, for streaming completions.
+/// </summary>
+/// <param name="Id">The id of the response.</param>
+/// <param name="Object">The object describing the response.</param>
+/// <param name="Created">The timestamp of the response.</param>
+/// <param name="Model">The model used for the response.</param>
+/// <param name="SystemFingerprint">The system fingerprint; together with the seed, this allows you to reproduce the response.</param>
+/// <param name="Choices">The choices made by the AI.</param>
+public readonly record struct ResponseStreamLine(string Id, string Object, uint Created, string Model, string SystemFingerprint, IList<Choice> Choices);
+
+/// <summary>
+/// Data model for a choice made by the AI.
+/// </summary>
+/// <param name="Index">The index of the choice.</param>
+/// <param name="Delta">The delta text of the choice.</param>
+public readonly record struct Choice(int Index, Delta Delta);
+
+/// <summary>
+/// The delta text of a choice.
+/// </summary>
+/// <param name="Content">The content of the delta text.</param>
+public readonly record struct Delta(string Content);
\ No newline at end of file