Generate Text with AI Chat

The chat completions API allows you to have dynamic conversations with Unreal's advanced AI models. Use this endpoint to generate responses for chatbots, content creation, question answering, and more.

Quick Example

curl -X POST https://openai.ideomind.org/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "r1-1776",
    "messages": [
      { "role": "user", "content": "Explain quantum computing in simple terms" }
    ]
  }'

Response Format

{
  "id": "chatcmpl-123abc456def789",
  "object": "chat.completion",
  "created": 1694268762,
  "model": "r1-1776",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing is like having a very special deck of cards. Normal computers use regular cards that can only be face up or face down (0 or 1). But quantum computers use magical cards that can be face up, face down, or somehow both at the same time until you look at them! This ability to be in multiple states at once lets quantum computers solve certain problems much faster than regular computers."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 185,
    "total_tokens": 199
  }
}

Request Parameters

Parameter	Type	Description
`model`	string	Required. ID of the model to use (e.g., `r1-1776`)
`messages`	array	Required. Array of message objects with `role` and `content`
`temperature`	number	Controls randomness (0-2, default: 1)
`max_tokens`	integer	Maximum tokens to generate (default varies by model)
`stream`	boolean	Whether to stream responses (default: false)

Advanced Usage

Multi-Turn Conversations

Include the complete conversation history to maintain context:

{
  "model": "mixtral-8x22b-instruct",
  "messages": [
    { "role": "user", "content": "What's the weather like today?" },
    { "role": "assistant", "content": "I don't have access to real-time weather data." },
    { "role": "user", "content": "What information can you provide?" }
  ]
}

Streaming Responses

Enable streaming for real-time generation:

curl -X POST https://openai.ideomind.org/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mixtral-8x22b-instruct",
    "messages": [{ "role": "user", "content": "Hello" }],
    "stream": true
  }'

Streamed responses are delivered as server-sent events:

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268762,"model":"mixtral-8x22b-instruct","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]}

Need help? Join our community on Discord or Telegram

Chat Completions