Introduction
The Invicta AI API provides a simple and powerful way to send prompts to our AI agents and receive intelligent responses. Whether you’re building a chatbot, automating customer support, or creating innovative AI-powered applications, our API offers the flexibility and functionality you need.Authentication
All API requests require authentication using an API key. You must include your API key in theX-INVICTA-API header for each request.
Base URL
All API requests should be made to:Endpoints
Send Prompt
This endpoint allows you to send a prompt to an AI agent and receive a response.HTTP Request
Headers
| Header | Type | Required | Description |
|---|---|---|---|
| X-INVICTA-API | string | Yes | Your unique API key for authentication |
| Content-Type | string | Yes | Must be set to application/json |
Request Body Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| userInput | string | Yes | The prompt for the AI agent |
| variables | array | Yes | Key-value pairs for customizing the system prompt |
| threadId | string | No | Identifier for maintaining conversation context |
| modelName | string | No | Specific AI model to use for the response |
Variables Array Structure
Example Request
Response
The API returns a JSON object with the following structure:Error Handling
The API uses standard HTTP status codes to indicate the success or failure of a request.| Status Code | Meaning |
|---|---|
| 200 | OK |
| 400 | Bad Request |
| 401 | Unauthorized |
| 404 | Not Found |
| 500 | Internal Server Error |
Example Error Response
Best Practices
- Always use HTTPS for secure communication.
- Store your API key securely and never expose it in client-side code.
- Implement proper error handling in your application to gracefully manage API errors.
- Use the
threadIdparameter for maintaining context in multi-turn conversations. - Consider rate limiting and implement retries with exponential backoff for robust integration.