Quickstart
Your first Chat Completion request
Make a test call to Unreal OpenAI backend using an API key.
Your first Chat Completion request
With an API key in hand, you’re ready to call the Unreal OpenAI endpoint.
Example (curl)
curl https://openai.ideomind.org/v1/chat/completions \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "llama4-scout-instruct-basic",
"messages": [{"role": "user", "content": "Hello, world!"}]
}'Response should look like:
{
"id": "bcd29fca-6ab9-96b3-af8f-091565c3ba73",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "Hi! How can I help you today? Is there anything you would like to talk about or ask about? I'm here to help with any questions you might have. Just let me know what's on your mind.",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1752388097,
"model": "accounts/fireworks/models/mixtral-8x22b-instruct",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": null,
"usage": {
"completion_tokens": 47,
"prompt_tokens": 5,
"total_tokens": 52,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}