Requests

Message Generation

Learn how to generate AI responses using the Messages API.

Endpoint

POST /v1/chat/completions

Request Body

{
  "model": string,
  "messages": array,
  "temperature": float = 0.7,
  "stream": boolean = false,
  "max_tokens": integer = null,
  "top_p": float = 1,
  "frequency_penalty": float = 0,
  "presence_penalty": float = 0,
  "stop": array[string] | null
}

Parameters

• model(required) - Model ID to use (e.g., "Reverix-Prod")

• messages(required) - Array of message objects with role and content

• temperature(optional) - Controls randomness (0-1)

• stream(optional) - Enable streaming response mode

• max_tokens(optional) - Maximum tokens to generate

• top_p(optional) - Nucleus sampling parameter

• frequency_penalty(optional) - Reduces repetition (-2.0 to 2.0)

• presence_penalty(optional) - Encourages new topics (-2.0 to 2.0)

• stop(optional) - Array of sequences where generation should stop

Example Request

curl -X POST "https://api.reverix.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Reverix-Prod",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write a function to calculate Fibonacci numbers"}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Rate Limits

The API is rate limited to 5 requests per second per API key. Requests exceeding this limit will receive a 429 status code.