Endpoints

API2.0

POSThttps://api.onlysq.ru/ai/v2

Generates a text response to a user message(s).

Starting with patch 4.0.1 beta (November 29, 2025), every request to v2/imagen must have Authorization header.

json

{"Authorization": "Bearer apikey"}

Basic API key is openai.

Request

This endpoint expects an object.

model (string, required)
The name of a OnlySq AI model which will process the request.
request (dict, required)
Query data dictionary containing:
- messages (list, required) - Chat messages in order.
- meta (dict, optional) - previously used by ImaGen.
- image_count (int, optional) - previously used when generating with ImaGen.

Response

id (string) - Unique identifier.
object (string) - Object init for OpenAI SDK.
created (int) - UNIX timestamp.
model (string) - Model that processed the request.
choices (list) - completion choices: index, message, finish_reason
usage (dict) - prompt_tokens, completion_tokens, total_tokens
user (int) - Unique of user by API key.

Sync Request Example

python

import requests

headers = {
    "Authorization": "Bearer openai"
}

send = {
    "model": "gemini-2.5-flash",
    "request": {
        "messages": [
            {
                "role": "user",
                "content": "Hi! Write a short one-line story"
            }
        ]
    }
}

request = requests.post('http://api.onlysq.ru/ai/v2', json=send, headers=headers)
response = request.json()
print(response)

Response Example

json

{
  "id": "chat_XBt6z670WKm7L9BVoCcLZLzTNZ03UJhD6sWqAEUyTgaJvhJA",
  "object": "chat.completion",
  "created": 1745146202,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\"Under the full moon, the werewolf realized he'd forgotten his keys—again.\"",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 11,
    "completion_tokens": 19,
    "total_tokens": 30
  },
  "user": 0
}

Streaming Request Example

python

import requests, json

url = "http://api.onlysq.ru/ai/v2"

data = {
    "model": "gpt-4o-mini",
    "request": {
        "messages": [
            {
                "role": "user",
                "content": "Write a one-line story about AI."
            }
        ],
        "stream": True
    }
}

with requests.post(url, json=data, stream=True) as response:
    if response.status_code == 200:
        for line in response.iter_lines():
            if line:
                decoded_line = line.decode('utf-8').strip()
                if decoded_line.startswith("data: "):
                    decoded_line = decoded_line[len("data: "):]
                if decoded_line == "[DONE]":
                    break
                chunk = json.loads(decoded_line)
                content = chunk["choices"][0]["delta"].get("content")
                if content:
                    print(content, end="", flush=True)
    else:
        print(response.status_code, response.text)

Console output:

"After mastering human emotions, the AI sighed and shut itself down, realizing loneliness wasn't worth the code."

Streaming Chunk Example

json

{
  "id": "chatcmpl_lQdhTfXn4yKoDlyCjuBpL0GfPZNonZufGqOyGl3wVpMhJRwP",
  "object": "chat.completion.chunk",
  "created": 1750612428,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "te",
        "role": "assistant"
      },
      "finish_reason": null
    }
  ],
  "usage": null
}

Learn more in docs