Grok Delphi API Client

Grok, developed by xAI, is a high-performance AI model designed for fast, intelligent responses with real-time knowledge and advanced reasoning capabilities. For Delphi developers looking to integrate Grok into their applications, sgcWebSockets provides TsgcHTTP_API_Grok — a native component that wraps the entire xAI Grok API with clean, type-safe Delphi code.

Whether you are building conversational assistants, analyzing images, orchestrating tool-augmented workflows, or streaming real-time responses, this component gives you direct access to every Grok feature. No REST boilerplate. No JSON wrangling. Just drop the component, set your API key, and start building.

Complete API Coverage

Every major feature of the xAI Grok API is supported out of the box.

Getting Started

Integrate xAI Grok into your Delphi project in under a minute. Drop the component, configure your API key, and send your first message.

// Create the component and configure the API key
var
  Grok: TsgcHTTP_API_Grok;
  vResponse: string;
begin
  Grok := TsgcHTTP_API_Grok.Create(nil);
  Try
    Grok.GrokOptions.ApiKey := 'YOUR_API_KEY';

    // Send a simple message to Grok
    vResponse := Grok._CreateMessage(
      'grok-3', 'Hello, Grok!');

    ShowMessage(vResponse);
  Finally
    Grok.Free;
  End;
end;

Chat Completions & Streaming

The Chat Completions API is the foundation of every Grok interaction. Send text with optional system prompts, and receive responses synchronously or streamed in real-time.

System Prompts

Control Grok's behavior by providing a system prompt that sets the context, personality, or constraints for the conversation.

vResponse := Grok._CreateMessageWithSystem(
  'grok-3',
  'You are a helpful assistant that responds in Spanish.',
  'What is the capital of France?');
// Returns: "La capital de Francia es París."

Real-Time Streaming

For responsive user interfaces, stream Grok's response token-by-token using Server-Sent Events. Assign the OnHTTPAPISSE event handler and call _CreateMessageStream.

// Enable streaming via SSE
Grok.OnHTTPAPISSE := OnSSEEvent;
Grok._CreateMessageStream('grok-3',
  'Explain the theory of relativity.');

procedure TForm1.OnSSEEvent(Sender: TObject;
  const aEvent, aData: string; var Cancel: Boolean);
begin
  // aData: JSON payload with generated content
  Memo1.Lines.Add(aData);
end;

Advanced Typed API

For full control over request parameters — temperature, top-p, frequency penalty, presence penalty, stop sequences, number of completions — use the typed request and response classes.

var
  oRequest: TsgcGrokClass_Request_ChatCompletion;
  oMessage: TsgcGrokClass_Request_Message;
  oResponse: TsgcGrokClass_Response_ChatCompletion;
begin
  oRequest := TsgcGrokClass_Request_ChatCompletion.Create;
  Try
    oRequest.Model := 'grok-3';
    oRequest.MaxTokens := 2048;
    oRequest.Temperature := 0.7;
    oRequest.TopP := 0.9;
    oRequest.FrequencyPenalty := 0.5;
    oRequest.N := 1;

    oMessage := TsgcGrokClass_Request_Message.Create;
    oMessage.Role := 'user';
    oMessage.Content := 'Explain quantum computing in simple terms.';
    oRequest.Messages.Add(oMessage);

    oResponse := Grok.CreateMessage(oRequest);
    Try
      if Length(oResponse.Choices) > 0 then
        ShowMessage(oResponse.Choices[0].Message.Content);
    Finally
      oResponse.Free;
    End;
  Finally
    oRequest.Free;
  End;
end;

Vision — Image Understanding

Grok can analyze and reason about images. Send photographs, screenshots, diagrams, or charts alongside a text prompt and receive detailed descriptions, data extraction, or visual Q&A.

// Load an image and ask Grok to analyze it
var
  vBase64: string;
begin
  vBase64 := sgcBase64Encode(LoadFileToBytes('dashboard-screenshot.png'));

  ShowMessage(Grok._CreateVisionMessage(
    'grok-3',
    'Analyze this dashboard and summarize the key metrics.',
    vBase64, 'image/png'));
end;

Tool Use — Function Calling

Define custom tools with JSON Schema, and Grok will decide when and how to invoke them. This is the foundation for building agentic, multi-step workflows that connect the AI to your business logic.

var
  oRequest: TsgcGrokClass_Request_ChatCompletion;
  oTool: TsgcGrokClass_Request_Tool;
  oResponse: TsgcGrokClass_Response_ChatCompletion;
begin
  // Define a tool with JSON Schema
  oTool := TsgcGrokClass_Request_Tool.Create;
  oTool.Name := 'search_database';
  oTool.Description := 'Search the product database by keyword';
  oTool.Parameters :=
    '{"type":"object","properties":{"query":{"type":"string",' +
    '"description":"Search keyword"}},"required":["query"]}';
  oRequest.Tools.Add(oTool);
  oRequest.ToolChoice := 'auto';

  oResponse := Grok.CreateMessage(oRequest);

  // Check if Grok wants to call a tool
  if oResponse.Choices[0].FinishReason = 'tool_calls' then
  begin
    for i := 0 to Length(oResponse.Choices[0].Message.ToolCalls) - 1 do
    begin
      vToolId   := oResponse.Choices[0].Message.ToolCalls[i].Id;
      vFuncName := oResponse.Choices[0].Message.ToolCalls[i].FunctionCall.Name;
      vFuncArgs := oResponse.Choices[0].Message.ToolCalls[i].FunctionCall.Arguments;
      // Execute the tool and return the result
    end;
  end;

Model Management

Query available Grok models programmatically. List all models to discover new capabilities as they become available.

// List all available Grok models
vModels := Grok._GetModels;

// Typed API: access model properties directly
var
  oModels: TsgcGrokClass_Response_Models;
  i: Integer;
begin
  oModels := Grok.GetModels;
  Try
    for i := 0 to Length(oModels.Data) - 1 do
      Memo1.Lines.Add(oModels.Data[i].Id);
  Finally
    oModels.Free;
  End;
end;

Configuration & Options

Fine-tune the component behavior with comprehensive configuration options.

Request Parameters