The AI endpoint allows you to interact with the Rocket Networking AI service, powered by OpenAI. This endpoint allows you to make requests to generate AI-based responses using the GPT-3.5 Turbo model. You need to provide proper authentication using the Authorization header to access this endpoint.

Endpoint Details

  • URL:

  • HTTP Method: POST

  • Authentication: Include your serverId in the Authorization header for all requests.


The AI endpoint accepts POST requests with the following parameters:

Request Body

The request body should include the following fields:

  • messages: An array of message objects that form the conversation context. Each message object should have a role (either 'system', 'user', or 'assistant') and content containing the text of the message.

  • temperature: A floating-point value controlling the randomness of the AI's response. Higher values (e.g., 0.8) make the response more random, while lower values (e.g., 0.2) make it more deterministic.

Example Request Body

  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Tell me a joke."},
    {"role": "assistant", "content": "Why did the chicken cross the road?"}
  "temperature": 0.7,



Upon successful completion of the AI request, the API will return a JSON response with the following fields:

  • creditsUsed: The number of RNet credits used for this AI request.

  • message: The content of the AI-generated response.

Example Response

  "creditsUsed": 54,
  "message": "Because it wanted to get to the other side!"

Error Handling

  • If the request lacks proper authentication (missing or invalid Authorization header), the API will respond with a 401 Unauthorized status and an error message.

  • In case of internal server errors, the API will respond with a 500 Internal Server Error status.

Last updated